DE102022209875A1 - Computer-implemented method and device for detecting an irregularity in a first system - Google Patents

Abstract

The invention relates to a computer-implemented method and a device for detecting an irregularity in a first system. The method includes providing target information of a first system, wherein the target information characterizes at least one target value of at least one measurement variable of the first system during a repeatable process, wherein the target information, in particular the target value, during a first execution of the process is recorded. The method further comprises recording actual information of the first system, wherein the actual information characterizes at least one actual value of the at least one measured variable of the first system during a current repetition of the process, the current repetition occurring after the first execution of the repetition carried out in the process. The method further includes determining at least one irregularity of the first system based on at least one deviation of the actual value from the target value of the at least one measured variable.

Description

The invention relates to a computer-implemented method and a device for detecting an irregularity in a first system.

Most error detection measures in systems such as vehicles are designed to avoid dangers and therefore often only intervene very late in a chain of errors. Examples of this are the failure of headlight lamps, where if the lamp burns out, for example, current flow can no longer be measured and a failure of the lamp is therefore detected. Accordingly, a user of the vehicle with a defective lamp must then go to a workshop and have it replaced, which can be safety-critical.

In general, an error is only detected when it exists. In addition to a reduction in security, this can also lead to other disadvantages such as system failure.

It is therefore an object of the present invention to provide a computer-implemented method and a device which eliminate or at least improve one or more of the aforementioned disadvantages. It is a particular object of the present invention to provide a computer-implemented method and a device which enable early and simple detection of errors, degradations and/or performance limitations in order to ensure early hazard prevention as well as planned maintenance or a temporary failure of the corresponding system to enable.

According to a first aspect, the task is solved by a computer-implemented method for detecting an irregularity of a first system, comprising providing target information of a first system, wherein the target information contains at least a target value of at least one measured variable of the first system of a repeatable process, wherein the target information, in particular the target value, is recorded during a first execution of the process. The method further comprises recording actual information of the first system, wherein the actual information characterizes at least one actual value of the at least one measured variable of the first system during a current repetition of the process, the current repetition occurring after the first execution of the repetition carried out in the process. The method further includes determining at least one irregularity of the first system based on at least one deviation of the actual value from the target value of the at least one measured variable.

The target information and the target value are recorded when the process is first executed. The first execution can actually be a first execution and/or implementation of the process. Alternatively, the first execution may be an execution of the process before the current iteration, recording the target information and target value. The first embodiment can alternatively or additionally include at least one, two, three or more simulations of the process, with the target information and the target value being determined by simulating the process. For two or more simulations, the target information can be determined by averaging the actual values of the simulations. The actual information and the actual value are recorded during a current iteration and compared with the target values from the previous first execution of the process. The process can be an at least partially, in particular completely, automated process. The process can be a process of an at least partially, in particular completely autonomous vehicle. The vehicle can be an L4 or L5 vehicle. The vehicle can be a car, a motorcycle, a bus or the like. The process can be a predetermined route. The vehicle can be set up to drive this route repeatedly. During a first execution or journey, the target information is recorded, whereby the measured variable can be the speed. If the process or trip is repeated after the first execution, the actual information is recorded. While driving, it can be determined that at a specific local and/or temporal section of the route the actual information, in particular the actual value of the speed, deviates from the target information, in particular the target value, and accordingly an irregularity exists. The irregularity can be due to at least one of a fault, a drift, a degradation, a comfort, in particular a loss of comfort, preferably in relation to passenger transport, a limitation in performance, a failure of an element of the system or the (entire) system and wear of the Element or the system, for example, indicate wear of a tire tread on a wheel of the vehicle. However, the tire tread does not have to be completely worn out and a braking distance may have been longer than in the target information, so that the speed of the vehicle decreased more slowly than in the target information. Accordingly, early on based on the at least one Irregularities, a change in the system can be detected, especially those that are safety-critical and/or process-critical.

According to the invention, the at least one measurement variable can be viewed holistically during the process and a change in the actual values compared to the target values can be an indication that an irregularity exists. Accordingly, even before a failure, process and/or performance limitation of the system, it can be recognized that one or more elements of the system have a defect and/or no longer function properly. Accordingly, an analysis of the first system is simplified and can be carried out in a much more resource-efficient manner compared to detailed analyzes in which additional calculations and modeling sometimes take place. Furthermore, using the proposed method, the system and the individual elements can be viewed in a coherent manner and there is no need for individual observation of the individual elements, so that monitoring of the individual elements can be reduced.

Determining the at least one irregularity may be determining the at least one irregularity during the current iteration of the process. Consequently, a live determination of at least one irregularity can be made.

The target and/or actual information, in particular the at least one target and/or actual values, can be characterized by a time and/or a position, in particular a location, so that a temporal and/or spatial assignment can take place. For this purpose, the method can further include detecting a (local) position of the system during the process. Alternatively or additionally, the target and/or actual information and the target and/or actual values can characterize the at least one measurement variable of the one or more elements of the system. Furthermore, the measured variables of the elements can be at least partially different and/or identical. Accordingly, a variety of measurement variables can be considered.

Two, three or more target and/or actual values of a measurement variable can be recorded. For example, the speed of the vehicle along the route can be recorded, with the speed varying along the route. A corresponding number of different values can be recorded. Additionally or alternatively, at least one target value and/or at least one actual value of two, three or more measured variables of the system and/or the individual elements can be recorded.

Recording the actual information of the first system can include recording actual information of a first measured variable of the first system and recording actual information of a second measured variable of the first system, wherein the actual information of the first and second measured variables is at least one actual -Characterize the value of the first and second measured variables of the first system during a current repetition of the process. Providing the target information of the first system can further include providing target information of the first measured variable and/or providing target information of the second measured variable, wherein the target information comprises at least a target value of the first and second measured variable characterize the first system during a repeatable process. Determining the at least one irregularity of the first system can alternatively or in addition to determining the at least one irregularity of the first system based on the at least one deviation of the actual value from the target value of the at least one measured variable determine the at least one irregularity based on comparing a first slope of the actual values of the first measured variable and a second slope of the actual values of the second measured variable in a predetermined time period and / or local section of the actual information, the first and second slopes in a target State of the system is in a predetermined relationship to one another. The method further includes determining the at least one irregularity in the event of a deviation from the predetermined ratio. The first measurement variable can be a power consumption and the second measurement variable can be a driving speed of the vehicle, in particular an electrically driven vehicle. When the vehicle accelerates, more electricity is consumed, so that a corresponding drive of the current and the driving speed can be determined. If the vehicle's electric drive is partially defective, this could lead to increased power consumption, although there is no proportionally higher acceleration. Accordingly, comparing the actual values of two or more actual information from two or more measured variables can indicate the irregularity.

The method can further include updating the target information, in particular the target value. The target information, in particular the target value, can be determined and/or updated after a predetermined number of repetitions of the process. Updating the target information can occur when the predetermined number of repetitions of the process occurs without determining the irregularity is. The predetermined number of repetitions may be 10, 50, 100, 500 or more.

The repeatable process may be a process that is repeatable by the system at least twice, three times or more. As an alternative to the at least partially autonomous vehicle, the system can be a manufacturing system for producing a product, with the individual production steps being identical for each product. Consequently, the manufacturing process for each product is identical in terms of production steps. Accordingly, it can be a repeatable process. Furthermore, the system can be an at least partially autonomous, in particular completely autonomous, bus. The omnibus can be an L4 or L5 omnibus. The bus can be set up to travel a predetermined route. The bus can travel this route several times a day, making it a repeatable process.

The target information, in particular the target value, can be provided by a manufacturer, a user and/or another system.

The method can further comprise providing actual information of at least a second system, wherein the actual information of the second system characterizes at least one actual value of the at least one measured variable of the second system during the process. Furthermore, the method can determine the irregularity of the first system as a temporary irregularity based on an agreement of the actual values of the first and second systems at least in a temporal and / or local section of the deviation of the actual value of the first system from the target Value of the first system include. Alternatively or additionally, the method may include determining the irregularity of the first system as an irregularity to be examined based on a deviation of the actual values of the first and second systems at least in the temporal and/or local portion of the deviation of the actual value of the first system from the target value of the first system.

The second system can be structurally identical and/or have the same type as the first system or be different from it. The first and second systems can each be an at least partially autonomous vehicle or a manufacturing system for producing a product. The first and second systems can be identical in construction, for example the same type of small car. Alternatively, the first system may be a small car and the second vehicle may be an off-road vehicle. If both vehicles travel the same predetermined route, at least some of the actual information, in particular the actual values, can be compared with one another. In particular, the two systems can have at least partially similar and/or identical target values. This can be, for example, a speed along the route. For example, the target information of the first vehicle can relate to a shock absorber setting of the first vehicle, with the target value remaining constant at one value along the route.

However, the actual information of the first vehicle shows a deviation from the target information at a specific location and/or time period. For example, it can be a newly created pothole that was not present when the route was first carried out or the first time it was driven. The deviation of the actual value from the target value is identified as an irregularity. This can be an irregularity that actually indicates a fault, a defect or something similar in the shock absorbers. To check, the actual value of the first vehicle can be compared with the actual value of the second vehicle. Even if the vehicles are of different designs, the recording of the measured variable of the shock absorber of the second vehicle in the temporal and / or spatial section of the pothole will also show a change in the measured variable. Accordingly, it can be concluded that this is an external change, in this case the route or the road, and not an irregularity in the first vehicle, so that the first vehicle would not have to go to the workshop. If instead a similar deflection of the shock absorber of the second vehicle were not detected and the actual value of the first vehicle also deviated from the actual value of the second vehicle, it can be concluded that the shock absorber of the first vehicle should be examined.

In the previous example, it was only compared with another second system, whereby the actual value can be compared with actual values from three, four or more systems. Furthermore, actual values of several measured variables of the first system can be recorded and compared accordingly with several actual values of the several measured variables of the several systems. In particular, the values of the individual measured variables can be compared with one another.

When determining the at least one irregularity as a temporary irregularity, the target information, in particular the target value of the first system, can be adjusted. In particular, the adjustment can be made in such a way that the temporary irregularity is part the target values are and / or supplemented and / or exchanged accordingly and there is therefore no longer a deviation between the actual values and the target values of the first system. The adjustment may occur when the process has been repeated a predetermined number of times and each of the predetermined number of repetitions is the temporary irregularity.

Matching the actual values of the first and second systems may be a match to a predetermined match threshold. The deviation of the actual values of the first and second systems from one another can be a deviation by a predetermined deviation threshold value. The agreement threshold can be determined depending on the deviation threshold. The agreement threshold can be 80%, in particular 80%, so that a match of at least 80%, in particular 90%, is a match. The deviation threshold value can be 80%, in particular 90%, so that a deviation of more than 80%, in particular more than 90%, constitutes a deviation. The agreement threshold can be at least partially identical and/or different for two, three or more actual values of different measured variables.

Alternatively or additionally, the agreement of the at least one actual value and the at least one target value can be determined in the form of a function and its function value. The function can include the at least one actual value and/or the at least one target value as input parameters and output a function value. The function value can indicate the agreement and/or the deviation of the at least one actual value from the at least one target value. For example, the power consumption of second components of the vehicle can be considered. The power consumption of the first component can be the actual value and the power consumption of the second component can be another actual value. For example, the power consumption of the second component should be twice as high as the power consumption of the first component. Consequently, the function would be designed in such a way that the function value reflects a factor of two, whereby the factor two is the target value here.

The method may include recording a plurality of initial information of the first system, wherein the initial information characterizes at least one recorded value of the at least one measurement variable of the first system during the first execution and further repetitions of the process that are carried out in time before the current repetition become. The method can further include determining the target information of the first system, in particular the target value of the first system, based on the plurality of recorded initial pieces of information, in particular the recorded values of the at least one measured variable of the first system. The repetitions of the initial information process can be performed before the current repetition, so that the desired information is already present before the actual information is recorded.

Determining the target information, in particular determining the at least one target value, can be an averaging of the recorded values of the initial information. Alternatively or additionally, determining the target information can include linearizing and/or polygonal averaging of the recorded values of the initial information.

By determining the target values based on the large number of initial pieces of information, which can be two, three or more, averaged target information, in particular target values, can be determined.

The deviation of the actual value from the target value of the first system can include a deviation of the actual value from the target value of the first system by a predetermined first threshold value, the first threshold value being in particular 20%, 10%, or 5%. is. The deviation of the actual value from the target value can be at least partially identical and/or different for two, three or more different measured values.

Threshold values and deviations mentioned above and below can additionally or alternatively be characterized by an absolute deviation and/or a gradient.

The first threshold value, the deviation threshold value and/or the agreement threshold value can be determined based on the plurality of initial information, in particular the plurality of values of the at least one measurement variable of the plurality of initial information. A bounding box can be determined based on the initial information. The first threshold, the deviation threshold, and/or the match threshold may be determined based on and/or correspond to the bounding box.

The repeatable process may be the repeatable route. The route can only have a start position, an end position and a path from the start position to the end position be ized. Additionally or alternatively, the route can be characterized by at least one or more speeds, braking processes, flashing processes, door opening and closing processes and at least one or more speeds. The route can be further or alternatively characterized by further measured variables that are provided and/or can be recorded by the first system, in particular the first vehicle. Alternatively, the repeatable process can be the manufacturing process or any other repeatable process in which the at least one measurement variable can be recorded repeatedly.

The at least one measurement variable can be one of a network utilization, a noise level, one or more data streams, a level of the data stream or data streams, a power consumption, a signal frequency of a signal, a spectral analysis and / or a Fourier analysis of one or the signal of the first system and/or at least one component of the first system is characterized. The network utilization can be characterized by the number of communicated data packets. Alternatively or additionally, the at least one measurement variable can be a derivative of one of the aforementioned measurement variables. The derivative can be and/or comprise a first, a second and/or a third derivative.

Alternatively or additionally, the network utilization can characterize a number of currently sending and/or receiving elements of the system and/or external units, hence a number of communicating elements and/or units of the network. The signals may be input and/or output signals of the system and/or the elements of the system. One of the data streams can be a data stream based on input and/or output signals of an element, in particular a data bus. A total data rate, in particular a total input data rate and/or a total output data rate of the data bus, can be characterized.

Alternatively or additionally, one of the data streams can be characterized at a specific interface or a specific element of the system. There should be a certain data rate at this particular interface, for example if all cameras in a vehicle work as a system. If one of the cameras is at least partially defective, a change in the data rate at this interface can indicate this defect. Accordingly, an irregularity would be determined when comparing the target values and the actual values of the data rate.

The level of a data stream can characterize at least one amplitude of an input and/or output signal of at least one of the elements and/or the system. In the case of a data bus, a voltage of the data bus can be characterized as a level. With a microphone, the sound pressure level can be characterized.

Alternatively or additionally, the at least one measurement variable can be one of a speed, an acceleration, a rotation rate, an angular velocity, a control angle for controlling the direction of the vehicle, a power consumption, a fuel consumption, one or more braking times, one or more braking strengths, in particular the one or the multiple braking times, a turn signal state of at least one turn signal, a headlight state of at least one headlight, a brake light state of at least one brake light, a vehicle door state of at least one vehicle door, an acceleration, a speed of at least one drive and / or a wheel of the vehicle. The at least one measurement variable can be an actual measurement variable, in particular a reaction of the vehicle to one or more control commands. An actuating command can be one of a steering angle, a brake pressure, a motor current, a door state, a power consumption and a state of lighting of the vehicle. Accordingly, the actual measurement quantity may be the actual steering angle, the actual brake pressure, the actual motor current, the actual door condition, the actual power consumption and the actual lighting condition.

The method can further include storing the actual information of the first system, in particular when determining the at least one irregularity, in particular the irregularity to be examined, of the first system, wherein at least the temporal and / or spatial section of the deviation of the actual value from the Target value of the first system is saved. Alternatively, only the temporal and/or spatial portion of the deviation can be saved. The recorded actual values can be stored in a ring buffer during the process. If the ring buffer is full, the oldest stored data is overwritten with the newest data. In order to check a later analysis of the irregularity, the actual information, in particular the irregularity, can be stored in a long-term memory in order to make it available later, for example to a workshop or via a network. The storage can include storing further information about the vehicle, which can in particular be provided by the vehicle. Ent Speaking of this, when an irregularity is determined, further information from the vehicle can be used for further analysis.

The method can further include outputting a maintenance signal when determining the at least one irregularity, in particular the irregularity of the system to be examined. The maintenance signal can be issued to a manufacturer of the system, a workshop and/or a user of the system.

The method may further include adjusting, in particular temporally adjusting, a timetable of the vehicle at least partially based on the irregularity. For example, the at least one measured value can characterize a door status of the system, in particular of a bus. Along the predetermined route, predetermined opening and closing processes and/or times are predetermined in the form of the target values. It may happen that opening times are longer than planned due to a high volume of people. The timetable can be adjusted accordingly.

The at least one measurement variable can additionally or alternatively be at least one of a time, a day, a year, a season, a traffic volume, a condition of at least one road traveled by the vehicle during the process, a number of passengers of the vehicle, a type of the first and/or second system and a date of manufacture of the first and/or second system.

The object is achieved according to a second aspect by a device for detecting an irregularity of a first system, comprising a memory which is set up to provide target information of a first system, wherein the target information contains at least a target value of at least one measured variable first system characterized during a repeatable process, wherein the target information, in particular the target value, is recorded during a first execution of the process. The device further comprises a recording unit which is set up to record actual information of the first system, wherein the actual information characterizes at least one actual value of the at least one measured variable of the first system during a current repetition of the process, the current repetition being a is a repetition carried out after the first execution of the process. The device further comprises a processor which is set up to determine at least one irregularity of the first system based on at least one deviation of the actual value from the target value of the at least one measured variable.

Previously mentioned and described method features of the method according to the first aspect can be implemented as device features of the device according to the second aspect. The device may include additional means that are designed to carry out the method steps and/or features.

The recording unit can be set up to receive the actual information from one of the first system and/or one or more elements of the first system and/or the actual information from the second system and/or one or more elements of the second system and to be recorded accordingly. Alternatively or additionally, the recording unit can be set up to record the actual information of the first and/or second systems. The recording unit can be or include a sensor and/or a transceiver. The recording unit can be set up to record the aforementioned values of the measured variables. The recording unit can have appropriate means for this purpose, such as an ammeter, a voltage meter, a microphone, a camera, a data stream meter, etc.

The memory may be non-volatile memory. The memory may be or include a ring buffer. Alternatively or additionally, the memory may include or be a long-term memory.

The recording unit can be set up to record the variety of initial information of the first system. Furthermore, the processor can be designed to determine the target information based on the plurality of initial information.

The processor can be set up to determine the target information, in particular to determine the at least one target value based on the averaging of the recorded values. Alternatively or additionally, the processor can be set up to determine the target information by linearizing and/or polygonally averaging the recorded values.

The memory can be set up to store the actual information of the first system, in particular when determining the at least one irregularity, in particular the irregularity of the first system to be examined, at least the temporal and / or spatial Section of the deviation of the actual value from the target value of the first system is saved.

The device can include a communication unit. The communication unit can be set up to output a maintenance signal when determining the at least one irregularity, in particular the irregularity of the system to be examined. The maintenance signal can be issued to a manufacturer of the system, a workshop and/or a user of the system.

The processor can be set up to adapt a timetable of the vehicle at least partially based on the irregularity, in particular to adapt it in time.

The memory can be set up to store a computer program product according to the following third and/or fourth aspect. Furthermore, the processor can be set up to execute the computer program product.

The object is solved according to a third aspect by a computer program product comprising program code sections for executing a computer-implemented method according to the first aspect when the computer program is executed by at least one processor. Alternatively or additionally, the task according to a fourth aspect is solved by a computer program product, comprising instructions that cause the device according to the second aspect to carry out the method steps of the method according to the first aspect.

The object is solved according to a fifth aspect by a system comprising a device according to the second aspect and/or a processor which is set up to execute the computer program product according to the third and/or fourth aspect.

The system may be configured to perform the repeatable process. In particular, the system can be set up to repeat the process at least once.

The system can be a vehicle, in particular an at least partially autonomous vehicle. The at least partially autonomous vehicle can be an L4 or L5 vehicle. Alternatively, the system may be a manufacturing system configured to repeatedly manufacture a product.

• 1 eine schematische Darstellung eines computer-implementierten Verfahrens zum Erfassen einer Unregelmäßigkeit eines ersten Systems;
• 2 eine schematische Darstellung einer Vorrichtung zum Erfassen einer Unregelmäßigkeit des ersten Systems;
• 3 ein Fahrzeug mit der Vorrichtung; und
• 4 eine schematische Darstellung eines Diagramms mit einem Vergleich einer Soll- und einer Ist-Information des ersten Systems.

Preferred exemplary embodiments are explained using the accompanying figures as examples. Show it:

• 1 a schematic representation of a computer-implemented method for detecting an irregularity of a first system;
• 2 a schematic representation of a device for detecting an irregularity of the first system;
• 3 a vehicle with the device; and
• 4 a schematic representation of a diagram with a comparison of target and actual information of the first system.

In the figures, identical or essentially functionally identical or similar elements are designated with the same reference numerals.

1 shows a schematic computer-implemented method 100 for detecting an irregularity of a first system 300 (see 3 ). The order of procedure 100 is in the 1 shown as an example and does not limit the invention to this sequence of steps. It will be apparent to those skilled in the art that the steps of method 100 may have a different order and/or may occur simultaneously.

The method 100 is described below in combination with a device 200, see 2 . The device 200 includes a memory 210, a recording unit 220, a processor 230 and a transceiver 240. The units of the device 200 can be connected to one another in a wired and/or wireless manner and can communicate with one another. The transceiver 240 is set up to send signals to and/or receive signals from external units.

The method 100 includes providing 110 target information of the first system 300. The target information is stored in the memory 210. The target information characterizes at least a target value of at least one measurement variable of the first system 300 during a repeatable process, wherein the target information, in particular the target value, is recorded during a first execution of the process.

The first system 300 is according to 3 a first vehicle, in particular an at least partially autonomous vehicle. The first vehicle 300 may be an L4 or L5 vehicle. Furthermore, the first vehicle 300 can be a car, a bus, a motorcycle or the like. The repeatable process can be the repeated driving of a predetermined route which has a start and an end point and these two points are connected by a path are. The first vehicle 300 is an L4 vehicle and travels the route repeatedly. The first vehicle 300 has preset settings for driving this route. These settings concern speed, braking, turn signal status, light settings, etc., which are required for autonomous driving of the route. These are initially always the same for the route. Accordingly, the autonomously driving first vehicle 300 will repeatedly travel the route in a similar manner, in particular identically, under almost unchanged conditions. However, it may happen that due to wear or external influences such as a pothole, a change occurs during a repetition of this process, in particular the repeated driving of the route. The route can, for example, be a route driven several times a day by an autonomously driving bus.

Alternatively to the first vehicle 300, the system 300 may be a system that performs a repeatable process. A repeatable process can be a manufacturing process that produces a product. It involves repeating the same steps to produce multiple products of the same type. The invention involves such a repeatable process.

The target information characterizes at least a target value of the measured variable of the first system during the process. For the vehicle 300, the measured variable can be a speed of the vehicle 300, which is recorded while driving along the route. The target information, in particular the target value, can characterize one or more (temporal and/or spatial) values of the measured variable, which reflect the values of the measured variable when the system, here the vehicle 300, functions correctly and has no defects or errors. A defect or error can, for example, be a worn tread on a tire of the vehicle 300.

For explanatory purposes, only one measurement variable is considered below, although the invention is not limited to a single measurement variable. The target information and/or the actual information can characterize target and/or actual values that characterize two, three or more measured values of the first system 300.

The method 100 further comprises recording 120, by means of the recording unit 220, an actual information of the first system, here the vehicle 300, the actual information being at least one actual value of the at least one measured variable of the first vehicle 300, here the speed of the Vehicle 300 is characterized during a current repetition of the process, here a repeated driving along the route, the current repetition being a repetition carried out after the first execution of the process.

The method 100 further includes determining 130, by means of the processor 230, at least one irregularity of the first vehicle 300 based on at least one deviation of the actual value from the target value of the at least one measured variable.

4 shows a diagram 400 of the target information and the actual information characterizing the target speed and the actual speed along the route. The solid line 410 shows the target values and the dashed line 430 shows the actual values. The time t is plotted on the x-axis and the speed V is plotted on the y-axis. Alternatively or additionally, the x-axis can indicate a position and/or route along the route.

The target information, in particular the target values 410, can be determined by averaging initial information. The vehicle 300 can, for example, drive the route several times, up to ten times, and the speed along the route is recorded with each repetition. The initial information characterizes the speed at each repetition of the route. By averaging and/or linearizing the initial information, in particular the speed values, the target information and the target values 410 can be determined. The initial information can be the first ten trips of the route. Alternatively, the initial information may be ten additional repetitions of the route. The repetitions do not have to be done one after the other.

By averaging, a bounding frame 420 of the target values 410 can also be determined. The bounding box indicates an expected fluctuation in the target values 410.

As long as the vehicle 300 does not experience any changes, such as tread wear or pothole, the recorded actual information will match the target information. More precisely, the actual values 430 will run within the bounding box 420.

4 shows that the actual values 430 deviate from the target values 410 in a time period in such a way that the bounding frame 420 is exceeded. According to method 100, in an irregularity 440 is determined in step 130, since here the actual values 430 deviate from the target values 410 in such a way that the actual values 430 leave the bounding frame 420.

The irregularity 440 may indicate an error, drift, wear and/or an external influence. In particular, it is important to determine whether it is an irregularity to be investigated that is due to the vehicle 300 itself, such as wear and tear and thus a potential safety risk that gradually increases, or whether it is a temporary irregularity , like the pothole. Due to the pothole, the first vehicle 300 is braked and has to accelerate again while normally traveling at a constant speed in this time period according to the target values.

For this purpose, the method 100 can further comprise providing actual information of at least a second system, wherein the actual information of the second system characterizes at least one actual value of the at least one measured variable of the second system during the process. For this purpose, the transceiver 240 can request and/or receive the actual information of the second system from the second system and/or a network. Alternatively or additionally, the actual information of the second system can be stored in the memory 220. According to the present exemplary embodiment, the actual information is a recorded speed of a second at least partially autonomous vehicle. In particular, the second vehicle is an L4 or L5 vehicle. The first and second vehicles can belong to the same vehicle type or series or can be different. The actual information of the second system can characterize the at least one measurement variable, for example on the same day, in the same week, in the same month and/or in the same season.

If the irregularity is the pothole, the actual values of the second vehicle will also show braking and re-acceleration in the time segment. Accordingly, it can be concluded that this is a temporary irregularity.

If the processor 230 instead determines that the actual values of the first and second vehicles differ from one another in the time period, this indicates that the first vehicle has an irregularity to be examined. For example, the reduced tire profile can lead to reduced friction and the first vehicle can partially spin the tire during the time segment, so that less acceleration is generated.

To check the irregularity, in particular the irregularity to be examined, the transceiver 240 can output a maintenance signal. The transceiver 240 can be set up to output the maintenance signal to the vehicle 300, a manufacturer and/or a driver of the vehicle 300 in order to inform them accordingly. Accordingly, a workshop appointment with a workshop can be made in good time, for example, without further reducing safety. Bursting of the tire can also be prevented.

In addition or as an alternative to the speed, the at least one measured value can be one of a network load, a noise level, one or more data streams, a level of the data stream or data streams, a power consumption, a signal frequency of a signal, a spectral analysis and / or a Fourier analysis of a or the signal of the first system 300 and/or at least one component of the first system 300. Alternatively or additionally, the at least one measurement variable can be one of a speed, a control angle, one or more braking times, one or more braking strengths, in particular the one or more braking times, a turn signal state of at least one turn signal, a headlight state of at least one headlight, a brake light state of at least one Brake light, a vehicle door state of at least one vehicle door, an acceleration, a speed of at least one drive and / or a wheel of the vehicle.

By means of the proposed method 100, the device 200 and the vehicle 300, early and simple detection of errors, degradations and/or performance limitations is made possible in order to enable early hazard prevention as well as planned maintenance or a temporary failure of the corresponding system.

Reference symbols

100

computer-implemented method for detecting an irregularity in a first system

110

Providing target information for a first system

120

Recording actual information of the first system

130

Determine at least one irregularity of the first system

200

Device for detecting an irregularity in a first system

210

Storage

220

Recording unit

230

processor

240

Transceiver

300

vehicle

400

Comparison of target information with actual information

410

Target values

420

Bounding box

430

Actual values

440

irregularity

Claims (14)

Computer-implemented method (100) for detecting an irregularity in a first system (300), comprising the steps: Providing (110) target information of a first system (300), wherein the target information characterizes at least one target value (410) of at least one measurement variable of the first system (300) during a repeatable process, wherein the target information, in particular the target value (410) is recorded during a first execution of the process; Recording (120) actual information of the first system (300), wherein the actual information characterizes at least one actual value (430) of the at least one measured variable of the first system (300) during a current repetition of the process, the current repetition is an iteration executed after the first execution of the process; Determining (130) at least one irregularity (440) of the first system (300) based on at least one deviation of the actual value (430) from the target value (410) of the at least one measured variable. Procedure (100) according to Claim 1 , further comprising: providing actual information of at least a second system, wherein the actual information of the second system characterizes at least one actual value of the at least one measured variable of the second system during the process; Determining the irregularity (440) of the first system (300) as a temporary irregularity based on an agreement of the actual values of the first and second systems at least in a temporal and / or spatial section of the deviation of the actual value of the first system from the target -Value of the first system; and/or determining the irregularity (440) of the first system (300) as an irregularity to be investigated based on a deviation of the actual values of the first and second systems at least in the temporal and/or spatial section of the deviation of the actual value of the first System from the target value of the first system. Method (100) according to one of the preceding claims, further comprising: Recording a plurality of initial information of the first system (300), wherein the initial information characterizes at least one recorded value of the at least one measured variable of the first system (300) during the first execution and further repetitions of the process that precede the current repetition be carried out, Determining the target information of the first system (300), in particular the target value (410) of the first system (300), based on the plurality of recorded initial pieces of information, in particular the recorded values of the at least one measured variable of the first system (300). Method (100) according to one of the preceding claims, wherein the first system (300) and/or the second system are an at least partially autonomous vehicle. Procedure (100) according to Claim 4 , where the repeatable process is a repeatable route. Method (100) according to one of the preceding claims, wherein the at least one measurement variable is one of a network utilization, a noise level, one or more data streams, a level of the data stream or data streams, a power consumption, a signal frequency of a signal, a spectral analysis and / or a Fourier analysis of one or the signal of the first system (300) and/or second system and/or at least one component of the first system (300) and/or second system is characterized, and/or wherein the at least one measured variable is one of a speed, an acceleration, a rotation rate, an angular velocity, a control angle, a power consumption, a fuel consumption, one or more braking times, one or more braking strengths, in particular the one or more braking times, a turn signal state of at least one turn signal, a headlight state of at least one headlight, a brake light state at least one brake light, a vehicle door state of at least one vehicle door, an acceleration nung, a speed of at least one drive and / or a wheel of the first and / or second vehicle. Method (100) according to one of the preceding claims, wherein the deviation of the actual value (430) from the target value (410) of the first system (300) is a deviation of the actual value (430) from the target value (410) of the first system (300) by a predetermined one includes first threshold value, where the first threshold value is in particular 20%, 10%, or 5%. Method (100) according to one of the preceding claims, further comprising: Storing the actual information of the first system (300), in particular when determining the at least one irregularity (440), in particular the irregularity of the first system (300) to be examined, at least the temporal and / or spatial section of the deviation of the actual Value (430) is stored from the target value (410) of the first system (300). Method (100) according to one of the preceding claims, further comprising: Outputting a maintenance signal when determining the at least one irregularity (440), in particular the irregularity of the system (300) to be examined. Method (100) according to one of the preceding claims, further comprising: Adapting, in particular temporally adapting, a timetable of the vehicle (300) at least partially based on the irregularity (440). Method (100) according to one of the preceding claims, wherein the at least one measurement variable further comprises at least one of a time of day, a season, a traffic volume, a state of at least one road traveled by the vehicle during the process, a number of passengers of the vehicle, a type of the first and/or second system and a date of manufacture of the first and/or second system. Device (200) for detecting an irregularity in a first system (300), comprising: a memory (310) which is set up to provide target information of a first system (300), the target information characterizing at least one target value (410) of at least one measured variable of the first system (300) during a repeatable process, wherein the target information, in particular the target value (410), is recorded during a first execution of the process; a recording unit (420) which is set up to record actual information of the first system (300), the actual information being at least one actual value (430) of the at least one measured variable of the first system (300) during a current repetition of the Process characterized, wherein the current repetition is a repetition carried out after the first execution of the process; a processor (430) which is set up to determine at least one irregularity (440) of the first system (300) based on at least one deviation of the actual value (430) from the target value (410) of the at least one measured variable. Computer program product, comprising program code sections for executing a computer-implemented method (100) according to one of Claims 1 until 11 when the computer program is executed by at least one processor (230). System (300), in particular vehicle, comprising a device (100). Claim 12 and/or a processor for running the computer program product Claim 13 is set up.

Images