Determining the clutch temperature of a vehicle clutch by means of on-demand activation of a neural network

Description

Technical field

[0001] The present invention relates to a method for determining the clutch temperature of a vehicle clutch by means of demand-based activation of a neural network. The invention further relates to a method for training a neural network configured to determine the clutch temperature of a vehicle clutch. The invention also relates to an associated control device for determining the clutch temperature of a vehicle clutch by demand-based activation of a neural network. State of the art

[0002] The temperature of a vehicle clutch can be calculated using a classic rule-based mathematical model. This calculation can be performed in a transmission control unit. Machine learning, such as a neural network, can be used for this purpose. However, running a neural network on the transmission control unit requires significant computing power.

[0003] DE 10 2020 206 309 A1 relates to a device and method for detecting and reducing a disturbance vibration in a vehicle. Description of the invention

[0004] The invention relates in a first aspect to a method for determining the clutch temperature of a vehicle clutch using a neural network.

[0005] The vehicle clutch can be installed in a motor-driven vehicle, such as a car, a motorcycle, or a two-wheeler that is at least partially electrically powered. The vehicle clutch allows the transmission of drive force from the vehicle's engine to a drive axle. The vehicle clutch can have at least two different switching states or gears, which can be defined by a predetermined ratio between the engine's output torque and the drive axle's input torque.

[0006] Clutch temperature can refer to the temperature of at least one clutch element, such as the temperature of a clutch disc. Alternatively, it can also refer to the temperature of the entire vehicle clutch, which might be determined by averaging the temperatures of the individual clutch elements. The vehicle's clutch temperature can change during operation. For example, it can rise during gear changes. If the clutch temperature exceeds a critical threshold, it can lead to damage or failure. Therefore, determining the clutch temperature contributes to vehicle safety.

[0007] A neural network can be understood as a mathematical model that at least partially replicates the structure of neurons in the human brain. A neural network can be created using a computer. It can have input nodes, output nodes, and multiple intermediate nodes located between the input and output nodes. The input nodes can be, for example, data interfaces through which input data can be fed into the neural network. The output nodes can be, for example, data interfaces through which output data can be sent from the neural network. The input nodes can be connected to the intermediate nodes, and the intermediate nodes can 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, which is generated by processing collected or measured data. Similarly, the output data can be historical data or synthetic data.

[0008] Intermediate nodes can be used to temporarily store information. At least one arithmetic operation can be performed on each intermediate node. 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 mathematically processed, for example, converted into output data. The intermediate nodes of the neural network can be arranged in one or more layers. Intermediate nodes within a layer can be interconnected. Additionally, intermediate nodes within a layer can be connected to intermediate nodes in other layers. The individual connections between the input nodes, intermediate nodes, and output nodes can be assigned mathematical weights.Depending on the purpose of the neural network, the individual connection weights can vary. These weights can be modified during the neural network's training. By adjusting the mathematical weights of the connections between individual nodes during training, the neural network can learn a relationship between the input data and the output data. When the neural network is used for its intended purpose, this learned relationship can be applied to the input data to generate output data according to the network's predefined purpose.

[0009] To determine a coupling temperature, 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 example of a neural network for determining a coupling temperature is a fully connected layer (FCL) network. In this neural network, all input nodes, intermediate nodes, and output nodes are interconnected. Furthermore, a convolutional neural network (CNN) can be used to determine a coupling temperature, in which the intermediate nodes of different layers are at least partially connected by a mathematical convolution function.

[0010] The procedure includes the step of detecting a shifting operation of the vehicle clutch. A shifting operation can be manual, for example, by the driver operating a pedal, or automatic, via a shift program of the vehicle. A shifting operation of the vehicle clutch can be detected by a change in at least one operating parameter of the vehicle clutch. For example, the rotational speed of a clutch element of the vehicle clutch can change during the shifting operation. Alternatively or additionally, the pressure acting on a clutch element of the vehicle clutch can change during the shifting operation. Alternatively or additionally, the current flowing through a clutch element of the vehicle clutch can change during the shifting operation. Alternatively or additionally, a shifting operation can be detected by a change in the target gear of the vehicle clutch.

[0011] The procedure further includes the step of activating the neural network to determine the clutch temperature. The neural network is activated upon detection of the shifting process. Upon detection of the shifting process, an activation signal can be generated, for example, by a vehicle control unit. This control signal can be used to activate the neural network. For instance, this control signal can be transmitted to an activation unit, which can be configured to activate the neural network depending on the receipt of the control signal. Activation of the neural network can be understood as the commencement of a calculation performed by the neural network. Alternatively or additionally, activation of the neural network can be understood as the neural network accessing data necessary for the calculation.

[0012] The method further includes the step of inputting at least one value of at least one operating parameter of the vehicle clutch as input data into the neural network. This at least one value of the operating parameter can be representative of the power supplied to the clutch. Alternatively or additionally, this at least one value can be representative of the clutch temperature. This at least one value of the operating parameter can, for example, be transmitted to at least one of the input nodes of the neural network via an input device. Alternatively, this at least one value of the operating parameter can be transmitted from a vehicle control unit to at least one of the input nodes of the neural network via a data interface.At least one value of the at least one operating parameter can be used as input data for the neural network to determine the coupling temperature. Alternatively or additionally, at least one value of the at least one operating parameter can be used as input data for training the neural network.

[0013] The method further includes the step of determining a coupling temperature using a neural network. The neural network determines the coupling temperature based on the input data and a relationship, learned by the neural network, between at least one operating parameter and the coupling temperature. The input data can be processed by the neural network, for example, at the intermediate nodes, according to the learned relationship to determine the coupling temperature. During the learning process, the neural network can modify the mathematical weights of the connections between the individual nodes to determine the coupling temperature.

[0014] The method further includes the step of outputting the determined clutch temperature by the neural network. This determined clutch temperature can be output by the neural network to a dedicated electrical signal processing device. The clutch temperature determined and output by the neural network can be used by other vehicle control components. For example, the determined clutch temperature can be used to generate a control signal for a vehicle control unit, such as a transmission control unit for an automatic transmission. This control signal can also be displayed on a vehicle display unit. Alternatively or additionally, the control signal based on the clutch temperature can be processed by an evaluation unit, which, for example, is used to monitor the vehicle's driving safety.

[0015] The procedure further includes the step of deactivating the neural network used to determine the clutch temperature. The neural network is deactivated depending on the determined clutch temperature. Deactivating the neural network can be understood as terminating or aborting the calculation of the clutch temperature by the neural network. Alternatively or additionally, deactivating the neural network can be understood as terminating or aborting the neural network's access to input data. The neural network can be deactivated by a specially trained control unit in the vehicle. Alternatively, the neural network itself can deactivate it.For this purpose, the neural network can be trained to recognize a deactivation condition, based on which the neural network is deactivated. To deactivate the neural network, the specific coupling temperature can be processed to determine a coupling temperature-dependent deactivation condition. Alternatively, the specific coupling temperature can be used directly, i.e., unprocessed, to deactivate the neural network.

[0016] The proposed method enables the determination of a clutch temperature using a neural network. This eliminates the need for classical mathematical models, which are generally very complex and therefore time-consuming to calculate. By using a neural network, the computation time required to determine the clutch temperature can be reduced. Furthermore, the proposed method allows the neural network to be activated on demand for determining the clutch temperature. The neural network is only activated when a shifting operation of the vehicle clutch is detected. During a shifting operation, the vehicle clutch is generally subjected to higher loads than during normal driving without shifting.Due to this increased load on the vehicle clutch, a particularly pronounced fluctuation in clutch temperature is to be expected during the shifting process. This fluctuation in clutch temperature therefore requires close monitoring. Conversely, when no shifting is taking place, the clutch temperature generally fluctuates less. Therefore, determining or monitoring the clutch temperature is not strictly necessary during this period. The neural network can thus be deactivated during this time. The proposed method can, for example, be implemented on a transmission control unit. In this case, the on-demand activation of the neural network enables the demand-based allocation of the computational resources available on the transmission control unit, such as available memory and / or computational time.The neural network only accesses these processing capacities when a gear shift is detected. If no gear shift is detected, the processing capacities of the transmission control unit can be used for other purposes, such as ensuring the functionality of the transmission.

[0017] In one embodiment, the neural network is deactivated when the clutch temperature falls below a defined threshold. This threshold can be defined by a user, such as the vehicle's driver. Alternatively, it can be defined by the vehicle manufacturer. The defined clutch temperature threshold can be representative of a temperature below which the probability of clutch damage due to temperature rise is sufficiently low. The threshold can be based on empirical data. Alternatively or additionally, it can be based on mathematical calculations or experimental tests. The threshold can be chosen differently for different vehicle clutches.It may be implemented that below a defined threshold, determining or monitoring the clutch temperature is no longer necessary. For example, below this threshold, clutch damage due to a temperature increase can be ruled out with sufficient probability. If the clutch temperature falls below the defined threshold, determining the clutch temperature by the neural network is no longer essential. The neural network can therefore be deactivated. Defining a threshold for the clutch temperature, below which the neural network is deactivated, thus improves the vehicle's driving safety.

[0018] According to another embodiment, the clutch temperature is determined by the neural network within a predefined time interval. This time interval can be specified by a user, such as the vehicle driver. Alternatively, it can be specified by the vehicle manufacturer. If the clutch temperature is determined by the neural network on a transmission control unit, the time interval can be determined based on the available processing power of the transmission control unit. For example, the neural network may be configured to use a maximum of 20%, 10%, 5%, or 1% of the total processing time available on the transmission control unit to determine the clutch temperature.The determination of the clutch temperature by the neural network within the specified time interval can be repeated at regular intervals as long as the neural network is activated. Alternatively, the determination of the clutch temperature by the neural network within the specified time interval can be performed a predetermined maximum number of times, for example, once, twice, or three times. Once the maximum number of predetermined calculation runs has been reached, the neural network can be configured to no longer determine the clutch temperature. By specifying the time interval within which the neural network determines the clutch temperature, the determination method can be adapted to different types of vehicle clutches or different types of control units on which the determination is performed.Furthermore, the computing capacity available to the neural network for determining the coupling temperature can be adapted to specific requirements, for example those of the user or the manufacturer, by specifying the time interval.

[0019] According to a further embodiment, the predetermined time interval is specified depending on the determined clutch temperature. For example, the time interval can be shortened as the determined clutch temperature increases. In this case, the clutch temperature can be determined more frequently at comparatively high clutch temperatures than at comparatively low clutch temperatures. Other forms of temperature-dependent determination of the time interval are not excluded by the present invention. The temperature-dependent determination of the time interval allows the determination method to be adapted to different operating conditions of the vehicle clutch.

[0020] According to one embodiment, the method further comprises a step of determining at least one input value that is representative of the power supplied to the vehicle clutch. This input value is determined based on the processing of successive values ​​for the power supplied to the vehicle clutch. The power supplied to the vehicle clutch can be understood as physical power, i.e., an amount of energy supplied to the vehicle clutch during a predetermined period of time. For example, the power supplied to the vehicle clutch could be the switching power supplied to the vehicle clutch during a shifting operation or gear change. The power supplied to the vehicle clutch could also be representative of a change in the clutch temperature.

[0021] The power supplied to the vehicle clutch can be recorded at specific time intervals. The individual values ​​for the power supplied to the vehicle clutch can, for example, be arranged in ascending order according to their recording time. These sequential values ​​for the power supplied to the vehicle clutch can be processed mathematically, for example, using a predefined calculation such as averaging.

[0022] In this embodiment, the method further includes the step of inputting at least one input value as input data into the neural network. The at least one input value can, for example, be transmitted to at least one of the input nodes of the neural network via an input device. Alternatively, the at least one input value can be transmitted from a control unit of the vehicle to at least one of the input nodes of the neural network via a data interface. The at least one input value can be used as input data for 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.

[0023] In this embodiment, determining the clutch temperature is also based on the temporal profile of the input data. This allows the neural network to take into account changes in the input data over time. For example, a cooling or heating phase of the vehicle clutch can be detected and considered when determining the clutch temperature. Furthermore, exceeding a limit value for the clutch temperature or a deviation from normal clutch temperature behavior during the heating or cooling phase can be considered. The clutch temperature can therefore be determined more precisely by the neural network. Moreover, the temporal profile of the input data is not determined by the neural network itself, but merely transmitted to it in the form of the processed input value. This reduces the computational effort required to determine the clutch temperature.This allows the structure of the neural network to be less complex. Therefore, the storage space required for the neural network can also be reduced.

[0024] According to one embodiment, the at least one input value is determined at predetermined time intervals. For example, the at least one input value can be determined at intervals of 1 second, 100 ms, or 10 ms. The determination of the input value can thus be adapted to the time intervals within which the neural network determines the coupling temperature. This provides the neural network with a current input value, i.e., one determined within the same time interval, within which the neural network determines the coupling temperature. The coupling temperature can therefore be determined even more precisely by the neural network. Since determining the input value generates a low computational load, efficient computation with high performance can be achieved by decoupled from the execution of the neural network.

[0025] In a second aspect, the invention relates to a method for training a neural network configured to determine the clutch temperature of a vehicle clutch. The method comprises the following steps: providing at least one value of an operating parameter of the vehicle clutch as input data; providing values ​​for the clutch temperature as output data; and training the neural network with the input and output data to learn the relationship between the input data and the clutch temperature.

[0026] The values ​​for at least one operating parameter of the vehicle coupling and the values ​​for the coupling temperature can be acquired using specially designed devices for electrical signal processing. The acquired values ​​can be provided to an input device for inputting data into the neural network. Alternatively, the acquired values ​​can be transmitted from the specially designed devices to the input nodes of the neural network via a data interface. Alternatively or additionally, the input data or the output data can be in the form of synthetic data, which can be generated by converting acquired or defined data.

[0027] According to one embodiment, the neural network is further trained using at least one specific input value, which is representative of the power supplied to the vehicle clutch. This input value is determined based on the processing of successive values ​​for the power supplied to the vehicle clutch.

[0028] According to one embodiment, the neural network is trained according to the method of the first aspect after the method of the second aspect. This allows the technical effects and advantages of both aspects to be combined.

[0029] According to one embodiment, 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 that is mechanically connected to 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 clutch element of the vehicle clutch; a current intensity of an electric current flowing through a clutch element of the vehicle clutch; and a sump temperature of a vehicle transmission at the beginning of a shifting operation of the vehicle clutch. Clutch elements can, for example, be the clutch discs of a vehicle clutch, which can be connected to transmit torque from the engine to the drive axle.The parameters above can be representative of the power supplied to the vehicle clutch. Alternatively or additionally, the parameters above can be representative of the clutch temperature. Using at least one of these parameters can thus facilitate the determination of the clutch temperature.

[0030] In a third aspect, the invention relates to a control device for determining the clutch temperature of a vehicle clutch. The control device comprises a computer-readable storage medium on which a neural network for determining the clutch temperature is stored. Furthermore, the control device comprises a detection device for recognizing a shifting operation of the vehicle clutch and an activation device for activating the neural network, depending on the detection of a shifting operation. The control device also comprises an input device for inputting data into the neural network, wherein the input data includes at least one value of at least one operating parameter of the vehicle clutch.The control device further includes an output device for outputting the specified coupling temperature by the neural network and a deactivation device for deactivating the neural network, depending on the specified coupling temperature.

[0031] In one embodiment, the coupling temperature is determined by the neural network according to the method described in the first aspect. Furthermore, the neural network was trained according to the method described in the second aspect.

[0032] The control device components described in the third aspect can be configured to receive, process, and transmit electrical signals. These control device components can be configured to perform the procedure described in the first aspect and / or the second aspect. Similarly, the procedure described in the first aspect or the second aspect can be performed by the control device described in the third aspect. The embodiments, technical effects, and advantages described in relation to the first and second aspects therefore also apply analogously to the control device described in the third aspect. Brief description of the drawings

[0033] Figure 1 shows a flowchart with steps of a method for determining the clutch temperature of a vehicle clutch using a neural network, according to one embodiment of the invention. Figure 2 shows a flowchart with steps of a method for training a neural network configured to determine the clutch temperature of a vehicle clutch, according to another embodiment of the invention. Figure 3 schematically shows a control device for determining the clutch temperature of a vehicle clutch using a neural network, according to another embodiment of the invention. Detailed description of embodiments

[0034] Figure 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.

[0035] In a first determination step BS1, a switching operation of the vehicle clutch is detected. In the exemplary embodiment of the Figure 1 detected by a change in the target gear of the vehicle coupling.

[0036] In a second determination step, BS2, the neural network for determining the clutch temperature is activated. Activation occurs depending on the detection of the shifting process. In the exemplary embodiment, activation takes place as follows: Figure 1 based on an activation signal generated by an activation device upon detection of a switching process.

[0037] In a third determination step, BS3, at least one value of at least one operating parameter of the vehicle coupling is entered as input data into the neural network. This at least one value of the at least one operating parameter is then transferred to at least one input node of the neural network.

[0038] In a fourth determination step, BS4, the neural network determines a coupling temperature. The coupling temperature is determined based on the input data and a relationship learned by the neural network between the input data and the coupling temperature.

[0039] To determine the coupling temperature, input data transmitted to the input nodes of the neural network is transferred to intermediate nodes of the neural network via mathematically weighted connections. At these intermediate nodes, the transmitted input data is processed and then transferred to output nodes of the neural network via mathematically weighted connections. The mathematical weights of these connections were adjusted by the neural network during a training process prior to the determination procedure, based on a training dataset. At least one output node of the neural network provides a coupling temperature value at the end of the process.

[0040] In a fifth determination step, BS5, the determined coupling temperature is output by the neural network. In the exemplary embodiment, the coupling temperature is... Figure 1 output to an output device.

[0041] In a sixth determination step, BS6, the neural network for determining the coupling temperature is deactivated. Deactivation occurs depending on the determined coupling temperature. In the exemplary embodiment of the Figure 1 The neural network is deactivated when the specific coupling temperature falls below a defined threshold.

[0042] The neural network can be activated as needed, depending on the detection of a switching process. Furthermore, the neural network can be deactivated as needed, depending on the determined clutch temperature. The determination of the clutch temperature by the neural network can thus be adapted to the given computing capacity of the control unit on which the determination by the neural network takes place.

[0043] Figure 2 shows a flowchart with steps of a method for training a neural network which is designed to determine a clutch temperature of a vehicle clutch, according to a further embodiment of the invention.

[0044] In the first training step TS1, at least one value of at least one operating parameter of the vehicle coupling is provided as input data. This value is representative of a coupling temperature of the vehicle coupling and is transmitted to at least one input node of the neural network.

[0045] In a second training step, TS2, values ​​for a coupling temperature are provided as output data. These values ​​are measured values ​​for the coupling temperature. In an embodiment not shown, the coupling temperature values ​​are synthetically generated. These values ​​are transmitted to at least one output node of the neural network.

[0046] In a third training step TS3, the neural network is trained with the input data and the output data to learn a relationship between the input data and the coupling temperature.

[0047] The method for determining the coupling temperature according to the embodiment of the Figure 1 The neural network used can be implemented according to the method of the embodiment of the Figure 2 be trained.

[0048] Figure 3 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.

[0049] The control unit 10 comprises a computer-readable storage medium 14 on which the neural network 12 is stored. The control unit 10 further comprises an input device 16, which is configured to receive values ​​18a, 18b, 18c of operating parameters of the vehicle coupling. The input device 16 transmits the values ​​18a, 18b, 18c of the operating parameters of the vehicle coupling as input data 20a to the neural network 12.

[0050] The control unit 10 includes a detection device 22, which detects a switching operation of the vehicle clutch based on a switching signal 24. Depending on the detected switching operation, the detection device 22 generates a detection signal 26 and transmits it to an activation device 28. Depending on the receipt of the detection signal 26, the activation device 28 generates an activation signal 30 and transmits it to the neural network 12. Depending on the receipt of the activation signal 30, the neural network 12 is activated.

[0051] The control unit 10 further comprises detection devices 32a, 32b, which detect successive values ​​34a, 34b and 34c, 34d respectively for the power supplied to the vehicle clutch. Detection devices 32a, 32b are low-pass filters, and the values ​​34a, 34b, 34c, 34d for the power supplied to the vehicle clutch represent the switching power supplied to the vehicle clutch during a shifting operation or gear change. The detected values ​​34a, 34b, 34c, and 34d for the switching power are transmitted by the detection devices 32a, 32b to a determination device 36. The determination device 36 determines at least an average value for the switching power by processing the successive values ​​34a, 34b, 34c, and 34d. At least one average value for the switching power is transmitted from the determining device 36 as input value 38 to the input device 16.The input device 16 transmits the input value 38 as input data 20b to the neural network 12.

[0052] From the input data 20a, 20b, the neural network 12 determines a clutch temperature KT of the vehicle clutch. The determined clutch temperature KT is transmitted by the neural network 12 to an output device 40. The output device 40 transmits the determined clutch temperature KT to a deactivation device 42. Depending on the determined clutch temperature KT, the deactivation device 42 generates a deactivation signal 44, by means of which the neural network 12 can be deactivated. In the exemplary embodiment of the Figure 3 The deactivation signal 44 for the neural network 12 is generated when the specific coupling temperature KT is below a defined threshold. Reference sign

[0053] 10 Control unit 12 Neural network 14 Storage medium 16 Input device 18a, 18b, 18c Values ​​of operating parameters 20a, 20b Input data 22 Detection device 24 Switching signal 26 Detection signal 28 Activation device 30 Activation signal 32a, 32b Detection devices 34a, 34b, temporally successive values ​​for one of the vehicle couplings 34c, 34d supplied power 36 Determination device 38 Input value 40 Output device 42 Deactivation device 44 Deactivation signal KT Coupling temperature BS1 First determination step BS2 Second determination step BS3 Third determination step BS4 Fourth determination step BS5 Fifth determination step BS6 Sixth determination step TS1 First training step TS2 Second training step TS3 Third Training step

Claims

1. Method for determining a clutch temperature of a vehicle clutch by way of a neural network (12), wherein the method comprises the following steps: - detecting (BS1) a shift process (24) of the vehicle clutch; - activating (BS2) the neural network (12) for determining the clutch temperature, depending on the detection of a shift process (24); - inputting (BS3) at least one value (18a, 18b, 18c) of at least one operating parameter of the vehicle clutch into the neural network (12) as input data (20a); - determining (BS4) a clutch temperature (KT) by means of the neural network (12), based on the input data (20a) and a relationship between the at least one operating parameter and the clutch temperature (KT), as learned by the neural network (12); - outputting (BS5) the determined clutch temperature (KT) by means of the neural network (12); and - deactivating (BS6) the neural network (12) for determining the clutch temperature, depending on the determined clutch temperature (KT).

2. Method according to Claim 1, wherein the neural network (12) is deactivated when the determined clutch temperature (KT) is below a defined threshold value.

3. Method according to Claim 1 or 2, wherein the clutch temperature is determined by the neural network (12) within a predefined time interval.

4. Method according to Claim 3, wherein the time interval is predefined depending on the determined clutch temperature.

5. Method according to one of Claims 1 to 4, wherein the method further comprises the following steps: - determining at least one input value (38) representative of a power supplied to the vehicle clutch, wherein the at least one input value (38) is determined based on processing of temporally successive values (32a, 32b, 32c, 32d) for the power supplied to the vehicle clutch; and - inputting the at least one input value (38) into the neural network (12) as input data (20b).

6. Method according to Claim 5, wherein the at least one input value (38) is determined in predefined time intervals.

7. Method for training a neural network (12) which is designed to determine a clutch temperature (KT) of a vehicle clutch, wherein the method comprises the following steps: - providing (TS1) at least one value (18a, 18b, 18c) of an operating parameter of the vehicle clutch as input data (20a); - providing (TS2) values for the clutch temperature as output data; and - training (TS3) the neural network (12) with the input data (20a) and the output data in order to learn a relationship between the input data and the clutch temperature.

8. Method according to Claim 7, wherein the neural network (12) is further trained by means of at least one determined input value (38) representative of a power supplied to the vehicle clutch, wherein the at least one input value (38) is determined based on processing of temporally successive values (32a, 32b, 32c, 32d) for the power supplied to the vehicle clutch.

9. Method according to one of Claims 1 to 6, wherein the neural network (12) was trained in accordance with the method for training a neural network according to either of Claims 7 and 8.

10. Method according to one of the preceding claims, wherein 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, said drive axle being operatively mechanically connected to 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 clutch element of the vehicle clutch; an amperage of an electric current flowing through a clutch element of the vehicle clutch; and a sump temperature of a vehicle transmission at the start of a shift process of the vehicle clutch.

11. Control device (10) for determining a clutch temperature of a vehicle clutch in accordance with the method of one of the preceding claims, the control device comprising: - a computer-readable storage medium (14) on which a neural network (12) for determining the clutch temperature is stored; - a detection apparatus (22) for detecting a shift process (24) of the vehicle clutch; - an activation apparatus (28) for activating (30) the neural network (12), depending on the detection (24) of a shift process; - an input apparatus (16) for inputting input data (20a, 20b) into the neural network (12), wherein the input data (20a, 20b) comprise at least one value (18a, 18b, 18c) of at least one operating parameter of the vehicle clutch; - an output apparatus (40) for outputting the determined clutch temperature (KT) by means of the neural network (12); and - a deactivation apparatus (42) for deactivating (44) the neural network (12), depending on the determined clutch temperature (KT).

12. Control device (10) according to Claim 11, wherein the clutch temperature (KT) is determined by the neural network (12) in accordance with the method according to one of Claims 1 to 6; and wherein the neural network (12) was trained in accordance with the method for training a neural network according to either of Claims 7 and 8.