Determining a clutch temperature of a vehicle clutch by means of

Abstract

The invention relates to a method for determining a clutch temperature (KT1, KT2) of a vehicle clutch (K1, K2) by means of a neural network (12), said method comprising the following steps: inputting (BS1) 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), by means of the neural network (12), the temperature (T1) on the basis of the input data (20a) and the relationship between the input data (20a) and the temperature (T1) learned by the neural network (12); applying (BS3) the ascertained scale factor (SF1, SF2) to the temperature (T1) in order to determine a clutch temperature (KT1, KT2) of the vehicle clutch (K1, K2). A control device (10) for determining clutch temperatures (KT1, KT2) of a plurality of vehicle clutches (K1, K2) using a neural network (12) is also disclosed.

Description

Technical Field

[0001] The invention relates to a method for determining a clutch temperature of a vehicle clutch by means of a neural network and to determining a proportionality factor for the clutch temperature. The invention also relates to a corresponding control device for determining the clutch temperature of a vehicle clutch by means of a neural network and for applying the determined proportionality factor to the clutch temperature. Background Art

[0002] The temperature of the vehicle clutch can be calculated using conventional rule-based mathematical models. Machine learning, such as neural networks, can also be used for this purpose. The calculation can be performed in the transmission controller. The computing power available on the transmission controller may be limited. Further neural networks can be used to determine further clutch temperatures of further vehicle clutches. Summary of the invention

[0003] In a first aspect, the present invention relates to a method for determining a clutch temperature of a vehicle clutch by means of a neural network.

[0004] A vehicle clutch can be installed in an engine-driven vehicle, such as a motor vehicle, a motorcycle or a two-wheeled vehicle driven at least partially electrically. The vehicle clutch can be used to transmit the driving force applied by the vehicle engine to the 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 driven torque of the engine and the driving torque of the drive axle.

[0005] The clutch temperature may be understood as the temperature of at least one clutch element, such as the temperature of a clutch plate. Alternatively, the clutch temperature may also be understood as the temperature of the entire vehicle clutch, which temperature may be determined, for example, based on an average value of the individual temperatures of the clutch elements. The temperature of the vehicle clutch may change due to the operation of the vehicle. For example, during a switching process or gear change, the temperature of the vehicle clutch may increase. If the temperature of the vehicle clutch increases above a critical temperature value, this may result in damage to or failure of the vehicle clutch. Thus, the determination of the clutch temperature of the vehicle clutch contributes to improving the safety of the vehicle.

[0006] A neural network can be understood as a mathematical model that at least partially mimics the structure of neurons in the human brain. A neural network can be created using a computer. A neural network can have an input node, an output node, and a plurality of intermediate nodes arranged between the input node and the output node. The input node can be, for example, a data interface, through which input data can be input into the neural network. The output node can be, for example, a data interface, through which output data can be output from the neural network. The input node can be connected to the intermediate node and the intermediate nodes can be connected to each other. The intermediate node can be connected to the output node. The input data can be historical data detected at a specific point in time. Alternatively or additionally, the input data can be synthetic data generated by processing collected or measured data. Similarly, the output data can be historical data or synthetic data.

[0007] Information can be at least temporarily buffered at the intermediate node. It can be provided that at least one computing operation is performed at the intermediate node. Input data can be transmitted from the input node to the output node via the intermediate node. During the transmission, 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 or levels. The intermediate nodes can be connected to each other within a layer. Additionally, the intermediate nodes of a layer can be connected to the intermediate nodes of other layers. The individual connections of the input nodes, intermediate nodes and output nodes can be provided with mathematical weights. Depending on the purpose of the neural network, the individual weights of the connections may be different. During the training of the neural network, the weights may be changed. By adjusting the mathematical weights of the connections of the individual nodes during training, the neural network can learn the relationship between the input data and the output data. During the use of the neural network for the set purpose, the relationship learned by the neural network is applied to the input data input so as to generate output data according to the predetermined application purpose of the neural network.

[0008] For example, a multilayer perceptron (MLP) can be used as a neural network to determine the clutch temperature. The neural network has at least one layer of intermediate nodes and uses at least one nonlinear mathematical function to calculate the output data. Another exemplary neural network for determining the 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. In addition, for example, a convolutional neural network (CNN) can be used to determine the clutch temperature, wherein the intermediate nodes of different layers are at least partially connected to each other in the form of a mathematical convolution function.

[0009] The neural network may be trained using training data that has been collected for a further vehicle clutch that is different from the vehicle clutch. The training data may be historically collected data or synthetically generated data. The training data may be collected in conjunction with a mathematical simulation, for example simulating a heating process of the further vehicle clutch. Alternatively or additionally, the training data may be collected on a test bench when measuring the further vehicle clutch. Alternatively or additionally, the training data may be collected during operation of the further vehicle clutch, for example during driving of a vehicle in which the further vehicle clutch is installed. The vehicle clutch and the further vehicle clutch may have at least one common characteristic that may be scaled according to a proportionality factor between the vehicle clutch and the further vehicle clutch. The training data may include at least one value of at least one operating parameter of the further vehicle clutch as input data, and a value of a clutch temperature of the further vehicle clutch as output data. During the training process, the neural network may learn a relationship between the input data and the output data.

[0010] The method comprises 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. The at least one value of the at least one operating parameter of the vehicle clutch may represent the 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 may represent the clutch temperature of the vehicle clutch. The at least one value of the at least one operating parameter may 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 may be transmitted to at least one of the input nodes of the neural network by a control device of the vehicle by means of a data interface. The at least one value of the at least one operating parameter may be used as input data for determining the clutch temperature using the neural network. Alternatively or additionally, the at least one value of the at least one operating parameter may be used as input data for training the neural network.

[0011] The method further comprises the step of calculating the temperature by means of a neural network. The neural network calculates the temperature based on the input data and the relationship between the time variation curve of the input data and the temperature learned by the neural network. The input data can be processed by the neural network, for example at an intermediate node according to the learned relationship, in order to calculate the temperature. When learning the relationship, the neural network can change the mathematical weights of the connections of the various nodes in order to determine the temperature.

[0012] The method also includes a step of applying a learned proportional factor to the calculated temperature to determine the clutch temperature of the vehicle clutch. The proportional factor can be learned based on the measured characteristics of the vehicle clutch. Alternatively or additionally, the proportional factor can be learned based on the calculated characteristics of the vehicle clutch. The proportional factor can be a mathematical value added to the calculated temperature value or subtracted from the calculated temperature value. Alternatively or additionally, the proportional factor can be a mathematical factor, and the calculated temperature value is multiplied or divided by the mathematical factor. Alternatively or additionally, the proportional factor can be a mathematical function applied to the calculated temperature value. The mathematical function can be, for example, linear, nonlinear, multidimensional, proportional, increasing, decreasing, logarithmic and / or exponential. The calculated temperature value can be at least one parameter of the mathematical function. Alternatively, the calculated temperature value can be mathematically preprocessed. The preprocessed value of the calculated temperature can be at least one parameter of the mathematical function. The proportional factor can be composed of a combination of the above examples. The proportional factor can be composed of, for example, a mathematical function and a mathematical factor, both of which are applied to the calculated temperature value. The scaling factor may, for example, consist of two or more interrelated mathematical functions.

[0013] The determined clutch temperature can be used by other components of the vehicle control. For example, the determined clutch temperature can be used to generate a control value for a control unit of the vehicle (for example, a transmission control unit of 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.

[0014] The proposed method makes it possible to determine the clutch temperature with the aid of a neural network. This makes it possible to dispense with the use of conventional mathematical models, which are usually very complex and therefore time-consuming to calculate. Thus, by using a neural network, the calculation time required for determining the clutch temperature can be reduced on the one hand. In addition, the clutch temperature is determined with the aid of a proportionality factor. Thus, when one or more operating parameters of the vehicle clutch change, it is possible to dispense with the training of a further neural network for determining the clutch temperature of the vehicle clutch. Furthermore, it is not necessary to re-ascertain the proportionality factor for each temperature calculated by the neural network. The proportionality factor can be determined once for each clutch so 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 also saves computing power.

[0015] In order to determine the clutch temperature of another vehicle clutch, an already trained neural network can be used. For another vehicle clutch, only another proportional factor applied to the temperature calculated by the neural network needs to be determined in order to be able to determine the clutch temperature of another vehicle clutch. It is thus possible to dispense with the training and implementation of another neural network for determining another clutch temperature. As a result, the computing power required for determining the clutch temperature of multiple vehicle clutches can be kept small. In particular, it is thus possible to perform the determination of the clutch temperature of multiple vehicle clutches on the transmission controller without excessively demanding the computing power of the transmission controller. Thus, despite the determination of multiple clutch temperatures, additional calculations can still be performed on the transmission controller. Finally, due to the low computing effort, the determination of the clutch temperature can be performed in real time with the help of the proportional factor and the determined clutch temperature can be transmitted in real time to other components of the vehicle control unit. This improves the safety of the vehicle.

[0016] According to one embodiment, the proportionality factor is determined based on the relationship between a measured clutch temperature of the vehicle clutch and a temperature calculated by the neural network. The measured temperature of the vehicle clutch can be measured during and / or after a test performed on the vehicle clutch, for example during its test phase. Alternatively or additionally, the measured temperature can be measured during and / or after operation of the vehicle clutch. The calculated temperature may deviate from the measured temperature. This deviation can be compensated for with the help of the proportionality factor. Alternatively, the calculated temperature can be compared with 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 proportionality factor on the determined clutch temperature. Thus, the determination of the clutch temperature can be matched to the temperature characteristics of the vehicle clutch.

[0017] According to one embodiment, the proportionality factor is determined based on at least one calculated parameter of the vehicle clutch. The calculated parameter can be calculated in conjunction with a mathematical model, such as 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 represent a physical property of the vehicle clutch, such as the thermal conductivity or the mass of the vehicle clutch. Thus, the determination of the clutch temperature can be adapted to different applications of the vehicle clutch.

[0018] According to another embodiment, the proportionality factor is also known in dependence on the determined clutch temperature. For example, the determined clutch temperature can be compared with a threshold value of the temperature of the vehicle clutch. The closer the determined clutch temperature is to the threshold value, the greater the influence of the proportionality factor on the determined clutch temperature. For example, the proportionality factor may be larger, the closer the determined clutch temperature is to the threshold value. Thus, the proportionality factor can be matched to changes in the clutch temperature.

[0019] According to one embodiment, the proportionality factor is determined as a function of at least one structural property of the vehicle clutch. The structural property may represent, for example, a geometrical dimension or a material composition of the vehicle clutch. The structural property may represent 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 may be determined more accurately.

[0020] According to another embodiment, the clutch temperature is calculated by another neural network designed for this purpose. A proportionality factor is determined based on the calculated temperature and the calculated clutch temperature. The other neural network can be trained using the above-mentioned parameters for determining the proportionality factor as input data and the value of the clutch temperature as output data. Alternatively or additionally, the other neural network can be trained using at least one value of an operating parameter of the vehicle clutch as input data and the value of the clutch temperature as output data. The other neural network can learn the relationship between the input data and the output data. The other neural network can be implemented on a transmission controller (the neural network for calculating the temperature is also implemented on the transmission controller). Alternatively, the other neural network can be implemented on a control device designed separately from the transmission controller. The clutch temperature calculated by the other neural network can be transmitted to the transmission controller. The proportionality factor can be determined on the transmission controller. The above-mentioned parameters can also be used to determine the proportionality factor. The proportionality factor calculated by the two neural networks can be used to determine the other clutch temperature, for example.

[0021] According to another embodiment, the method is used to determine the clutch temperature of a further vehicle clutch. A first temperature is determined as the clutch temperature of the further vehicle clutch. The clutch temperature of the vehicle clutch and the further clutch temperature of the further vehicle clutch can be proportionally scaled, for example, according to a proportionality factor. Thus, the clutch temperatures of both vehicle clutches can be determined with the aid of a neural network. As a result, the computational effort for determining both clutch temperatures can be reduced.

[0022] According to another embodiment, the method is used to determine the clutch temperature of a further vehicle clutch and further comprises the following steps: determining a further proportionality factor for the further vehicle clutch; and applying the determined further proportionality 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 proportionality factor can be determined according to the above-described embodiments of the method. Alternatively or in addition, the further proportionality factor can depend on the determined proportionality factor. Thus, in order to determine the clutch temperature of the further vehicle clutch, only the further proportionality factor needs to be determined. For example, it is not necessary to calculate the further clutch temperature by means of a neural network. Thus, the computational effort for determining the further clutch temperature can be kept low.

[0023] In one embodiment, the further vehicle clutch has a further structural characteristic that is scaled proportionally to at least one structural characteristic of the vehicle clutch according to the proportionality factor or the further proportionality factor. The structural characteristic may be, for example, the mass of the vehicle clutch. The further structural characteristic may be, for example, the mass of the further vehicle clutch, which is twice the mass of the vehicle clutch. Thus, the mass of the respective vehicle clutch is scaled proportionally by a proportionality factor equal to two. Alternatively, the structural characteristic may be, for example, the number of friction plates of the vehicle clutch. The further structural characteristic may be, for example, the number of friction plates of the further vehicle clutch, which is, for example, three times the number of friction plates of the vehicle clutch. Thus, the number of friction plates of the respective vehicle clutch is scaled proportionally by a further proportionality factor equal to three. Thus, the different temperatures of the respective vehicle clutches can be determined in a simple manner according to the respective proportionality factors.

[0024] According to another embodiment, at least one structural characteristic or at least one further structural characteristic of the vehicle clutch is selected from at least one of the following: the material of the vehicle clutch; the material composition of the vehicle clutch; the thermal conductivity of the vehicle clutch; the type of vehicle clutch; and the application of the vehicle clutch. The type of vehicle clutch can be understood, for example, as a vehicle clutch that works based on mechanical pressure or according to the eddy current braking principle. The application of the vehicle clutch can be understood, for example, as the application of the vehicle clutch in a passenger car or a truck. The mentioned structural characteristics can represent the flow of a heating or cooling process of the respective vehicle clutch.

[0025] According to another specific embodiment, the proportionality factor or the further proportionality factor is determined by a further neural network designed for this purpose. The further neural network can be trained with the above-mentioned parameters for determining the proportionality factor. The further neural network can be implemented on the transmission control unit. Alternatively, the neural network can be implemented on a control unit separate from the transmission control unit. The proportionality factor or the further proportionality factor can be transmitted to the transmission control unit. The proportionality factor or the further proportionality factor can be determined more quickly with the aid of the further neural network.

[0026] According to another embodiment, the method further comprises the step of determining at least one input value, the at least one input value representing the power supplied to the vehicle clutch. The at least one input value is determined based on processing temporally consecutive values ​​of the power supplied to the clutch. According to this embodiment, the method further comprises the step of inputting the at least one input value as input data into the neural network.

[0027] The power supplied to the vehicle clutch can be understood as physical power, that is, energy supplied to the vehicle clutch within a predetermined time period. The power supplied to the vehicle clutch can be, for example, the switching power supplied to the vehicle clutch during a switching process or gear change. The power supplied to the vehicle clutch can represent a change in the clutch temperature of the vehicle clutch.

[0028] 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 by a control device of the vehicle by means of 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 determining the clutch temperature using the neural network. Alternatively or additionally, the at least one input value can be used as input data for training the neural network.

[0029] In this embodiment, the determination of the clutch temperature is also based on the time profile of the input data. The neural network can thus also take into account the time profile of the input data. For example, the cooling or heating phase of the vehicle clutch can be detected and taken into account when calculating the vehicle clutch temperature. In addition, for example, exceeding of limit values ​​of the clutch temperature or deviations from the normal behavior of the clutch temperature during the heating or cooling phase can be taken into account. The clutch temperature can thus also be determined more accurately. In addition, the time profile of the input data is not determined by the neural network itself, but is only transmitted to the neural network in the form of processed input values. This reduces the computational effort required for calculating the temperature. As a result, the structure of the neural network can be designed to be less complex. As a result, the storage space required for the neural network can also be reduced.

[0030] According to another embodiment, at least one operating parameter of the vehicle clutch is selected from at least one of the following: the torque of the drive shaft of the vehicle engine that is in mechanical connection with the vehicle clutch; the speed difference between two rotating clutch elements of the vehicle clutch; the speed of the rotating clutch element of the vehicle clutch; the mechanical pressure acting on the clutch element of the vehicle clutch; the current intensity of the current flowing through the clutch element of the vehicle clutch; the oil sump temperature of the vehicle transmission at the beginning of the switching process of the vehicle clutch. The clutch elements of the vehicle clutch can be, for example, clutch plates of the vehicle clutch, which can be connected to transmit force from the engine to the drive axle. The above parameters can represent the power supplied to the vehicle clutch. Alternatively or additionally, the above parameters can represent the clutch temperature of the vehicle clutch. Thus, by applying at least one of the parameters, it is easy to determine the clutch temperature.

[0031] In a second aspect, the present invention relates to a control device for determining the clutch temperature of a plurality of vehicle clutches. The control device comprises a computer-readable storage medium on which a neural network is stored, the neural network being designed to determine at least one temperature of at least one vehicle clutch among a plurality of vehicle clutches. The control device further comprises input means for inputting input data into the neural network. The input data comprises at least one value of at least one operating parameter of the vehicle clutch. Furthermore, the control device further comprises output means for outputting the temperature calculated by the neural network. Furthermore, the control device further comprises an application means for applying the learned proportionality factor to the output temperature in order to determine the clutch temperature of at least one vehicle clutch among a plurality of vehicle clutches.

[0032] According to one specific embodiment, the control device further comprises a determination device for determining a proportionality factor for at least one temperature as a function of at least one structural property of at least one vehicle clutch from among the plurality of vehicle clutches.

[0033] The mentioned device of the control device according to the second aspect can be designed to receive, process and forward electrical signals. The mentioned device of the control device according to the second aspect can be designed to perform the method according to the first aspect. Similarly, the method according to the first aspect can be performed by the control device according to the second aspect. Therefore, the implementation, technical effects and advantages described for the first aspect are also similarly applicable to the control device according to the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A flow chart is shown which includes the steps of a method for determining a clutch temperature of a vehicle clutch by means of a neural network and a proportional factor for the clutch temperature according to one specific embodiment of the present invention.

[0035] Figure 2 A control device for determining a clutch temperature of a vehicle clutch using a neural network and a proportional factor according to a further specific embodiment of the present invention is schematically shown.

[0036] Figure 3a to Figure 3c Various possibilities for determining the clutch temperature of a further vehicle clutch by means of a proportionality factor according to a further specific embodiment of the present invention are shown. DETAILED DESCRIPTION

[0037] Figure 1 A flow chart showing the steps of a method for determining a clutch temperature of a vehicle clutch by means of a neural network according to one specific embodiment of the present invention.

[0038] In a first determination step BS1, at least one value of at least one operating parameter of the vehicle clutch is input as input data to the neural network. In this case, at least one value of at least one operating parameter is transmitted to at least one input node of the neural network.

[0039] In the second determination step BS2, the temperature is calculated by the neural network. The temperature is calculated based on the input data and the relationship between the input data and the temperature learned by the neural network.

[0040] In order to calculate the temperature, the input data transmitted to the input nodes of the neural network are transmitted to the intermediate nodes of the neural network via the connections mathematically weighted by the neural network. At the intermediate nodes, the transmitted input data are processed and transmitted to the output nodes of the neural network via the connections mathematically weighted by the neural network. The mathematical weights of the respective connections have been adapted by the neural network during the training process of the neural network before the determination of the method in terms of time based on a training data set. At the end of the execution of the method, the value of the temperature is present at at least one output node of the neural network.

[0041] In a third determination step BS3 , the learned proportionality factor is applied to the temperature calculated by the neural network in order to determine the clutch temperature of the vehicle clutch.

[0042] exist Figure 1 In an embodiment of the invention, the proportionality factor is determined based on the deviation of a measured clutch temperature of the vehicle clutch from the temperature calculated by the neural network. Furthermore, the proportionality factor is determined based on a measured thermal conductivity of the vehicle clutch. To determine the proportionality factor, the determined clutch temperature is also compared with a limit value of a maximum permissible clutch temperature. The closer the determined clutch temperature is to the limit value, the greater the proportionality factor is selected. Furthermore, the proportionality factor is determined as a function of the steel quality of the friction lining of the vehicle clutch. Other parameters for determining the proportionality factor are not excluded.

[0043] The clutch temperature of a vehicle clutch can be determined in a simple manner by means of the proportionality factor. Furthermore, the clutch temperature of a further vehicle clutch can also be determined based on the temperature calculated by the neural network by applying the proportionality factor. Thus, it is not necessary to train a further neural network for each vehicle clutch, but it is sufficient to apply the respective proportionality factor to the calculated temperature of the vehicle clutch. This can save computing power, for example, on a transmission control unit. Furthermore, the clutch temperature can be determined in real time.

[0044] Figure 2 A control device 10 for determining a clutch temperature of a vehicle clutch (not shown) is schematically shown, which has a neural network 12 according to another specific embodiment of the invention. The control device 10 can be part of the vehicle clutch or designed separately from the vehicle clutch.

[0045] The control device 10 comprises 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 to the neural network 12 as input data 20a.

[0046] The control device 10 further comprises detection devices 22a, 22b, which detect temporally successive values ​​24a, 24b or 24c, 24d of the power supplied to the vehicle clutch. The detection devices 22a, 22b are low-pass filters, and the values ​​24a, 24b, 24c, 24d of the power supplied to the vehicle clutch are the switching power supplied to the vehicle clutch during the switching process or gear change. The detected values ​​24a, 24b, 24c and 24d of the switching power are transmitted from the detection devices 22a, 22b to the determination device 26. The determination device 26 determines at least one average value of the switching power by processing the temporally successive values ​​24a, 24b, 24c, 24d. The at least one average value of the switching power is transmitted by the determination device 26 as an input value 28 to the input device 16. The input device 16 transmits the input value 28 as input data 20b to the neural network 12.

[0047] The neural network 12 calculates the temperature T1 of the vehicle clutch from the input data 20a, 20b. The calculated temperature T1 is output by the output device 30 to the application device 32. The application device 32 applies the learned proportional factor SF1 to the calculated temperature T1. The proportional factor SF1 is learned by the learning device 34 based on a plurality of parameters 36a, 36b of the vehicle clutch. By applying the proportional 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 learning device 34 can be designed separately from the control device 10.

[0048] Based on the temperature T1 calculated by the neural network 12, the clutch temperature of another vehicle clutch can be determined, such as Figures 3a to 3c shown.

[0049] Figures 3a to 3c Different possibilities are shown for determining the clutch temperature of a further vehicle clutch based on the temperature T1 calculated by the neural network 12 .

[0050] Figure 3a Schematically showing the Figure 2 The neural network 12 in the embodiment of determines the clutch temperature of the vehicle clutch K2. Figure 2In the embodiment of the present invention, the neural network 12 calculates the first temperature T1. Figure 3a In the embodiment of FIG. 1 , the calculated temperature T1 is determined as the clutch temperature KT2 of the clutch K2. In other words, in Figure 3a In an implementation manner, it is known that the value of the scale factor is one.

[0051] Figure 3b Schematically showing the Figure 2 The neural network 12 in the embodiment of FIG. 1 determines the clutch temperature of the first vehicle clutch K1 and the second vehicle clutch K2. Figure 2 In the embodiment of the present invention, the neural network 12 calculates the first temperature T1. Figure 3b In the implementation mode, by Figure 2 The application device 32 shown applies a first proportionality factor SF1 to the calculated temperature T1 in order to determine the clutch temperature KT1 of the first vehicle clutch K1. Figure 3b In the implementation mode, by Figure 2 The application device 32 shown applies a second proportionality 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 need to be calculated in a complex manner but can be determined by simply applying the second proportionality factor SF2 to the temperature T1.

[0052] Figure 3c Schematically showing the Figure 2 The neural network 12 in the embodiment of FIG. 1 determines the clutch temperature of the first vehicle clutch K1 and the second vehicle clutch K2. Figure 2 In the embodiment of the present invention, the neural network 12 calculates the first temperature T1. Figure 3c In the implementation mode, by Figure 2 The illustrated application device 32 applies a first proportionality factor SF1 to the calculated temperature T1 in order to determine the clutch temperature KT1 of the first vehicle clutch K1. Figure 2 The application device 32 shown applies the second proportionality factor SF2 to the determined clutch temperature KT1 in order to determine the clutch temperature KT2 of the second vehicle clutch K2. The clutch temperature KT2 thus does not need to be calculated in a complex manner but can be determined by simply applying the second proportionality factor SF2 to the clutch temperature KT1.

[0053] Reference numerals

[0054] 10 Control Equipment

[0055] 12 Neural Networks

[0056] 14 Storage Media

[0057] 16 Input Devices

[0058] 18a, 18b, 18c Values ​​of operating parameters

[0059] 22a, 22b Detection device

[0060] 24a, 24b, 24c, 24d Time-sequential values ​​of the power supplied to the vehicle clutch

[0061] 26 Determine the device

[0062] 28 Input value

[0063] 30 Output device

[0064] 32 Application Devices

[0065] 34 Acquisition Device

[0066] 36a, 36b Vehicle clutch parameters

[0067] SF1 First scale factor

[0068] SF2 Second scale factor

[0069] T1 Calculated temperature

[0070] KT1 First clutch temperature

[0071] KT2 Second clutch temperature

[0072] K1 First vehicle clutch

[0073] K2 Second vehicle clutch

[0074] BS1 First Determination Step

[0075] BS2 Second determination step

[0076] BS3 Third Determination Step

Claims

1. A method for determining a clutch temperature (KT1, KT2) of a vehicle clutch (K1, K2) by means of a neural network (12), wherein: The method comprises the following steps: - inputting (BS1) 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 means of the neural network (12) based on the input data (20a) and the relationship between the input data (20a) and the temperature (T1) learned by the neural network (12); and - applying (BS3) the known proportionality factor (SF1, SF2) to the temperature (T1) in order to determine a clutch temperature (KT1, KT2) of the vehicle clutch (K1, K2).

2. The method according to claim 1, wherein: The proportionality factor (SF1, SF2) is determined based on a relationship between a measured clutch temperature of the vehicle clutch (K1, K2) and a temperature (T1) calculated by the neural network (12).

3. The method according to claim 1 or 2, wherein: The proportionality factor (SF1, SF2) is determined based on at least one calculated parameter of the vehicle clutch (K1, K2).

4. A method according to any one of the preceding claims, wherein: The proportionality factors (SF1, SF2) are also determined as a function of the determined clutch temperatures (KT1, KT2).

5. A method according to any one of the preceding claims, wherein: The proportionality factor (SF1, SF2) is determined as a function of at least one structural property of the vehicle clutch (K1, K2).

6. A method according to any one of the preceding claims, wherein: The clutch temperatures (KT1, KT2) are calculated by a further neural network designed for this purpose, wherein the proportionality factors (SF1, SF2) are determined based on the calculated temperature (T1) and the calculated clutch temperatures (KT1, KT2).

7. A method according to any one of the preceding claims, wherein: The method is used to determine a clutch temperature (KT2) of a further vehicle clutch (K2), wherein a first temperature (T1) is determined as the clutch temperature (KT2) of the further vehicle clutch (K2).

8. The method according to any one of claims 1 to 6, wherein: The method is applied to determine a clutch temperature (KT2) of a further vehicle clutch (K2), the method further comprising the following steps: - determining a further proportionality factor (SF2) for the further vehicle clutch (K2); and - applying the determined further proportionality 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).

9. The method according to any one of claims 5 to 8, wherein: The further vehicle clutch (K2) has further structural properties which are scaled proportionally to at least one structural property of the vehicle clutch (K1) according to the proportionality factor (SF1) or the further proportionality factor (SF2).

10. The method according to any one of claims 5 to 9, wherein: At least one structural property or at least one further structural property of the vehicle clutch (K1, K2) is selected from at least one of the following: the material of the vehicle clutch (K1, K2); the material composition of the vehicle clutch (K1, K2); the thermal conductivity of the vehicle clutch (K1, K2); the type of the vehicle clutch (K1, K2); Application of the vehicle clutch (K1, K2).

11. A method according to any one of the preceding claims, wherein: The scaling factor (SF1) or the further scaling factor (SF2) is determined by a further neural network designed for this purpose.

12. 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) representing the power supplied to the vehicle clutch (K1, K2), wherein the at least one input value (28) is determined based on processing temporally consecutive values ​​(24a, 24b, 24c, 24d) of the power supplied to the vehicle clutch (K1, K2); and - inputting the at least one input value (28) as input data (20b) into the neural network (12).

13. A method according to any one of the preceding claims, wherein: At least one operating parameter of the vehicle clutch (K1, K2) is selected from at least one of the following: a torque of a drive shaft of a vehicle engine 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 rotational speed of a rotating clutch element of the vehicle clutch (K1, K2); a mechanical pressure acting on a clutch element of the vehicle clutch (K1, K2); a current intensity of a current flowing through a clutch element of the vehicle clutch (K1, K2); The oil sump temperature of the vehicle transmission at the start of a shifting process of the vehicle clutch (K1, K2).

14. A control device (10) for determining a clutch temperature (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, the neural network being designed to calculate at least one temperature (T1) of at least one vehicle clutch (K1) of a 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) comprises at least one value (18a, 18b, 18c) of at least one operating parameter of a vehicle clutch (K1, K2); - an output device (30) for outputting the temperature (T1) calculated by the neural network (12); and - an application device (32) for applying the determined proportionality factor (SF1, SF2) to the output temperature (T1) in order to determine a clutch temperature (KT1, KT2) of at least one vehicle clutch (K1, K2) of a plurality of vehicle clutches.

15. The control device (10) according to claim 14, further comprising: - a determination device (34) for determining a proportionality factor (SF1, SF2) for the at least one temperature (T1) as a function of at least one structural characteristic (36a, 36b) of at least one vehicle clutch (K1, K2) of a plurality of vehicle clutches (K1, K2).

Images