DE102022205784A1 - Determining a clutch temperature of a vehicle clutch using a neural network and determining a scaling factor therefor - Google Patents

Abstract

A method is disclosed for determining a clutch temperature (KT1, KT2) of a vehicle clutch (K1, K2) using a neural network (12), the method comprising the following steps: input (BS1) of at least one value (18a, 18b, 18c) at least one operating parameter of the vehicle clutch (K1, K2) as input data (20a) into the neural network (12); Calculating (BS2) a temperature (T1) by the neural network (12), based on the input data (20a) and a relationship between the input data (20a) and the temperature (T1) learned by the neural network (12); and applying (BS3) a determined scaling factor (SF1, SF2) to the temperature (T1) to determine the clutch temperature (KT1, KT2) of the vehicle clutch (K1, K2). Also disclosed is a control device (10) for determining clutch temperatures (KT1, KT2) of a plurality of vehicle clutches (K1, K2) using a neural network (12).

Description

Technical area

The present invention relates to a method for determining a clutch temperature of a vehicle clutch using a neural network and determining a scaling factor for the clutch temperature. The invention also relates to an associated control device for determining a clutch temperature of a vehicle clutch using a neural network and for applying a determined scaling factor to the clutch temperature.

State of the art

The temperature of a vehicle clutch can be calculated using a classic rule-based mathematical model. Machine learning can also be used for this, for example a neural network. The calculation can take place in a transmission control unit. The calculation capacity available on the transmission control unit may be limited. Additional neural networks can be used to determine additional clutch temperatures of additional vehicle clutches.

Presentation of the invention

In a first aspect, the invention relates to a method for determining a clutch temperature of a vehicle clutch using a neural network.

The vehicle clutch can be installed in a motor-driven vehicle, such as a motor vehicle, a motorcycle or an at least partially electrically driven two-wheeler. By means of the vehicle clutch, a driving force applied by the engine of the vehicle can be transmitted to a drive axle of the vehicle. The vehicle clutch can have at least two different switching states or gears, which can be defined by a predetermined ratio between the output torque of the engine and the drive torque of the drive axle.

A clutch temperature can be understood to mean the temperature of at least one clutch element, for example the temperature of a clutch disc. Alternatively, a clutch temperature can also be understood as a temperature of the entire vehicle clutch, which can be based, for example, on the determination of an average value of the individual temperatures of the clutch elements. Operating the vehicle may cause the temperature of the vehicle clutch to change. For example, the temperature of the vehicle clutch can increase during a gear shift or a gear change. If the temperature of the vehicle clutch rises above a critical temperature value, this can lead to damage or failure of the vehicle clutch. Determining a clutch temperature of the vehicle clutch therefore contributes to the safety of the vehicle.

A neural network can be understood as a mathematical model that at least partially replicates the structure of the neurons in the human brain. The neural network can be created using a computer. The neural network may include input nodes, output nodes, and a plurality of intermediate nodes disposed between the input nodes and the output nodes. The input nodes can be, for example, data interfaces via which input data can be entered into the neural network. The output nodes can be, for example, data interfaces via which output data from the neural network can be output. The input nodes may be connected to the intermediate nodes and the intermediate nodes may be connected to each other. The intermediate nodes can be connected to the output nodes. The input data can be historical data collected at a specific point in time. Alternatively or additionally, the input data can be synthetic data that was generated by processing recorded or measured data. Analogously, the output data can be historical data or synthetic data.

Information can be stored at least temporarily on the intermediate nodes. It can be provided that at least one arithmetic operation is carried out on the intermediate nodes. The input data can be transferred from the input nodes to the output nodes via the intermediate nodes. During this transfer, the input data can be processed mathematically, for example converted into the output data. The intermediate nodes of the neural network can be arranged in one or more layers or levels. The intermediate nodes can be connected to one another within a layer. In addition, the intermediate nodes of one layer can be connected to the intermediate nodes of other layers. The individual connections of the input nodes, the intermediate nodes and the output nodes can be provided with mathematical weights. Depending on the purpose of the neural network, the individual weights of the connections can be different. During the train nings of the neural network, the weights can be changed. By adjusting the mathematical weights of the connections of the individual nodes during training, the neural network can learn a connection between the input data and the output data. While using the neural network for its intended purpose, the learned context from the neural network can be applied to input data to produce output data according to the intended purpose of using the neural network.

To determine a clutch temperature, for example, a multi-layer perceptron, MLP, can be used as a neural network. This neural network has at least one layer of intermediate nodes and uses at least one non-linear mathematical function to calculate the output data. Another exemplary neural network for determining a clutch temperature can be a fully connected layer, FCL, network. In this neural network, all input nodes, intermediate nodes and output nodes are connected to each other. Furthermore, to determine a coupling temperature, a convolutional neural network, CNN, can be used, for example, in which the intermediate nodes of different layers are at least partially connected to one another in the form of a mathematical convolution function.

The neural network can be trained with training data that was collected for a vehicle clutch that is different from the vehicle clutch. The training data can be historically recorded or synthetically generated data. The training data can be collected using a mathematical simulation, for example the simulation of a heating process of the additional vehicle clutch. Alternatively or additionally, the training data can be collected during a measurement of the additional vehicle clutch on a test stand. Alternatively or additionally, the training data can be collected during operation of the further vehicle clutch, for example while driving a vehicle in which the further vehicle clutch is installed. The vehicle clutch and the further vehicle clutch can have at least one common property, which is scalable according to the scaling factor between the vehicle clutch and the further vehicle clutch. The training data can include at least one value of at least one operating parameter of the further vehicle clutch as input data and values for the clutch temperature of the further vehicle clutch as output data. During the training process, the neural network can learn a relationship between the input data and the output data.

The method includes the step of entering at least one value of at least one operating parameter of the vehicle clutch as input data into the neural network. The at least one value of the at least one operating parameter of the vehicle clutch can be representative of a power supplied to the vehicle clutch. Alternatively or additionally, the at least one value of the at least one operating parameter of the vehicle clutch can be representative of a clutch temperature of the vehicle clutch. The at least one value of the at least one operating parameter can be transmitted to at least one of the input nodes of the neural network, for example by means of an input device. Alternatively, the at least one value of the at least one operating parameter can be transmitted from a control device of the vehicle via a data interface to at least one of the input nodes of the neural network. The at least one value of the at least one operating parameter can be used as input data for using the neural network to determine the clutch temperature. Alternatively or additionally, the at least one value of the at least one operating parameter can be used as input data for training the neural network.

The method further includes the step of calculating a temperature by the neural network. The neural network calculates the temperature based on the input data and a relationship learned by the neural network between a time course of the input data and the temperature. The input data can be processed by the neural network, for example on the intermediate nodes, according to the learned context to calculate the temperature. When learning the connection, the neural network can change the mathematical weighting of the connections of the individual nodes to determine the temperature.

The method further includes the step of applying a determined scaling factor to the calculated temperature to determine the clutch temperature of the vehicle clutch. The scaling factor can be determined based on measured properties of the vehicle clutch. Alternatively or additionally, the scaling factor can be determined based on calculated properties of the vehicle clutch. The scaling factor may be a mathematical value that is added to or subtracted from the value of the calculated temperature. Alternatively or additionally The scaling factor can be a mathematical factor by which the value of the calculated temperature is multiplied or divided. Alternatively or additionally, the scaling factor may be a mathematical function applied to the value of the calculated temperature. The mathematical function can be, for example, linear, non-linear, multidimensional, proportional, progressive, degressive, logarithmic and/or exponential. The value of the calculated temperature can be at least one parameter of the mathematical function. Alternatively, the value of the calculated temperature can be pre-processed mathematically. This preprocessed value of the calculated temperature can be at least one parameter of the mathematical function. The scaling factor can be a combination of the above examples. For example, the scaling factor may consist of a mathematical function and a mathematical factor, each of which is applied to the value of the calculated temperature. For example, the scaling factor can consist of two or more mathematical functions that are linked to one another.

The determined clutch temperature can be used by other components of the vehicle control system. For example, the specific clutch temperature can be used to generate a control value for a control unit of the vehicle, for example a transmission control for an automatic transmission. The control value can also be displayed on a display unit of the vehicle. Alternatively or additionally, the control value based on the clutch temperature can be processed by an evaluation unit, which is used, for example, to monitor the driving safety of the vehicle.

The proposed method enables a clutch temperature to be determined using a neural network. This makes it possible to avoid the use of classic mathematical models, which are generally very complex and therefore time-consuming to calculate. By using a neural network, the calculation time required to determine the clutch temperature can be reduced. Furthermore, the coupling temperature is determined using the scaling factor. This means that there is no need to train another neural network to determine the clutch temperature of the vehicle clutch if one or more operating parameters of the vehicle clutch are changed. Furthermore, it is not necessary to re-determine the scaling factor for each temperature calculated by the neural network. The scaling factor can be determined once for the respective clutch in such a way that it can be applied to all temperatures calculated by the neural network in order to determine the respective clutch temperature of the vehicle clutch. This can also save calculation capacity.

The already trained neural network can be used to determine the clutch temperature of other vehicle clutches. For the other vehicle clutches, only a further scaling factor needs to be determined, which is applied to the temperature calculated by the neural network in order to be able to determine the clutch temperatures of further vehicle clutches. The training and execution of additional neural networks to determine additional clutch temperatures can therefore be dispensed with. This allows the calculation capacity required to determine the clutch temperatures of several vehicle clutches to be kept low. In particular, this makes it possible to determine the clutch temperatures of several vehicle clutches on a transmission control unit without placing a disproportionate strain on the calculation capacity of the transmission control unit. Further calculations on the transmission control unit are therefore possible despite the determination of several clutch temperatures. Finally, the determination of the clutch temperatures can be carried out in real time using the scaling factor due to the low calculation effort and the determined clutch temperatures can be transmitted to other components of the vehicle control system in real time. This increases the safety of the vehicle.

According to one embodiment, the scaling factor is determined based on a relationship between the temperature calculated by the neural network and a measured clutch temperature of the vehicle clutch. The measured temperature of the vehicle clutch can be measured during and/or after tests carried out on the vehicle clutch, for example during a test phase thereof. Alternatively or additionally, the measured temperature can be measured during and/or after operation of the vehicle clutch. The calculated temperature may differ from the measured temperature. This deviation can be compensated for using the scaling factor. Alternatively, the calculated temperature can be compared to a threshold value for the temperature of the vehicle clutch. The closer the calculated temperature is to the threshold value, the greater the influence of the scaling factor on the specific coupling temperature can be. Determining the clutch temperature can thus be adapted to the temperature behavior of the vehicle clutch.

According to one embodiment, the scaling factor is determined based on at least one calculated parameter of the vehicle clutch. The calculated parameter can be calculated using a mathematical model, for example a simulation model of the vehicle clutch. Alternatively or additionally, the calculated parameter can be calculated based on operating data of the vehicle clutch.

The parameter can be representative of physical properties of the vehicle clutch, such as thermal conductivity or a mass of the vehicle clutch. The determination of the clutch temperature can therefore be adapted to different uses of the vehicle clutch.

According to a further embodiment, the scaling factor is also determined depending on the specific clutch temperature. The determined clutch temperature can be compared, for example, with a threshold value for the temperature of the vehicle clutch. The closer the specific clutch temperature is to the threshold value, the greater the influence of the scaling factor on the specific clutch temperature can be. For example, the scaling factor can be greater the closer the specific clutch temperature is to the threshold value. The scaling factor can therefore be adapted to changes in the coupling temperature.

According to one embodiment, the scaling factor is determined as a function of at least one structural property of the vehicle clutch. The structural property can, for example, represent a geometric dimension or a material composition of the vehicle coupling. The structural property can be representative of a thermal conductivity or a heating or cooling process of the vehicle clutch. By taking the structural property into account, the clutch temperature of the vehicle clutch can be determined more precisely.

According to a further embodiment, the clutch temperature is calculated by a further neural network designed for this purpose. The scaling factor is determined based on the calculated temperature and the calculated coupling temperature. The further neural network can be trained with the aforementioned parameters for determining the scaling factor as input data and values for a clutch temperature as output data. Alternatively or additionally, the further neural network can be trained with at least one value of an operating parameter of the vehicle clutch as input data and values for a clutch temperature as output data. The further neural network can learn a connection between the input data and the output data. The further neural network can be executed on a transmission control unit on which the neural network for calculating the temperature is also executed. Alternatively, the further neural network can be executed on a control device designed separately from the transmission control unit. The clutch temperature calculated by the further neural network can be transmitted to the transmission control unit. The scaling factor can be determined on the transmission control unit. The aforementioned parameters can also be used to determine the scaling factor. The scaling factor determined by calculating two neural networks can be used, for example, to determine further coupling temperatures.

According to a further embodiment, the method for determining a clutch temperature of a further vehicle clutch is used. The first temperature is determined as the clutch temperature of the further vehicle clutch. For example, the clutch temperature of the vehicle clutch and the further clutch temperature of the further vehicle clutch can scale according to the scaling factor. This means that the clutch temperature of two vehicle clutches can be determined using a neural network. The computational effort for determining two clutch temperatures can therefore be reduced.

According to a further embodiment, the method is used to determine a clutch temperature of a further vehicle clutch and further comprises the steps: determining a further scaling factor for the further vehicle clutch; and applying the determined further scaling factor to the temperature calculated by the neural network or to the determined clutch temperature in order to determine the clutch temperature of the further vehicle clutch. The further scaling factor can be determined according to the aforementioned embodiments of the method. Alternatively or additionally, the further scaling factor can be dependent on the determined scaling factor. To determine the clutch temperature of the additional vehicle clutch, only the additional scaling factor needs to be determined. A calculation of the further clutch temperature, for example by a neural network, is not necessary. The calculation effort for determining further clutch temperatures can therefore be kept low.

In one embodiment, the further vehicle coupling has a further structural characteristic shaft, which scales with the at least one structural property of the vehicle clutch according to the scaling factor or the further scaling factor. For example, the structural property may be a mass of the vehicle clutch. The further structural property can, for example, be a mass of the further vehicle coupling, which is twice as large as the mass of the vehicle coupling. The mass of the respective vehicle clutches therefore scales with a scaling factor of two. Alternatively, the structural property can be, for example, the number of plates of the vehicle clutch. The further structural property can be, for example, the number of plates of the additional vehicle clutch, which is three times as large as the number of plates of the vehicle clutch. The number of plates of the respective vehicle clutches therefore scales with a further scaling factor of three. The different temperatures of the individual vehicle clutches can therefore be determined in a simple manner using the respective scaling factors.

According to a further embodiment, the at least one structural property or the at least one further structural property of the vehicle clutch is selected from at least one of the following: a material of the vehicle clutch; a material composition of the vehicle clutch; a thermal conductivity coefficient of the vehicle clutch; a type of vehicle clutch; and using the vehicle clutch. A type of vehicle clutch can be understood to mean, for example, a vehicle clutch based on mechanical pressure or one that works on the principle of an eddy current brake. A use of the vehicle clutch can be understood to mean, for example, the use of the vehicle clutch in a passenger car or a truck. The structural properties mentioned can be representative of the heating or cooling process of the respective vehicle clutch.

According to a further embodiment, the scaling factor or the further scaling factor is determined by a further neural network designed for this purpose. The additional neural network can be trained with the above-mentioned parameters to determine the scaling factor. The additional neural network can be executed on a transmission control unit. Alternatively, the neural network can be executed on a control device that is separate from the transmission control unit. The scaling factor or the further scaling factor can be transmitted to the transmission control unit. Using the further neural network, the scaling factor or the further scaling factor can be determined more quickly.

According to a further embodiment, the method further comprises the step of determining at least one input value which is representative of a power supplied to the vehicle clutch. The at least one input value is determined based on processing successive values for the power supplied to the vehicle clutch. According to this embodiment, the method further comprises the step of entering the at least one input value as input data into the neural network.

The power supplied to the vehicle clutch can be understood as a physical power, i.e. an amount of energy which is supplied to the vehicle clutch during a predetermined period of time. For example, the power supplied to the vehicle clutch can be a switching power supplied to the vehicle clutch during a switching process or a gear change. The power supplied to the vehicle clutch may be representative of a change in the clutch temperature of the vehicle clutch.

The at least one input value can be transmitted to at least one of the input nodes of the neural network, for example by means of an input device. Alternatively, the at least one input value can be transmitted from a control device of the vehicle via a data interface to at least one of the input nodes of the neural network. The at least one input value can be used as input data for using the neural network to determine the clutch temperature. Alternatively or additionally, the at least one input value can be used as input data for training the neural network.

In this embodiment, determining the clutch temperature is also based on a time course of the input data. This means that a temporal change in the input data can also be taken into account by the neural network. For example, a cooling or heating phase of the vehicle clutch can be recorded and taken into account when calculating the clutch temperature. Furthermore, for example, the exceeding of a limit value for the clutch temperature or a deviation from a standard behavior of the clutch temperature during the heating or cooling phase can be taken into account. The clutch temperature can therefore can also be determined more precisely. Furthermore, the time course of the input data is not determined by the neural network itself, but is only transmitted to it in the form of the processed input value. This reduces the computational effort required to calculate the temperature. The structure of the neural network can therefore be made less complex. Therefore, the storage space required for the neural network can also be reduced.

According to a further embodiment, the at least one operating parameter of the vehicle clutch is selected from at least one of the following: a torque of a drive axle of a vehicle engine, which is in mechanical operative connection with the vehicle clutch; a speed difference between two rotating clutch elements of the vehicle clutch; a speed of a rotating clutch element of the vehicle clutch; a mechanical pressure acting on a coupling element of the vehicle clutch; a current intensity of an electric current flowing through a coupling element of the vehicle clutch; and a sump temperature of a vehicle transmission at the beginning of a shifting process of the vehicle clutch. Coupling elements of the vehicle clutch can be, for example, the clutch disks of a vehicle clutch, which can be connected to transmit power from the engine to the drive axle. The above parameters may be representative of power supplied to the vehicle clutch. Alternatively or additionally, the above parameters can be representative of a clutch temperature of the vehicle clutch. By using at least one of these parameters, the determination of the clutch temperature can be made easier.

In a second aspect, the invention relates to a control device for determining clutch temperatures of a plurality of vehicle clutches. The control device comprises a computer-readable storage medium on which a neural network is stored, which is designed to determine at least one temperature of at least one vehicle clutch from the plurality of vehicle clutches. The control device further comprises an input device for inputting input data into the neural network. The input data includes at least one value of at least one operating parameter of the vehicle clutch. The control device further comprises an output device for outputting the calculated temperature by the neural network. Furthermore, the control device comprises an application device for applying a determined scaling factor to the output temperature in order to determine a clutch temperature of the at least one vehicle clutch from the plurality of vehicle clutches.

According to one embodiment, the control device further comprises a determination device for determining the scaling factor for the at least one temperature as a function of at least one structural property of the at least one vehicle clutch from the plurality of vehicle clutches.

The mentioned devices of the control device according to the second aspect can be designed to receive, process and forward electrical signals. The mentioned devices of the control device according to the second aspect can be designed to carry out the method according to the first aspect. Analogously, the method according to the first aspect can be carried out by the control device according to the second aspect. The embodiments, technical effects and advantages explained in the first aspect therefore also apply analogously to the control device according to the second aspect.

Brief description of the drawings

• 1 shows a flowchart with steps of a method for determining a clutch temperature of a vehicle clutch using a neural network and a scaling factor for the clutch temperature, according to an embodiment of the invention.
• 2 schematically shows a control device for determining a clutch temperature of a vehicle clutch with a neural network and a scaling factor according to a further embodiment of the invention.
• 3a-3c show various options for determining the clutch temperature of other vehicle clutches using a scaling factor according to further embodiments of the invention.

Detailed Description of Embodiments

1 shows a flowchart with steps of a method for determining a clutch temperature of a vehicle clutch using a neural network according to an embodiment of the invention.

In a first determination step BS1, at least one value of at least one operating parameter of the vehicle clutch is entered into the neural network as input data. The at least one value of the at least one operating parameter is transmitted to at least one input node of the neural network.

In a second determination step BS2, a temperature is calculated by the neural network. The temperature is calculated based on the input data and a relationship between the input data and the temperature learned by the neural network.

To calculate the temperature, the input data transmitted to the input nodes of the neural network are transmitted to intermediate nodes of the neural network via connections mathematically weighted by the neural network. The transmitted input data is processed at the intermediate nodes and transmitted to output nodes of the neural network via connections mathematically weighted by the neural network. The mathematical weighting of the respective connections was adjusted by the neural network based on a training data set during a training process of the neural network that preceded the determination process. At the end of the method implementation, there is a value for the temperature on at least one output node of the neural network.

In a third determination step BS3, a determined scaling factor is applied to the temperature calculated by the neural network in order to determine the clutch temperature of the vehicle clutch.

The scaling factor is in the exemplary embodiment 1 determined based on a deviation of the temperature calculated by the neural network and a measured clutch temperature of the vehicle clutch. Furthermore, the scaling factor is determined based on a measured thermal conductivity coefficient of the vehicle clutch. To determine the scaling factor, the determined coupling temperature is also compared with a limit value for a maximum permissible coupling temperature. The closer the specific coupling temperature is to the limit value, the larger the scaling factor is chosen. Furthermore, the scaling factor is determined depending on the steel mass of the plates of the vehicle clutch. Further parameters for determining the scaling factor are not excluded.

Using the scaling factor, the clutch temperature of the vehicle clutch can be determined in a simple manner. Furthermore, the clutch temperatures of other vehicle clutches can also be determined based on the temperature calculated by the neural network using a scaling factor. This means that another neural network does not have to be trained for each vehicle clutch; instead, it is sufficient to apply a respective scaling factor to the calculated temperature of the vehicle clutch. This can save calculation capacity, for example on a transmission control unit. Furthermore, the clutch temperatures can be determined in real time.

2 schematically shows a control device 10 for determining a clutch temperature of a vehicle clutch, not shown, with a neural network 12 according to a further embodiment of the invention. The control device 10 can be part of the vehicle clutch or designed separately from it.

The control device 10 includes a computer-readable storage medium 14 on which the neural network 12 is stored. The control device 10 further comprises an input device 16, which is designed to receive values 18a, 18b, 18c of operating parameters of the vehicle clutch. The input device 16 transmits the values 18a, 18b, 18c of the operating parameters of the vehicle clutch as input data 20a to the neural network 12.

The control device 10 further comprises detection devices 22a, 22b, which detect successive values 24a, 24b or 24c, 24d for a power supplied to the vehicle clutch. The detection devices 22a, 22b are low-pass filters and the values 24a, 24b, 24c, 24d for a power supplied to the vehicle clutch are a switching power supplied to the vehicle clutch during a switching process or gear change. The detected values 24a, 24b, 24c and 24d for the switching power are transmitted from the detection devices 22a, 22b to a determination device 26. The determination device 26 determines at least one average value for the switching power by processing the temporally successive values 24a, 24b, 24c, 24d. The at least one mean value for the switching power is transmitted from the determining device 26 to the input device 16 as an input value 28. The input device 16 transmits the input value 28 as input data 20b to the neural network 12.

The neural network 12 calculates a temperature T1 of the vehicle clutch from the input data 20a, 20b. The calculated temperature T1 is output from an output device 30 to an application device 32. The application device 32 applies a determined scaling factor SF1 to the calculated temperature T1. The scaling factor SF1 is determined by a Determination device 34 determined based on several parameters 36a, 36b of the vehicle clutch. By applying the scaling factor SF1 to the calculated temperature T1, the clutch temperature KT1 of the vehicle clutch is determined. The clutch temperature KT1 is transmitted to other components of the vehicle clutch. The determination device 34 can be designed separately from the control device 10.

Based on the temperature T1 calculated by the neural network 12, the clutch temperatures of further vehicle clutches can be determined, as in the 3a until 3c shown.

The 3a until 3c show various options for determining the clutch temperature of other vehicle clutches based on the temperature T1 calculated by the neural network 12.

The 3a shows schematically the determination of a clutch temperature for a vehicle clutch K2 using the neural network 12 from the embodiment of 2 . Analogous to the embodiment of 2 the neural network 12 calculates a first temperature T1. In the embodiment of 3a This calculated temperature T1 is determined as the clutch temperature KT2 of the clutch K2. In other words, in the embodiment the 3a a scaling factor with the value one is determined.

The 3b shows schematically the determination of a clutch temperature for a first vehicle clutch K1 and a second vehicle clutch K2 using the neural network 12 from the embodiment of 2 . Analogous to the embodiment of 2 the neural network 12 calculates a first temperature T1. In the embodiment of 3b is based on this calculated temperature T1 by the in 2 illustrated application device 32, a first scaling factor SF1 is applied to determine the clutch temperature KT1 of the first vehicle clutch K1. Furthermore, in the embodiment the 3b through the in 2 illustrated application device 32 applies a second scaling factor SF2 to the calculated temperature T1 in order to determine the clutch temperature KT2 of the second vehicle clutch K2. The clutch temperature KT2 therefore does not have to be calculated in a complex manner, but can be determined by simply applying the second scaling factor SF2 to the temperature T1.

The 3c shows schematically the determination of a clutch temperature for a first vehicle clutch K1 and a second vehicle clutch K2 using the neural network 12 from the embodiment of 2 . Analogous to the embodiment of 2 the neural network 12 calculates a first temperature T1. In the embodiment of 3c is based on this calculated temperature T1 by the in 2 illustrated application device 32, a first scaling factor SF1 is applied to determine the clutch temperature KT1 of the first vehicle clutch K1. The specific clutch temperature KT1 is determined by the in 2 illustrated application device 32, a second scaling factor SF2 is applied to determine the clutch temperature KT2 of the second vehicle clutch K2. The clutch temperature KT2 therefore does not have to be calculated in a complex manner, but can be determined by simply applying the second scaling factor SF2 to the clutch temperature KT1.

Reference symbols

10

Control device

12

Neural network

14

storage medium

16

Input device

18a, 18b, 18c

Values of operating parameters

22a, 22b

Detection devices

24a, 24b,

successive values for one of the vehicle clutches

24c, 24d

power supplied

26

Determination device

28

Input value

30

Dispensing device

32

Application device

34

Detection device

36a, 36b

Vehicle clutch parameters

SF1

first scaling factor

SF2

second scaling factor

T1

calculated temperature

KT1

first clutch temperature

KT2

second clutch temperature

K1

first vehicle clutch

K2

second vehicle clutch

BS1

first determination step

BS2

second determination step

BS3

third determination step

Claims (15)

Method for determining a clutch temperature (KT1, KT2) of a vehicle clutch (K1, K2) using a neural network (12), the method comprising the following steps: - Input (BS1) of at least one value (18a, 18b, 18c) of at least one operating parameter of the vehicle clutch (K1, K2) as input data (20a) into the neural network (12); - Calculating (BS2) a temperature (T1) by the neural network (12), based on the input data (20a) and a relationship between the input data (20a) and the temperature (T1) learned by the neural network (12); and - Applying (BS3) a determined scaling factor (SF1, SF2) to the temperature (T1) in order to determine the clutch temperature (KT1, KT2) of the vehicle clutch (K1, K2). Procedure according to Claim 1 , wherein the scaling factor (SF1, SF2) is determined based on a relationship between the temperature (T1) calculated by the neural network (12) and a measured clutch temperature of the vehicle clutch (K1, K2). Procedure according to Claim 1 or 2 , wherein the scaling factor (SF1, SF2) is determined based on at least one calculated parameter of the vehicle clutch (K1, K2). Method according to one of the preceding claims, wherein the scaling factor (SF1, SF2) is further determined as a function of the determined clutch temperature (KT1, KT2). Method according to one of the preceding claims, wherein the scaling factor (SF1, SF2) is determined as a function of at least one structural property of the vehicle clutch (K1, K2). Method according to one of the preceding claims, wherein the clutch temperature (KT1, KT2) is calculated by a further neural network trained for this purpose, the scaling factor (SF1, SF2) being based on the calculated temperature (T1) and the calculated clutch temperature (KT1, KT2). is determined. Method according to one of the preceding claims, wherein the method for determining a clutch temperature (KT2) of a further vehicle clutch (K2) is used, the first temperature (T1) being determined as the clutch temperature (KT2) of the further vehicle clutch (K2). Procedure according to one of the Claims 1 until 6 , wherein the method for determining a clutch temperature (KT2) of a further vehicle clutch (K2) is used, further comprising the steps: - determining a further scaling factor (SF2) for the further vehicle clutch (K2); and - applying the determined further scaling factor (SF2) to the temperature (T1) calculated by the neural network (12) or to the determined clutch temperature (KT1) in order to determine the clutch temperature (KT2) of the further vehicle clutch (K2). Procedure according to one of the Claims 5 until 8th , wherein the further vehicle clutch (K2) has a further structural property which scales with the at least one structural property of the vehicle clutch (K1) according to the scaling factor (SF1) or the further scaling factor (SF2). Procedure according to one of the Claims 5 until 9 , wherein the at least one structural property or the at least one further structural property of the vehicle clutch (K1, K2) is selected from at least one of the following: a material of the vehicle clutch (K1, K2); a material composition of the vehicle clutch (K1, K2); a thermal conductivity coefficient of the vehicle clutch (K1, K2); a type of vehicle clutch (K1, K2); and using the vehicle clutch (K1, K2). Method according to one of the preceding claims, wherein the scaling factor (SF1) or the further scaling factor (SF2) is determined by a further neural network trained for this purpose. A method according to any one of the preceding claims, wherein the method further comprises the following steps: - Determining at least one input value (28) which is representative of a power supplied to the vehicle clutch (K1, K2), the at least one input value (28) being based on processing temporally successive values (24a, 24b, 24c, 24d) for the the power supplied to the vehicle clutch (K1, K2) is determined; and - Entering the at least one input value (28) as input data (20b) into the neural network (12). Method according to one of the preceding claims, wherein the at least one operating para meter of the vehicle clutch (K1, K2) is selected from at least one of the following: a torque of a drive axle of a vehicle engine, which is in mechanical operative connection with the vehicle clutch (K1, K2); a speed difference between two rotating clutch elements of the vehicle clutch (K1, K2); a speed of a rotating clutch element of the vehicle clutch (K1, K2); a mechanical pressure acting on a coupling element of the vehicle clutch (K1, K2); a current intensity of an electrical current flowing through a coupling element of the vehicle clutch (K1, K2); and a sump temperature of a vehicle transmission at the beginning of a shifting process of the vehicle clutch (K1, K2). Control device (10) for determining clutch temperatures (KT1, KT2) of a plurality of vehicle clutches (K1, K2), the control device (10) comprising: - a computer-readable storage medium (14), on which a neural network (12) is stored, which is designed to calculate at least one temperature (T1) of at least one vehicle clutch (K1) from the plurality of vehicle clutches (K1, K2); - an input device (16) for inputting input data (20a, 20b) into the neural network (12), wherein the input data (20a, 20b) contains at least one value (18a, 18b, 18c) of at least one operating parameter of the vehicle clutch (K1, K2 ) include; - an output device (30) for outputting the calculated temperature (T1) from the neural network (12); and - an application device (32) for applying a determined scaling factor (SF1, SF2) to the output temperature (T1) in order to determine a clutch temperature (KT1, KT2) of the at least one vehicle clutch (K1, K2) from the plurality of vehicle clutches. Control device (10). Claim 14 , further comprising: - a determination device (34) for determining the scaling factor (SF1, SF2) for the at least one temperature (T1) as a function of at least one structural property (36a, 36b) of the at least one vehicle clutch (K1, K2) from the Majority of vehicle clutches (K1, K2).

Images