System for operating a hybrid or electric vehicle

Abstract

The present disclosure relates to a system (100) for operating a hybrid or electric vehicle (1), comprising: - a temperature-control module (HO) which is designed to thermally condition a drive energy store (10) of the hybrid or electric vehicle (1); - a prediction module (120) which is designed to predict a temperature of the drive energy store (10) for upcoming route segments of a route having a plurality of route segments using at least one long short-term memory, LSTM, network; and - a control module (130) which is designed to control the temperature-control module (110) in such a way that the drive energy store (10) is thermally conditioned on the basis of the predicted temperature of the drive energy store (10).

Description

[0001] System for operating a hybrid or electric vehicle

[0002] The present disclosure relates to a system for operating a hybrid or electric vehicle, a vehicle with such a system, a method for operating a hybrid or electric vehicle, and a storage medium for executing the method. The present disclosure relates in particular to a prediction of the temperature of a drive energy storage device using artificial intelligence with active target guidance.

[0003] State of the art

[0004] In light of the growing demands on mobility technology, particularly regarding the efficiency of energy storage systems in hybrid and electric vehicles, the development of high-performance thermal management has become a top priority. As part of thermal management, a process called preconditioning of the drive energy storage system can be implemented. Preconditioning involves preheating or precooling the drive energy storage system before the vehicle is started or charged. This measure ensures that the drive energy storage system operates at optimal temperatures, thus improving both its performance and lifespan.

[0005] Disclosure of the invention

[0006] It is an object of the present disclosure to specify a system for operating a hybrid or electric vehicle, a vehicle with such a system, a method for operating a hybrid or electric vehicle, and a storage medium for carrying out the method, which enable improved prediction of the temperature of a drive energy storage device. In particular, it is an object of the present disclosure to enable improved thermal conditioning of the drive energy storage device.

[0007] 24-0473 ABZ EXA 26.08.2024 This problem is solved by the subject matter of the independent claims. Advantageous embodiments are specified in the dependent claims.

[0008] According to an independent aspect of the present disclosure, a system for operating a hybrid or electric vehicle is specified. The system comprises a temperature control module configured to thermally condition a drive energy storage device of the hybrid or electric vehicle; a prediction module configured to predict the temperature of the drive energy storage device for upcoming route segments of a route with a plurality of route segments using at least one Long Short-Term Memory (LSTM) network; and a control module configured to control the temperature control module such that the thermal conditioning of the drive energy storage device is carried out based on the predicted temperature of the drive energy storage device.

[0009] According to the invention, a Long Short-Term Memory (LSTM) network is used to predict the temperature of a drive energy storage system. Specifically, information from already traversed track segments can be combined with information from upcoming or yet-to-be-traversed track segments and fed into the LSTM network to predict the drive energy storage system's temperature based on this information. The LSTM network allows the information to be stored and used over extended periods, thus improving the accuracy of the drive energy storage system's temperature prediction. As a result, improved thermal management of the drive energy storage system is possible.

[0010] For example, unnecessary cooling or heating processes of the drive energy storage system can be avoided, thereby minimizing energy losses. For instance, the drive energy storage system can be kept at a higher temperature before the end of a journey to reduce the need for subsequent heating. Furthermore, temperature preconditioning can be avoided for short journeys, as it offers no significant benefit in such cases. Finally, the precise estimation of

[0011] 24-0473 ABZ EXA 26.08.2024 upcoming temperature-load profiles play an important role in enabling early or timely temperature control of the drive energy storage system and thus increasing the efficiency of the overall system.

[0012] The prediction module and the control module may include software components / algorithms that are set up to run on at least one processor and thereby perform the functionalities of the respective module.

[0013] The prediction module and the control module can be implemented in a single software and / or hardware module. Alternatively, the prediction module and the control module can each be implemented in separate software and / or hardware modules.

[0014] Depending on the specific design, the hybrid or electric vehicle can be a pure electric vehicle (BEV) or a plug-in hybrid vehicle (PHEV). The term "vehicle" includes cars, trucks, buses, motorhomes, motorcycles, etc., used for the transport of persons, goods, etc. In particular, the term includes motor vehicles for passenger transport.

[0015] The drive energy storage system in a hybrid or electric vehicle is an energy storage system that stores electrical energy in the form of high-voltage direct current. This stored energy is used to power at least one of the vehicle's electric motors. Typically, these drive energy storage systems are composed of lithium-ion cells or modules configured in a battery pack. The drive energy storage system can also be referred to as a high-voltage storage system or battery.

[0016] The drive energy storage system can be connected to a charging station and charged via the charging device of the hybrid or electric vehicle. Various charging technologies can be used to charge the electric drive energy storage system of such hybrid or electric vehicles. During AC charging, the device is located...

[0017] 24-0473 ABZ EXA 26.08.2024, which converts the alternating current into direct current for charging the electric drive energy storage system in the vehicle. With DC charging, however, the conversion of the alternating current takes place directly in the charging station.

[0018] Preferably, the system includes a navigation module that is set up to determine the route.

[0019] Preferably, the navigation module is configured to perform active route guidance along the route. In other embodiments, a route can be determined from the circumstances without active route guidance. For example, historical data can be used to recognize that the driver is taking a specific route to a specific destination (e.g., a trip from home to work).

[0020] Preferably, a multitude of route segments determined by the navigation module for active route guidance and the multitude of route segments used by the prediction module for predicting the temperature of the drive energy storage system are identical and / or of the same length.

[0021] Alternatively, the multitude of route segments determined by the navigation module for active route guidance and the multitude of route segments used by the prediction module for predicting the drive energy storage temperature can be different and / or of different lengths. For example, the route segments determined by the navigation module for active route guidance can be shorter than the route segments used by the prediction module for predicting the drive energy storage temperature. For instance, segmentation can be predefined by map data. Since these route segments can often be very short (a few meters), the prediction module can generate a new segmentation by aggregating map segments until a minimum length is reached. The minimum length can be, for example, 500 m or more, preferably 1000 m or more.

[0022] 24-0473 ABZ EXA 26.08.2024 The system of the present disclosure uses at least one Long Short-Term Memory (LSTM) network to predict the temperature of the drive energy storage device. An LSTM network is a type of neural network designed for processing and predicting sequences. LSTM networks belong to the family of recurrent neural networks (RNNs), which can store information in a sequence and efficiently use this information across different time steps.

[0023] In some embodiments, at least one LSTM network can be integrated into a deep learning architecture. Within the deep learning architecture, the LSTM network enables the storage and utilization of information over long sequences, thus allowing for improved prediction of the drive energy storage temperature through the deep learning architecture.

[0024] Preferably, the prediction module is configured to predict the temperature of the drive energy storage system based on vehicle- and / or route-related information from previously traversed route segments of the plurality of route segments. In particular, the vehicle- and / or route-related information from previously traversed route segments can serve as input for the at least one LSTM network.

[0025] Examples of vehicle-related information from previously traveled route segments include, but are not limited to: speed; and / or acceleration; and / or weight; and / or the temperature of the drive energy storage system; and / or energy consumption; and / or outside temperature; and / or the status of at least one vehicle function (e.g., rear window defroster); and / or

[0026] 24-0473 ABZ EXA 26.08.2024 a travel time.

[0027] Examples of route-related information from previously traveled route segments include, but are not limited to: a road gradient; and / or a speed limit; and / or a road type (e.g. motorway, country road, etc.).

[0028] Preferably, the prediction module is configured to predict the temperature of the drive energy storage system based on vehicle- and / or track-related information from the preceding track segments. In particular, the vehicle- and / or track-related information from the preceding track segments can serve as input for the at least one LSTM network.

[0029] In some embodiments, the information from already traversed route segments of the multitude of route segments can be stored in a database and used as information for upcoming route segments to predict the temperature of the drive energy storage system.

[0030] Examples of vehicle-related information for upcoming route segments include, but are not limited to: historical speed from past journeys; and / or historical acceleration from past journeys; and / or historical weight from past journeys; and / or historical temperature of the drive energy storage system from past journeys; and / or historical energy consumption from past journeys; and / or historical status of at least one vehicle function (e.g., rear window defroster) from past journeys; and / or historical travel time from past journeys.

[0031] 24-0473 ABZ EXA 26.08.2024 Exemplary route-related information for upcoming route segments includes, but is not limited to: a road gradient; and / or a speed limit; and / or a road type (e.g. motorway, country road, etc.); and / or an estimated travel time.

[0032] Preferably, the prediction module is configured to further perform the temperature of the drive energy storage system using at least one Recurrent Fully Connected Feedforward Network (RFFN), wherein the at least one RFFN processes an output of the at least one LSTM network to predict the temperature.

[0033] A Recurrent Fully Connected Feedforward Network (RFFN) is an architecture that combines elements of both recurrent neural networks (RNNs) and fully connected feedforward networks. The at least one LSTM network can be used to process a sequence of the aforementioned information about the individual track segments, and the outputs of the LSTM layers can then be fed into the at least one RFFN to perform non-sequential processing for predicting the temperature of the drive energy storage system.

[0034] Preferably, the prediction module is configured to correct the predicted temperature for an initial distance of the route. In particular, deviations can occur at the beginning of the route due to a lack of information about previously traveled route segments, which would accumulate over time. This initial correction prevents such discrepancies.

[0035] Preferably, the initial distance of the route is 20km or less, or 10km or less.

[0036] 24-0473 ABZ EXA 26.08.2024 Preferably, the prediction module is configured to correct the predicted temperature using exponential damping over the initial distance (e.g., 10 km) of the route. For example, a difference between the actual temperature and the predicted temperature at the beginning (kilometer 0) can be distributed over a certain number of subsequent predicted values ​​(e.g., 9 further values, i.e., up to kilometer 10) using exponential smoothing.

[0037] Preferably, the temperature control module is configured to thermally precondition the drive energy storage device before a charging process. The term "thermal preconditioning," as used in this disclosure, refers to adjusting the temperature of the drive energy storage device to a target temperature by heating or cooling. This corresponds to a temperature that is optimal for charging the drive energy storage device, for example, with regard to charging time, charging power, and / or the load on the drive energy storage device during the charging process.

[0038] Preferably, the charging process is a fast charging process. The term "fast charging process," as used in the present disclosure, refers to DC charging in which a fast charging station itself converts the alternating current into direct current and transmits the direct current to the drive energy storage system of the hybrid or electric vehicle with minimal loss.

[0039] In some designs, the fast charging station can implement the so-called IU charging method. Here, charging initially takes place with a constant current until approximately 80% of the charging capacity is reached. Afterward, the fast charging station uses a constant voltage. This enables a short charging time and / or high charging power.

[0040] Preferably, the control module is configured to control the temperature control module in such a way that the drive energy storage system is activated at a specific time (e.g., an expected arrival time at a charging station or an expected departure time of the parked vehicle) and / or at a specific geoposition (e.g.,

[0041] 24-0473 ABZ EXA 26.08.2024 of a charging station) essentially has a target temperature. The thermal conditioning can be carried out, for example, in such a way that the temperature of the drive energy storage system has reached the target temperature upon arrival at the charging station, i.e., that optimal charging with regard to charging time, charging power and / or load on the drive energy storage system can be carried out upon arrival at the charging station.

[0042] Preferably, the temperature control module comprises at least one cooling device configured to cool the drive energy storage device for thermal conditioning, for example, to the target temperature. The at least one cooling device may include fans, liquid-based cooling, and / or a heat pump; however, the present disclosure is not limited to these.

[0043] Preferably, the temperature control module comprises at least one heating device configured to heat the drive energy storage device for thermal conditioning, for example, to the target temperature. The at least one heating device may include electric heating elements, a liquid-based heater, a heat pump, an internal resistance heater, and / or an induction heater; however, the present disclosure is not limited to these.

[0044] According to another independent aspect of the present disclosure, a hybrid or electric vehicle, in particular a motor vehicle, is specified. The hybrid or electric vehicle comprises the system for operating a hybrid or electric vehicle according to the embodiments of the present disclosure.

[0045] According to another independent aspect of the present disclosure, a computer-implemented method for operating a hybrid or electric vehicle is specified. The method comprises predicting, by a prediction module, the temperature of a drive energy storage device for upcoming route segments of a route with a plurality of route segments using at least one long short-term memory network; and controlling, by a control module, a temperature control module such that thermal conditioning of the

[0046] 24-0473 ABZ EXA 26.08.2024 Drive energy storage based on the predicted temperature of the drive energy storage.

[0047] The procedure for operating a hybrid or electric vehicle may implement aspects of the system for operating a hybrid or electric vehicle described in this document.

[0048] According to another independent aspect of the present disclosure, a software (SW) program is specified. The SW program can be configured to run on one or more processors and thereby execute the method described in this document for operating a hybrid or electric vehicle.

[0049] According to another independent aspect of the present disclosure, a storage medium is specified. The storage medium may include a software program configured to run on one or more processors and thereby execute the method described in this document for operating a hybrid or electric vehicle.

[0050] According to another independent aspect of the present disclosure, software with program code is specified. The software is designed to carry out the method for operating a hybrid or electric vehicle when the software runs on one or more software-controlled devices.

[0051] According to another independent aspect of the present disclosure, a system is specified. The system comprises one or more processors; and at least one memory connected to the one or more processors and containing instructions that can be executed by the one or more processors to carry out the method described in this document for operating a hybrid or electric vehicle.

[0052] 24-0473 ABZ EXA 26.08.2024 A processor or a processor module is a programmable arithmetic unit, i.e. a machine or an electronic circuit that controls other elements according to given instructions and thereby advances an algorithm (process).

[0053] Brief description of the drawings

[0054] Examples of the manifestation of the revelation are shown in the figures and are described in more detail below. They show:

[0055] Figure 1 schematically shows a hybrid or electric vehicle with a system according to embodiments of the present disclosure,

[0056] Figure 2 schematically shows a prediction of the temperature of a drive energy storage device according to embodiments of the present disclosure, and

[0057] Figure 3 shows a flowchart of a method for operating a hybrid or electric vehicle according to embodiments of the present disclosure.

[0058] Implementations of the revelation

[0059] Unless otherwise noted, the same reference symbols are used for identical and equivalent elements in the following.

[0060] Figure 1 schematically shows a hybrid or electric vehicle 1 with a system 100 according to embodiments of the present disclosure. The hybrid or electric vehicle 1 can, according to embodiments, be a battery electric vehicle (BEV) or a plug-in hybrid electric vehicle (PHEV).

[0061] The hybrid or electric vehicle 1 includes a drive energy storage device 10, which can be connected to a charging station and charged via a charging device of the hybrid or electric vehicle 1. To charge the drive energy storage device 10, for example,

[0062] 24-0473 ABZ EXA 26.08.2024 to optimally carry out the charging time, charging power and / or load of the drive energy storage unit 10, the drive energy storage unit 10 can be thermally preconditioned to a target temperature by heating or cooling before the charging process.

[0063] For example, the drive energy storage device 10 can be thermally preconditioned such that it has essentially a target temperature at a specific time (e.g., the expected arrival time at a charging station or the expected departure time of the parked vehicle) and / or at a specific geolocation (e.g., a charging station). The thermal conditioning can be carried out, for example, such that the temperature of the drive energy storage device 10 has reached the target temperature upon arrival at the charging station, meaning that optimal charging with regard to charging time, charging power, and / or load on the drive energy storage device 10 can be performed upon arrival at the charging station.

[0064] For thermal management of the drive energy storage system 10, its temperature can be predicted using a Long Short-Term Memory (LSTM) network. Such temperature prediction enables precise and reliable thermal conditioning, such as setting an optimal target temperature before charging. For example, unnecessary cooling or heating of the drive energy storage system can be avoided, thereby minimizing energy losses. For instance, the drive energy storage system can be kept at a higher temperature before the end of a journey to reduce the need for subsequent reheating. Furthermore, temperature preconditioning can be avoided for short journeys, as it offers no significant benefit in such cases.Finally, the precise estimation of the upcoming temperature-load profiles plays an important role in enabling early or timely temperature control of the drive energy storage system and thus increasing the efficiency of the overall system.

[0065] 24-0473 ABZ EXA 26.08.2024 The following explains in detail the system 100 for the thermal management of the drive energy storage unit 10.

[0066] The system 100 comprises a temperature control module 110, which is configured to thermally condition the drive energy storage 10 of the hybrid or electric vehicle 1; a prediction module 120, which is configured to predict a temperature of the drive energy storage 10 for upcoming route segments of a route with a plurality of route segments using at least one Long Short-Term Memory (LSTM) network; and a control module 130, which is configured to control the temperature control module 120 such that the thermal conditioning of the drive energy storage 10 is carried out based on the predicted temperature of the drive energy storage 10.

[0067] In some embodiments, the temperature control module 110 comprises at least one cooling device configured to cool the drive energy storage unit 10 for thermal conditioning, for example, to the target temperature. The at least one cooling device may include fans, liquid-based cooling, and / or a heat pump; however, the present disclosure is not limited to these.

[0068] Additionally or alternatively, the temperature control module 110 comprises at least one heating device configured to heat the drive energy storage device 10 for thermal conditioning, for example to the target temperature for charging the drive energy storage device 10. The at least one heating device may comprise electric heating elements, a liquid-based heater, a heat pump, an internal resistance heater and / or an induction heater; however, the present disclosure is not limited to these.

[0069] Figure 2 schematically shows a prediction of the temperature of a drive energy storage device according to embodiments of the present disclosure.

[0070] 24-0473 ABZ EXA 26.08.2024 The route comprises a multitude of track segments, including segments already traversed (area A in Figure 2) and upcoming track segments (area B in Figure 2). The vehicle's current position P can be assigned to the track segments already traversed, but the present disclosure is not limited to this.

[0071] In some embodiments, the route can be determined by a navigation module as part of active route guidance. The multitude of route segments determined by the navigation module for active route guidance and the multitude of route segments used by the prediction module for predicting the temperature of the drive energy storage system can be different and / or of different lengths. For example, the route segments determined by the navigation module for active route guidance can be shorter than the route segments used by the prediction module for predicting the temperature of the drive energy storage system. For instance, segmentation can be predefined by map data. Since these route segments can often be very short (a few meters), the prediction module can generate a new segmentation by merging map segments until a minimum length is reached.The minimum length can be, for example, 500m or more, preferably 1000m or more.

[0072] In some embodiments, information Data S2 and S3 from already traversed track segments, along with information S4 and S5 from upcoming or yet-to-be-traversed track segments, are fed into the LSTM network to predict the temperature of the drive energy storage system. The LSTM network allows this information to be stored and used over extended periods, thus improving the accuracy of the drive energy storage system temperature prediction.

[0073] Examples of vehicle-related information from previously traveled route segments include, but are not limited to, speed, acceleration, weight, temperature of the drive energy storage system, etc.

[0074] 24-0473 ABZ EXA 26.08.2024 Energy consumption, an outside temperature, a status of at least one vehicle function (e.g. rear window heating) and / or a driving time.

[0075] Examples of route-related information from previously traveled route segments include, but are not limited to, a road gradient, a speed limit and / or a road type (e.g. motorway, country road, etc.).

[0076] Examples of vehicle-related information for upcoming route segments include, but are not limited to, historical speed from past journeys, historical acceleration from past journeys, historical weight from past journeys, historical temperature of the drive energy storage from past journeys, historical energy consumption from past journeys, historical status of at least one vehicle function (e.g. rear window heating) from past journeys and / or historical driving time from past journeys.

[0077] Examples of route-related information for upcoming route segments include, but are not limited to, road gradient, speed limit, road type (e.g. motorway, country road, etc.) and / or estimated travel time.

[0078] In some embodiments, the information from already traversed route segments of the multitude of route segments can be stored in a database and used as information for upcoming route segments to predict the temperature of the drive energy storage system.

[0079] The temperature of the drive energy storage system can be further predicted using at least one Recurrent Fully Connected Feedforward Network (RFFN), wherein the at least one RFFN processes an output from the at least one LSTM network to predict the temperature. In particular, outputs from the at least one LSTM network relating to information S4, S5 from upcoming or yet-to-be-traversed track segments can be fed into the LSTM network to predict the

[0080] 24-0473 ABZ EXA 26.08.2024 To predict the temperature of the drive energy storage system. Figure 2 shows example outputs E4 and E5 for two upcoming or yet-to-be-traversed track segments.

[0081] In some embodiments, the prediction module can be configured to correct the predicted temperature for an initial route distance. In particular, deviations can occur at the beginning of the route due to a lack of information about previously traveled route segments, which would accumulate over time. This initial correction prevents such deviations. The initial route distance can be 20 km or less, or 10 km or less.

[0082] The predicted temperature can be corrected, for example, using exponential damping over the initial distance (e.g., 10 km) of the route. For instance, a difference between the actual temperature and the predicted temperature at the beginning (kilometer 0) can be distributed over a specific number of subsequent predicted values ​​(e.g., 9 further values, i.e., up to kilometer 10) using exponential smoothing.

[0083] Figure 3 schematically shows a flowchart of a method 300 for operating a hybrid or electric vehicle according to embodiments of the present disclosure. The method 300 can be implemented by appropriate software that can be executed by one or more processors (e.g., a CPU).

[0084] The method 300 comprises in block 310 a prediction, by a prediction module, of a temperature of a drive energy storage device for upcoming route segments of a route with a plurality of route segments using at least one Long Short-Term Memory network; and in block 320 a control, by a control module, of a temperature control module such that thermal conditioning of the drive energy storage device is carried out based on the predicted temperature of the drive energy storage device.

[0085] 24-0473 ABZ EXA 26.08.2024 According to the invention, a Long Short-Term Memory (LSTM) network is used to predict the temperature of a drive energy storage system. In particular, information from already traversed track segments can be combined with information from upcoming or yet-to-be-traversed track segments in order to predict the temperature of the drive energy storage system based on this information. The LSTM network makes it possible to store and use the information over longer periods, thus improving the accuracy of the prediction of the drive energy storage system's temperature. As a result, improved thermal management of the drive energy storage system is possible.

[0086] Although the invention has been further illustrated and explained in detail by means of preferred embodiments, the invention is not limited by the disclosed examples, and other variations can be derived from them by a person skilled in the art without departing from the scope of protection of the invention. It is therefore clear that a multitude of possible variations exist. It is also clear that the embodiments mentioned as examples are truly only examples and are not to be understood in any way as limiting, for example, the scope of protection, the possible applications, or the configuration of the invention.Rather, the preceding description and the description of the figures enable the person skilled in the art to implement the exemplary embodiments in concrete terms, whereby the person skilled in the art, with knowledge of the disclosed inventive concept, can make various changes, for example with regard to the function or the arrangement of individual elements mentioned in an exemplary embodiment, without leaving the scope of protection defined by the claims and their legal equivalents, such as further explanations in the description.

[0087] 24-0473 ABZ EXA 26.08.2024

Claims

Patent claims 1. System (100) for operating a hybrid or electric vehicle (1), comprising: a temperature control module (HO) configured to provide a to thermally condition the drive energy storage device (10) of the hybrid or electric vehicle (1); a prediction module (120) configured to predict the temperature of the drive energy storage device (10) for upcoming route segments of a route with a plurality of route segments using at least one Long Short-Term Memory (LSTM) network; and a control module (130) configured to control the temperature control module (110) such that the thermal conditioning of the drive energy storage device (10) is carried out based on the predicted temperature of the drive energy storage device (10).

2. System (100) according to claim 1, further comprising a navigation module configured to determine the route and to perform active route guidance along the route.

3. System (100) according to claim 1 or 2, wherein the prediction module (120) is configured to predict the temperature of the drive energy storage device (10) based on vehicle and / or route-related information from already traversed route segments of the plurality of route segments as well as vehicle and / or route-related information of the preceding route segments.

4. System (100) according to any one of claims 1 to 3, wherein the prediction module (120) is configured to further perform the temperature of the drive energy storage device (10) using at least one Recurrent Fully Connected Feedforward Network, RFFN, wherein the at least one RFFN processes an output of the at least one LSTM network to predict the temperature. 24-0473 ABZ EXA 26.08.2024 5. System (100) according to any one of claims 1 to 4, wherein the prediction module (120) is configured to perform a correction of the predicted temperature for an initial distance of the route, in particular wherein the initial distance of the route is 20km or less, or 10km or less.

6. System (100) according to claim 5, wherein the prediction module (120) is configured to perform the correction of the predicted temperature by means of exponential damping over the initial distance of the route.

7. System (100) according to any one of claims 1 to 6, wherein: the temperature control module (110) is configured to thermally precondition the drive energy storage device (10) before a charging process; and / or the control module (130) is configured to control the temperature control module (110) such that the drive energy storage device (10) has a substantially target temperature at a specific time and / or at a specific geoposition.

8. Hybrid or electric vehicle (1), in particular motor vehicle, comprising the system (100) according to any one of claims 1 to 7.

9. Computer-implemented method (300) for operating a hybrid or electric vehicle (1), comprising: Predicting (310), by a prediction module (120), a temperature of a drive energy storage device (10) for upcoming route segments of a route with a plurality of route segments using at least one Long Short-Term Memory network; and Ansteuem (320), by a control module (120), a temperature control module (110) such that thermal conditioning of the drive energy storage (10) takes place based on the predicted temperature of the drive energy storage (10). 24-0473 ABZ EXA 26.08.2024 10. Storage medium comprising a software program configured to run on one or more processors and thereby to execute the method (300) according to claim 9. 24-0473 ABZ EXA 26.08.2024

Images