DE102019123454B4 - Method for forecasting the wear of a component of a vehicle and vehicle - Google Patents

Abstract

Method for predicting wear of at least one component of a vehicle, with the steps:- during operation of the vehicle: determining at least one first variable with a first value using an electronic computing device;- using the electronic computing device: converting the first value of the first variable into at least one second value of at least one second variable (10) that is different from the first variable as a function of at least one parameter that is different from the variables and characterizes a configuration of the vehicle;- by means of the electronic computing device: assigning a load level (A1) to the second value; - by means of the electronic computing device: determining at least one load spectrum value (L) defining at least one load spectrum, which characterizes a duration and/or a frequency of occurrence of at least the load level (A1) assigned to the second value; and- by means of the electronic computing device: using a model that is trained by machine learning and describes a relationship between the load level (A1) assigned to the second value and a wear (14) of the component resulting from the load level (A1) in order to calculate the wear (14) of the component by using the model and thereby depending on the relationship described by the model and depending on the collective load value, the wear (14) is predicted and the wear is thereby predicted from the respective collective load using the previously learned model.

Description

The invention relates to a method for predicting wear of at least one component of a vehicle. The invention also relates to a vehicle, in particular a motor vehicle.

the DE 10 2005 052 476 A1 discloses a method for individually estimating the current and average wear of a tire used in a vehicle during operation of the vehicle having a vehicle data bus system and wheel speed sensors. The necessary vehicle data, which is used to determine the history of the vehicle's operating conditions, are recorded. In addition, it is provided that the wear of the vehicle tire is determined at least from the parameters longitudinal acceleration or longitudinal forces of the vehicle tire and lateral forces acting on the tire, and that an acoustic and/or visual signal is emitted when a certain level of the maximum mileage of the tire is reached.

In the pamphlet DE 102 35 525 A1 describes a monitoring system for a motor vehicle, with which a condition of the vehicle is monitored by using a failure model to calculate an expected downtime from recorded and processed data from sensors and electronic control units, or using a behavior model to estimate an expected model behavior of the vehicle in order to To be able to evaluate the deviation of the real vehicle behavior from the model behavior. The failure model uses a frequency matrix as a load aggregate, which indicates how often components of the motor vehicle were in which load state. The values from the frequency matrix are combined into a total wear value using weighting values.

From the pamphlet EP 1 340 926 A2 wear detection for motor vehicles is known, which maps sensor signals to a wear value by means of a transfer function. The total energy converted during braking maneuvers is taken as the basis here as the load aggregate.

The object of the present invention is to create a method and a vehicle so that wear of at least one component of a vehicle can be predicted, ie predicted, in a particularly simple and precise manner.

According to the invention, this object is achieved by a method having the features of patent claim 1 and by a vehicle having the features of patent claim 12 . Advantageous configurations with expedient developments of the invention are specified in the remaining claims.

A first aspect of the invention relates to a method for forecasting, that is to say predicting or predicting wear of at least one component of a vehicle, preferably a motor vehicle and particularly preferably a motor vehicle. In a first step of the method, at least one first variable with a first value is determined during operation of the vehicle, in particular while the vehicle is traveling, using an electronic computing device, in particular of the vehicle. In other words, in the first step it is provided that during operation of the vehicle, in particular while the vehicle is being driven, at least one first value of at least one first variable is determined by means of an electronic computing device, in particular of the vehicle. For this purpose, for example, the first value or the first variable is recorded by means of at least one, in particular electronic, sensor, in particular of the vehicle. The sensor provides, for example, a signal, in particular an electrical signal, which characterizes the first variable detected by the sensor or the first value detected by the sensor. The electronic computing device receives the signal and thus the first value, as a result of which the electronic computing device determines the first value. Alternatively, it is conceivable that the sensor detects a measured variable that differs from the first variable, for example, so that the signal characterizes the measured variable. The electronic computing device receives the signal and determines, in particular calculates, the first value of the first variable from the signal and thus from the measured variable.

In the second step of the method, the electronic computing device is used to convert the first value of the first variable into at least one second value of at least one second variable that is different from the first variable, specifically as a function of at least one of the variables and one, in particular current one , Configuration of the vehicle characterizing parameters. The configuration of the vehicle means its design and thus, for example, an embodiment and/or equipment and/or an equipment and/or construction variant of the vehicle. The feature that the first value is converted into the second value or the first quantity into the second quantity can in particular be understood to mean that the second value of the second quantity is calculated from the first value of the first quantity and is thus obtained. Since the second value from the first value is calculated as a function of the parameter and thus as a function of the configuration of the vehicle, when calculating the second value the configuration of the vehicle and thus its, in particular current, specific design is taken into account. This feature is based in particular on the knowledge that, depending on the configuration of the vehicle, different second values can result from the first value. In other words, if, for example, the same first value is determined for different vehicles in which the method according to the invention is used, with the vehicles differing from one another in their configurations, for example, different second values are obtained from the same determined first value in the vehicles values calculated. It can already be seen here that due to the fact that the first value is determined and the second value is calculated from the first value depending on the configuration of the vehicle, the method according to the invention is particularly simple and therefore requires little effort and is particularly cost-effective for different vehicles or different variants and / or equipment of the vehicle can be used.

In a third step of the method, the second value is assigned a corresponding load level, which is stored, for example, in a storage device of the electronic computing device, by means of the electronic computing device. For example, different load levels are stored in the memory device. The second value is compared to the stored stress levels, for example. Depending on the comparison, one of the stored load levels is selected from the stored load level. The selected stress level is then assigned to the second value.

In a fourth step of the method, at least one load spectrum value defining at least one load spectrum is determined, in particular calculated, by means of the electronic computing device, which characterizes a duration and/or a frequency of occurrence of at least the load level associated with the second value. In other words, the collective load value indicates or expresses how often and/or how long the load level has occurred, in particular continuously or without interruption. The occurrence of the stress level is to be understood in particular as meaning that the stress level acts on the component or that the component has been or is being subjected to the stress level. Thus, for example, the collective load value expresses how often and/or how long the component was or is subjected to the load level. In this fourth step, for example, the frequency of a wear-equivalent load level across different components is calculated.

In a fifth step of the method, a model that is stored, for example, in the storage device and is trained by machine learning is used by means of or by the electronic computing device, which model describes a relationship between the load level assigned or selected to the second value and wear on the component resulting from the load level or depicts. The model is used by the computing device to predict the wear of the component, ie to predict the wear of the component using the model and thereby as a function of the relationship described by the model and as a function of the collective load value. In general, the frequency of stress levels with regard to several second values can be taken into account.

The invention is based in particular on the following findings: Usually, a respective wear of components of vehicles is not predicted, but a respective user of a respective vehicle is instructed to visit a workshop regularly to check the state of wear of certain components and subsequently, if necessary, the components to be serviced or replaced. Components are sometimes designed to have indicative failure behavior. This means that the respective component wears out or fails in such a way that the driver recognizes this and subsequently visits the workshop. This is done in such a way that there is no safety risk and safe operation is always guaranteed and there is still an acceptable remaining time until the component is replaced.

• Insbesondere bestehen bei herkömmlichen Lösungen Nachteile bei künftigen Nutzungsszenarien, bei denen das Fahrzeug nicht Eigentum des jeweiligen Nutzers ist. Es kann daher nicht mehr davon ausgegangen werden, dass der Nutzer das Fahrzeug zu einer Werkstatt bringt und/oder Schäden meldet. Die Wirtschaftlichkeit des Nutzungsszenarios wird durch lange Standzeiten, insbesondere vor Werkstattbesuchen, durch Abschleppen und/oder durch unnötige Werkstattbesuche, beispielsweise durch solche Werkstattbesuche, bei denen routinemäßig die Werkstatt aufgesucht, jedoch keine Teile ersetzt werden, stark verringert. Eine Bewertung des Restwertes eines Fahrzeugs ist verhältnismäßig schwierig, weil der Zustand der Einzelteile nicht mit vertretbarem Aufwand geprüft werden kann. Kommen eigene, spezielle Sensoren zur Verschleißerkennung zum Einsatz, so führt dies zu Mehrkosten, zu erhöhtem Gewicht, zu erhöhtem Bauraumbedarf und zu höherem Montageaufwand. Ein weiterer Nachteil ist, dass fahrzeugspezifische Modelle zum Einsatz kommen, welche angelernt werden müssen. Mittels eines solchen Modells können beispielsweise aus Beanspruchungsgrößen Verschleiße errechnet werden. Die Modelle unterscheiden sich stark je nach Fahrzeugkonfiguration wie beispielsweise Schwerpunkthöhe, Reifengröße et cetera und Spezifikation des beispielsweise als Bremsbelag ausgebildeten Bauteils. Deshalb ist die Modellbildung zum einen häufig zu wiederholen, zum andere liegen hierzu nur eine begrenzte Anzahl von Messdaten zur Verfügung, weil jeweils nur Messdaten der jeweiligen, passenden Konfiguration verwendet werden können. Außerdem sind Modelle nur sehr bauteilspezifisch, sodass für unterschiedliche Bauteile jeweilige, eigene Modelle erschaffen und erlernt werden müssen.

In special cases, such as with brake pads, sensors are sometimes used to detect wear. It is also conceivable to determine wear of a component such as a brake pad by integrating stress variables such as brake pressure or temperature. It is also conceivable to determine wear on the basis of load variables such as forces, in particular longitudinal and transverse forces. With this in mind, the following disadvantages have been identified:

• In particular, conventional solutions have disadvantages in future usage scenarios in which the vehicle is not owned by the respective user. It can therefore no longer be assumed that the user will bring the vehicle to a workshop and/or report damage. The profitability of the usage scenario is greatly reduced by long downtimes, in particular before workshop visits, by towing and/or by unnecessary workshop visits, for example by those workshop visits in which the workshop is routinely visited but no parts are replaced. An assessment of the residual value of a vehicle is relatively difficult because the condition of the individual parts cannot be checked with reasonable effort. If your own special sensors are used to detect wear, this leads to additional costs, increased weight, increased installation space requirements and higher assembly costs. Another disadvantage is that vehicle-specific models are used, which have to be trained. Such a model can be used, for example, to calculate wear and tear from stress variables. The models differ greatly depending on the vehicle configuration, such as the height of the center of gravity, tire size, etc., and the specification of the component designed as a brake pad, for example. Therefore, on the one hand, the modeling has to be repeated frequently, on the other hand, only a limited amount of measurement data is available for this purpose, because only measurement data of the respective, suitable configuration can be used. In addition, models are only very component-specific, so that individual models have to be created and learned for different components.

The problems and disadvantages mentioned above can now be avoided by the method according to the invention. The method according to the invention can be used in a simple manner for different components of different vehicles, in particular because the second value is calculated from the first value, without the model having to be specially trained or taught for the respective component or for the respective vehicle. In particular, the method according to the invention makes it possible to independently recognize, even before excessive wear or damage to the component occurs, if a workshop visit or maintenance or replacement of the component is required. In particular, the vehicle can also report the status of its components or its part, in particular to people in the interior of the vehicle. The method enables this without the use of additional sensors used specifically for wear detection.

Within the scope of the invention, a parameter or a physical variable, for example a measured variable or arithmetic variable, which can assume different values, is to be provided under a variable. A value is therefore a value or an amount of the respective variable, with the value preferably being able to have a unit.

The first variable is a physical variable, for example. In particular, the first variable is a stress variable, for example, which is at least largely independent of the configuration of the vehicle per se and at least largely independent of the component and its specification per se. In the calculation step for the second variable, for example, vehicle-dependent relationships are taken into account, i.e. a value is created which is largely vehicle-independent. In the subsequent calculation step of assigning the frequency of a wear-equivalent load level, component-specific relationships are taken into account, i.e. a value that is at least largely component-independent is created.

It is therefore sufficient to determine the model, on the basis of which the wear can be deduced from the load spectrum, only once and a particularly large database is available, since measurement data from different vehicle derivatives, in particular for wear detection and/or for the model and/or to train the model. The stress variable (first variable) depends on the vehicle and the component or component, i.e. depending on the type or design of the component, a variable that determines the wear of the component, in particular mainly, and can be determined or measured, for example, by component tests. As part of such a component test, the component is examined and subjected to a load caused by the stress variable. The number of stress variables can be chosen according to the desired prognosis accuracy, computing speed and memory requirements. The stress variables are preferably classified in such a way that they represent wear-equivalent variables. This means that although components have different wear characteristics (some components only wear out under extreme conditions, others continuously) there are at least largely component-independent stress variables.

The method can be carried out or implemented without additional sensors used specifically for detecting wear. However, it is conceivable to install and use additional sensors, for example to record accelerations and/or temperatures and thus also to measure load collectives, which are useful for predicting the wear of one or more components.

It has been shown to be particularly advantageous if a component that is different from a tire is used as the component. As a result, the wear of the component can be predicted particularly advantageously and precisely. The method can be applied to any components, in particular components that are different from a tire.

A further embodiment is characterized in that a pressure, in particular a pressure of a fluid and preferably a pressure of a liquid and thus, for example, a hydraulic pressure, is used as the first variable. It has been found that the wear can be predicted particularly precisely on the basis of a pressure or the pressure. This is particularly advantageous for forecasting the wear of brake pads.

It has been shown to be particularly advantageous if a brake pressure is used as the pressure. This embodiment is based on the knowledge that braking operations or braking maneuvers, during which the vehicle is braked by actuating a brake of the vehicle designed, for example, as a service brake, can be particularly decisive for the wear. It is therefore preferably provided to determine the wear on the basis of the brake pressure. As a result, the wear can be predicted with particular precision. In addition, the brake pressure is a variable that is particularly advantageously available and can be determined, for example, via an on-board network and/or via a data bus of the vehicle. In this case, for example, the electronic computing device receives the aforementioned signal via the data bus or the vehicle electrical system.

In a particularly advantageous embodiment of the invention, a force and/or a temperature is used as the second variable or as a further variable. As a result, the wear of the component can be predicted particularly precisely.

In order to be able to achieve a particularly high forecast accuracy, especially in the case of brake pads, it is provided in a further embodiment of the invention that the configuration of the vehicle has a height of the center of gravity of the vehicle and/or an axle load distribution of the vehicle and/or a diameter of a tire of the vehicle and/or a radius of a tire or the tire of the vehicle.

In order to be able to predict wear particularly precisely, it is provided in a further embodiment of the invention that during operation of the vehicle at least one third value of at least one third variable different from the first variable and the second variable is determined using the electronic computing device. The electronic computing device converts the third value of the third variable into at least a fourth value of at least one fourth variable that is different from the first, second and third variable, depending on the parameter that is different from the variables and characterizes the configuration of the vehicle. Furthermore, a second stress level, which is different from the stress level, is assigned to the fourth value by means of the electronic computing device. The collective load value characterizes the duration and/or the frequency of the simultaneous or joint occurrence of the first load level and the second load level. This embodiment is based on the finding that during the operation of the vehicle, the component whose wear is to be predicted is frequently subjected not only to one load or one load level, but to multiple loads or multiple load levels simultaneously. By taking the at least two load levels into account, the wear on the component can be predicted particularly precisely. The first variable is, for example, the aforementioned pressure, the second variable being, for example, the aforementioned force. The third variable is time, for example, with the fourth variable being the aforementioned temperature, for example. The second and fourth variables can thus be determined on the basis of the first and third variables, which are at least largely independent of the component, so that the wear can be precisely predicted.

It has also been shown to be particularly advantageous if, by means of the electronic computing device, the first value of the first variable is converted into at least a third value of at least one third variable that is different from the first and second variable, depending on the different variable and the configuration of the Vehicle characterizing parameters is converted. By means of the electronic computing device, a second load level that differs from the load level is assigned to the third value, the collective load value being the Characterized duration and / or the frequency of simultaneous occurrence of the first stress level and the second stress level. This embodiment is based on the finding that the first value or the first variable usually results not only in the first load level, which relates to a force, for example, but also the second load level, which relates to a temperature, for example. In other words, for example, the occurrence of the pressure designed in particular as brake pressure leads both to a force or moment load and to a temperature load on the component designed, for example, as a brake lining. The second and third values are thus determined from the first value, as a result of which the wear can be predicted particularly precisely.

The respective stress level includes, for example, a range of values with a number of different values. The background to this embodiment is that, for example, different second values per se, or not every second value, are not used to predict wear, but the different second values are assigned to the same load level, for example, which is used to predict wear. As a result, the wear can be predicted, on the one hand, precisely and, on the other hand, with sufficiently little computing effort and thus quickly.

It has been shown to be particularly advantageous if the component used is a brake pad, a bearing, a control arm for guiding a wheel of the vehicle, a component, in particular a bearing, an axle and/or wheel suspension of the vehicle, a wheel bearing, a damper or a spring is used. The wear can thus be predicted with particular precision.

Finally, it has proven to be particularly advantageous if at least one signal, which can be perceived in particular by touch and/or acoustically and/or visually, is output by means of an electronic display device in the vehicle, in particular in the interior of the vehicle, if the predicted wear is one, in particular predetermined or definable, threshold value exceeded or reached. In this way, for example, the user or driver of the vehicle can be informed that the wear has progressed to such an extent that maintenance or replacement of the component is appropriate. As a result, a particularly advantageous and safe operation of the vehicle can be guaranteed.

A second aspect of the invention relates to a vehicle, preferably designed as a motor vehicle, which is designed to carry out a method according to the first aspect of the invention. Advantages and advantageous configurations of the first aspect of the invention are to be regarded as advantages and advantageous configurations of the second aspect of the invention and vice versa.

The invention also includes developments of the vehicle according to the invention, which have features as have already been described in connection with the developments of the method according to the invention. For this reason, the corresponding developments of the vehicle according to the invention are not described again here.

The motor vehicle according to the invention is preferably designed as a motor vehicle, in particular as a motor vehicle, for example as a passenger car or truck, or as a passenger bus or motorcycle.

The invention also includes the combinations of features of the described embodiments.

• 1 ein Diagramm zum Veranschaulichen des erfindungsgemäßen Verfahrens;
• 2 ein weiteres Diagramm zum Veranschaulichen des erfindungsgemäßen Verfahrens;
• 3 ein weiteres Diagramm zum Veranschaulichen des erfindungsgemäßen Verfahrens;
• 4 ein weiteres Diagramm zum Veranschaulichen des erfindungsgemäßen Verfahrens;
• 5 ein weiteres Diagramm zum Veranschaulichen des erfindungsgemäßen Verfahrens;
• 6 eine Matrix zum Veranschaulichen des erfindungsgemäßen Verfahrens;
• 7 eine weitere Matrix zum Veranschaulichen des erfindungsgemäßen Verfahrens; und
• 8 ein Blockdiagramm zum Veranschaulichen des erfindungsgemäßen Verfahrens.

An exemplary embodiment of the invention is described below. For this shows:

• 1 a diagram to illustrate the method according to the invention;
• 2 another diagram to illustrate the method according to the invention;
• 3 another diagram to illustrate the method according to the invention;
• 4 another diagram to illustrate the method according to the invention;
• 5 another diagram to illustrate the method according to the invention;
• 6 a matrix to illustrate the method according to the invention;
• 7 another matrix to illustrate the method according to the invention; and
• 8th a block diagram to illustrate the method according to the invention.

The exemplary embodiments explained below are preferred embodiments of the invention. In the exemplary embodiments, the described components of the embodiments each represent individual features of the invention that are to be considered independently of one another and that each also develop the invention independently of one another. Therefore, the revelation is intended to include others than those illustrated Combinations of the features of the embodiments include. Furthermore, the described embodiments can also be supplemented by further features of the invention that have already been described.

Elements that are the same or have the same function are provided with the same reference symbols in the figures.

A method for predicting wear of at least one component of a vehicle, which is preferably designed as a motor vehicle, is explained below with reference to the figure. The component is preferably a component of the vehicle that is different from a tire. The component is preferably a brake pad. This means that the method is explained below using an example in which the component is a brake lining. The previous and following explanations can of course also be transferred without further ado to other components of the vehicle, in particular those that differ from tires, and vice versa.

First, for example, wear and tear of the component, also referred to as wear behavior, is determined under stresses with relevant loads such as temperature and force, in particular empirical means. 1 and 2 each show a diagram on the abscissa 10 or 12 of which a respective load, also referred to as a load variable, is plotted, with the component being subjected to the load variable and thus to the stress or load resulting from the load variable, for example. The aforementioned force is plotted on the abscissa 10 , the aforementioned temperature being plotted on the abscissa 12 . A respective wear is plotted on the respective ordinate 14 or 16 of the respective diagram, which results from the respective stress resulting from the respective load variable (force or temperature). For example, a curve 18 illustrates the wear of the component with increasing force. A curve 20 illustrates the wear of the component with increasing temperature. A curve 22 illustrates, for example, wear of a second component with increasing force, and a curve 24 illustrates, for example, wear of the second component with increasing temperature. The second component is, for example, a second brake pad. The respective brake lining is also simply referred to as a lining.

the end 3 and 4 it can be seen that load levels A1 and A2 are determined for the force and for the first component and load levels B1, B2 and B3 are determined for the force and for the second component. Stress levels C1, C2, C3 and C4 are determined for the temperature and for the first component, and stress levels D1, D2, D3 and D4 are determined for the temperature and the second component. It can also be seen that the respective stress level A1-2, B1-3, C1-4 and D1-4 is a range, in particular a range of values, or includes such a range, in particular such a range of values, with the respective range comprising several includes different values or extends over several consecutive values without interruption. The respective load level A1-2, B1-3, C1-4, D1-4 is a respective, in particular component-specific, wear-equivalent level of the aforementioned loads. These levels can be linear or non-linear or distributed.

By carrying out the determination of the wear behavior and the determination of the wear-equivalent levels, a model for predicting wear is learned, ie trained, by machine learning. In particular, the model is trained using test vehicles and thus through empirical tests, so that the model establishes a connection between the respective load variable (in the present example the force or temperature) that acts on the respective component or to which the respective component is subjected and the respective load level A1 -2, B1-3, C1-4, D1-4 describes. In this case, for example, the respective wear occurring in or on the respective test vehicle and caused by the respective load variable is either determined or recorded by a sensor and/or recognized by component failure.

Finally, in order to predict the wear of the respective component, at least one first value of at least one first variable is determined, for example during operation, in particular while driving, of the vehicle using an electronic computing device, in particular of the vehicle. Since the respective component in the present example is a brake pad of a brake of the vehicle designed, for example, as a service brake, the first variable is, for example, a brake pressure, in particular a hydraulic brake pressure. When the vehicle is braked and the vehicle is slowed down by braking, the brake pressure is used to actuate the brake and thus, for example, press the respective brake pad against a corresponding brake disc rotating with a wheel of the vehicle.

By means of the electronic computing device, for example, the first value of the first Variable (brake pressure) converted into at least one second value of at least one second variable that is different from the first variable as a function of at least one parameter that is different from the variables and characterizes a configuration of the vehicle. This means that the second value of the second variable is calculated from the first value of the first variable. The second variable is, for example, the aforementioned force, which results, for example, from the ascertained, in particular measured, brake pressure and acts, for example, on the brake pad during braking or braking. In other words, the force is applied to the brake lining, for example, in order to thereby press the brake lining against the brake disc. Thus, for example, the second value of the force is calculated from the first value of the brake pressure. In addition, at least one third value of at least one third variable that differs from the first variable and the second variable is calculated, for example, by means of the electronic computing device from the first value of the first variable (brake pressure) as a function of the parameter and thus as a function of the configuration of the vehicle. The third variable is, for example, the aforementioned temperature to which, for example, the brake lining is brought or heated by the braking effected by the brake pressure. Thus, for example, the third value of the temperature is calculated from the first value of the brake pressure.

5 shows a diagram with the time plotted on the abscissa 26 . The aforementioned force, for example, which was or is calculated from the brake pressure as a function of the parameter and thus as a function of the configuration of the vehicle, is plotted on the ordinate 28 . A curve 30 illustrates the force occurring over time and acting on the second component. where is in 5 a first braking is denoted by BR1, a second braking being denoted by BR2. Braking operations BR1 and BR2 are spaced apart in time and follow one another in time. When braking BR1, for example, the second component is pressed so hard against the brake disk by the braking pressure or the braking pressure is so great during braking BR1 that the force resulting from the braking pressure is so great that the force is at load level B2 or that the load level B2 occurs. When braking BR2, however, the braking pressure is so great that the force is so great that the load level B3 occurs. The first braking BR1 and thus the second load level B2 are present over an uninterrupted first time period T1, which is five seconds, for example. In 5 a second period of time T2, for example one second, is illustrated, during which, for example, the load level B2 is present without interruption. In addition, 5 For example, a third period of time T3 is shown, during which, for example, the load level B2 is present without interruption. In addition, 5 a point in time is denoted by t4, which is, for example, 9 seconds starting from a starting point. At this point in time t4, for example, the load level B2 was exercised or driven. The statements to 5 , which relate to force, can easily be transferred to temperature and the corresponding stress levels C1-4, D1-4 and vice versa.

In the method, one of the load levels A1-2 is assigned to the second value, for example, in order to predict the wear of the first component. For example, one of the load levels B1-3 is assigned to the second value in order to predict the wear of the second component. For example, one of the load levels C1-4 is assigned to the third value in order to predict the wear of the second component. It is also conceivable that one of the load levels D1-4 is assigned to the third value, for example in order to predict the wear of the second component. In addition, the method provides for at least one load spectrum value defining at least one load spectrum to be determined by means of the electronic computing device , D1-4 characterized.

At an in 6 illustrated embodiment is an in 6 collective load value denoted by L is a period of time which corresponds, for example, to time t4 and in the present case is nine seconds, for example. With regard to the second component, the force and the temperature, for example, the collective load value L in an in 6 illustrated matrix. In the matrix, stress levels B1-3 are arranged in rows of the matrix, while stress levels D1-3 are arranged in columns of the matrix. At the in 6 In the embodiment shown, the collective load value L states that the load levels B2 and D1 have occurred simultaneously or together for nine seconds, that is to say have acted on the second component. Are accordingly in the in 6 If further collective load values are entered in the matrix shown, the collective load is thereby defined by the collective load values entered, with this collective load value describing a load acting on the second component.

At an in 7 embodiment shown are in the rows of the matrix, for example the stress levels B1-3 are entered, while respective periods of time are entered in the columns of the matrix, which in the present case can be one second, two seconds, three seconds or four seconds. the in the in 7 The collective load values L entered in the matrix shown state that, for example with regard to the second component and the force, the load level B2 was present for exactly one second and exactly three seconds, in particular without interruption. Thus characterize according to 7 the respective collective load values L a respective frequency of occurrence of a period of time during which the respectively assigned load level, in this case the respective load level B1-3, in particular without interruption, existed or was present.

Furthermore, the method provides for the aforementioned model, trained by machine learning, to be used, which establishes a connection between the first load level or second load level assigned to the second value or the third value and the wear of the respective load level resulting from the respective load level component describes. The model is used to predict the wear of the component by using the model and thus depending on the relationship described by the model and depending on the respective collective load value L, the wear of the component is predicted.

The first variable (brake pressure) is a vehicle electrical system variable, for example, since the first variable or the first value of the first variable is provided by a device via a vehicle electrical system and is received by the electronic computing device. The vehicle electrical system variable or its first value is converted into the second and third variable or into the second and third value, with the second and third variable also being referred to as stress variables. The vehicle electrical system size is converted into the respective stress size as a function of the configuration, also referred to simply as the vehicle configuration, which includes, for example, a height of a center of gravity of the vehicle, an axle load distribution and a tire radius of the vehicle.

The respective collective load is determined or recorded, for example by counting how often the vehicle is operated at or at what load level. The collective load is filed, ie stored, in the form of the respective matrix in a memory device of the electronic computing device, which is designed as a control unit, for example. Finally, the wear is predicted from the respective load collective using the previously learned model.

8th shows a block diagram to illustrate the method. In 8th a counter is illustrated by a block 32 which, for example, determines, in particular calculates, the respective collective load value L. In other words, the counter counts how often and/or how long the respective stress level is present and/or how often and/or how long at least two of the stress levels are present simultaneously. An arrow 34 illustrates at least one, in particular electrical, signal which, for example, characterizes the vehicle electrical system variable or the first value and in particular transmits it to the electronic computing device. An arrow 36 shows that the load levels A1-2, B1-3, C1-4, D1-4, which were determined from component tests, in particular empirically, are supplied to the counter. A block 38 illustrates the respective matrix, which is stored, for example, in the memory device of the electronic computing device.

For example, a block 40 illustrates the model. The model, on the basis of which the wear is deduced or calculated from the collective load, can be designed in one part or in one stage or else in two parts or in two stages. If the model is designed in two stages or in two parts, for example, then block 40 illustrates a first part of the model. The first part can be independent of the configuration of the vehicle and independent of a specification of the component. A block 42 illustrates an optionally provided second part of the model. The second part depends, for example, on the configuration of the vehicle and/or on the specification of the component, with the second part being learned individually for each vehicle/brake pad combination, for example. The second part then serves to improve the quality of the forecast, because specific effects are taught in it, but effects with significantly less correlation to the wear than if only the second part were provided.

How out 6 and 7 can be seen, there are at least two different ways, for example, to determine the respective collective load value L, that is, to count how often or at what load level the vehicle was moved. According to 6 the period of time, also referred to as time, is measured in or during which the respective stress level occurs and/or at least two of the stress levels occur simultaneously. According to 7 is used as an additional load size, a load duration in the form of in the columns of in 7 shown mat rix defined time spans shown. For the respective load level, it is then counted how often the respective period of time occurs during which the respective load level occurs, in particular without interruption. In other words, for each level it is counted how often and correspondingly how long a corresponding stress is or was present. As a result, a particularly high information content of the matrix can be realized.

Finally, a block 44 illustrates parameterization in the test vehicle, this parameterization--as illustrated by an arrow 46--being supplied to the first part in general and--as illustrated by an arrow 48--to the second part in a vehicle-specific manner. Finally, an arrow 50 illustrates the wear forecast.

In principle, the process can be applied to any component, especially brake pads. Axle suspension links and bearings, wheel bearings, dampers, springs, tires. Based on the wear forecast, at least one message or at least one signal can be output to a driver of the vehicle and/or transmitted to a control center using at least one or more thresholds, in order to initiate workshop visits, for example. Alternatively or additionally, the wear prognosis can be used for diagnosis et cetera.

Claims (12)

Method for predicting wear of at least one component of a vehicle, with the steps: - During operation of the vehicle: determining at least one first variable with a first value by means of an electronic computing device; - by means of the electronic computing device: converting the first value of the first variable into at least one second value of at least one second variable (10) which is different from the first variable as a function of at least one parameter which is different from the variables and characterizes a configuration of the vehicle; - by means of the electronic computing device: assigning a stress level (A1) to the second value; - by means of the electronic computing device: determining at least one load spectrum value (L) defining at least one load spectrum, which characterizes a duration and/or a frequency of occurrence of at least the load level (A1) assigned to the second value; and - by means of the electronic computing device: using a model that is trained by machine learning and describes a relationship between the load level (A1) assigned to the second value and a wear (14) of the component resulting from the load level (A1) in order to calculate the wear (14) of the To predict the component by using the model and thereby depending on the relationship described by the model and depending on the collective load value of the wear (14) is predicted and the wear is thereby predicted from the respective collective load using the previously learned model. procedure after claim 1 , characterized in that a component other than a tire is used as the component. procedure after claim 1 or 2 , characterized in that a pressure, in particular of a fluid, is used as the first variable. procedure after claim 3 , characterized in that a braking pressure is used as the pressure. Method according to one of the preceding claims, characterized in that a force or a temperature is used as the second variable (10). Method according to one of the preceding claims, characterized in that the configuration of the vehicle comprises a height of the center of gravity of the vehicle and/or an axle load distribution of the vehicle and/or a diameter of a tire of the vehicle and/or a radius of a tire of the vehicle. Method according to one of the preceding claims, characterized by the steps: - during operation of the vehicle: determining at least a third value of at least one of the first variable and the second variable third variable by means of the electronic computing device; - by means of the electronic computing device: converting the third value of the third variable into at least one fourth value of at least one fourth variable (12) different from the first, second and third variable, depending on the parameter which is different from the variables and characterizes the configuration of the vehicle; and - by means of the electronic computing device: assigning a second load level (C1) that differs from the load level (A1) to the fourth value, with the collective load value (L) indicating the duration and/or the frequency of the simultaneous occurrence of the first load level (A1) and the second load level (C1). Procedure according to one of Claims 1 until 6 , characterized by the steps: - by means of the electronic computing device: converting the first value of the first variable into at least one third value of at least one third variable (12) different from the first and second variable depending on the different variable from the variables and the configuration of the vehicle characterizing parameters; and - by means of the electronic computing device: assigning a second load level (C1) that differs from the load level (A1) to the third value, with the collective load value (L) indicating the duration and/or the frequency of the simultaneous occurrence of the first load level (A1) and the second load level (C1). Method according to one of the preceding claims, characterized in that the stress level (A1, C1) has a value range with a number of different values. Method according to one of the preceding claims, characterized in that as the component, a brake pad, a bearing, a control arm for guiding a wheel of the vehicle, a component, in particular a bearing, an axle and / or wheel suspension of the vehicle, a wheel bearing, a damper or a spring is used. Method according to one of the preceding claims, characterized in that at least one signal is output by means of an electronic display device of the vehicle when the predicted wear (14) exceeds or reaches a threshold value. Vehicle designed to carry out a method according to one of the preceding claims.

Images