Vehicle power parameter determination method and device, equipment, storage medium and product
By acquiring multi-dimensional operating condition data of new energy vehicles, using deep neural networks and federated reinforcement learning models to identify driving conditions, and combining historical driving styles to adjust power parameters, the problem of unstable driving of new energy vehicles in complex environments has been solved, achieving adaptive matching of power parameters and improving driving stability and safety.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHONGQING LANDIAN AUTOMOBILE TECHNOLOGY CO LTD
- Filing Date
- 2026-03-06
- Publication Date
- 2026-05-05
AI Technical Summary
New energy vehicles cannot effectively cope with complex and ever-changing real-world driving environments during operation, which affects driving safety.
By acquiring multi-dimensional operating condition data of the target vehicle, deep neural networks and federated reinforcement learning models are used to analyze vehicle status and identify driving conditions, determine target power parameters, and adjust parameters in combination with historical driving styles to achieve personalized matching of power parameters.
This ensures the adaptability of power parameters to different operating conditions and improves the driving stability and safety of new energy vehicles.
Smart Images
Figure CN121973759A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of automotive power control technology, and in particular to a method, apparatus, device, storage medium, and product for determining vehicle power parameters. Background Technology
[0002] With the continuous development of new energy technologies, the popularity of new energy vehicles is also increasing.
[0003] However, during operation, new energy vehicles often rely on single control parameters (such as vehicle speed or pedal opening) for power control, which makes them unable to effectively cope with complex and ever-changing real-world driving environments and affects their driving safety. Summary of the Invention
[0004] Therefore, it is necessary to provide a method, device, equipment, storage medium, and product for determining vehicle power parameters that can ensure the driving safety of new energy vehicles, addressing the aforementioned technical problems.
[0005] Firstly, this application provides a method for determining vehicle dynamic parameters. The method includes:
[0006] Obtain multi-dimensional operating condition data corresponding to the target vehicle;
[0007] The vehicle status is analyzed based on the multi-dimensional operating condition data to obtain the vehicle status of the target vehicle.
[0008] The driving conditions of the target vehicle are identified based on the multi-dimensional operating condition data to obtain the target operating conditions corresponding to the target vehicle.
[0009] Based on the target operating conditions and the vehicle status of the target vehicle, the target power parameters corresponding to the target vehicle are determined.
[0010] Secondly, this application also provides a vehicle dynamic parameters determination device. The device includes:
[0011] The acquisition module is used to acquire multi-dimensional operating condition data corresponding to the target vehicle and the vehicle status of the target vehicle;
[0012] The identification module is used to identify the driving conditions of the target vehicle based on the multi-dimensional operating condition data, and obtain the target operating conditions corresponding to the target vehicle.
[0013] The determination module is used to determine the target power parameters corresponding to the target vehicle based on the target operating conditions and the vehicle status of the target vehicle.
[0014] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:
[0015] The acquisition module is used to acquire multi-dimensional operating condition data corresponding to the target vehicle.
[0016] The identification module is used to analyze the vehicle status based on the multi-dimensional working condition data to obtain the vehicle status of the target vehicle.
[0017] The identification module is used to identify the driving conditions of the target vehicle based on the multi-dimensional operating condition data, and obtain the target operating conditions corresponding to the target vehicle.
[0018] The determination module is used to determine the target power parameters corresponding to the target vehicle based on the target operating conditions and the vehicle status of the target vehicle.
[0019] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:
[0020] Obtain multi-dimensional operating condition data corresponding to the target vehicle;
[0021] The vehicle status is analyzed based on the multi-dimensional operating condition data to obtain the vehicle status of the target vehicle.
[0022] The driving conditions of the target vehicle are identified based on the multi-dimensional operating condition data to obtain the target operating conditions corresponding to the target vehicle.
[0023] Based on the target operating conditions and the vehicle status of the target vehicle, the target power parameters corresponding to the target vehicle are determined.
[0024] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:
[0025] Obtain multi-dimensional operating condition data corresponding to the target vehicle;
[0026] The vehicle status is analyzed based on the multi-dimensional operating condition data to obtain the vehicle status of the target vehicle.
[0027] The driving conditions of the target vehicle are identified based on the multi-dimensional operating condition data to obtain the target operating conditions corresponding to the target vehicle.
[0028] Based on the target operating conditions and the vehicle status of the target vehicle, the target power parameters corresponding to the target vehicle are determined.
[0029] The aforementioned vehicle power parameter determination method, apparatus, equipment, storage medium, and product acquire multi-dimensional operating condition data and vehicle status corresponding to the target vehicle; identify the driving conditions of the target vehicle based on the multi-dimensional operating condition data to obtain the target operating conditions corresponding to the target vehicle; and then determine the target power parameters corresponding to the target vehicle based on the target operating conditions and vehicle status. As can be seen from the above, in the process of determining vehicle power parameters, this application first acquires multi-dimensional operating condition data and vehicle status corresponding to the target vehicle, thereby characterizing the operating conditions and vehicle status of the target vehicle through multi-dimensional operating condition data and vehicle status, providing a data foundation for subsequent identification of the driving conditions of the target vehicle and determination of the target power parameters corresponding to the target vehicle. Furthermore, by acquiring the target operating conditions corresponding to the target vehicle, this application achieves the determination of the target power parameters based on the target operating conditions and vehicle status, ensuring that the determined target power parameters conform to the target operating conditions corresponding to the target vehicle, enabling the target vehicle to cope with the current driving environment, ensuring that the power parameters of the target vehicle have a certain degree of operating condition adaptability during driving, and ensuring the driving stability and driving safety of the target vehicle. Attached Figure Description
[0030] Figure 1 This application provides an illustration of the application environment for a method for determining vehicle dynamic parameters.
[0031] Figure 2 A flowchart illustrating the first method for determining vehicle dynamic parameters provided in this application embodiment;
[0032] Figure 3 A flowchart illustrating the second method for determining vehicle dynamic parameters provided in this application embodiment;
[0033] Figure 4 A flowchart illustrating the third method for determining vehicle dynamic parameters provided in this application embodiment;
[0034] Figure 5 A schematic diagram of a multi-dimensional coordinate system consisting of at least one target dimension, provided for embodiments of this application;
[0035] Figure 6 A flowchart illustrating the fourth method for determining vehicle dynamic parameters provided in this application embodiment;
[0036] Figure 7 A structural block diagram of a vehicle dynamic parameter determination device provided in an embodiment of this application;
[0037] Figure 8 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation
[0038] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0039] The vehicle dynamic parameters determination method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, the vehicle-mounted terminal 102 communicates with the server 104 via a network. A data storage system can store the data that the server 104 needs to process. The data storage system can be integrated onto the server 104 or placed in the cloud or on another network server. The vehicle-mounted terminal 102 or the server 104 acquires multi-dimensional operating condition data and the vehicle status of the target vehicle; identifies the driving conditions of the target vehicle based on the multi-dimensional operating condition data to obtain the target operating condition corresponding to the target vehicle; and then determines the target power parameters corresponding to the target vehicle based on the target operating condition and the vehicle status. The server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.
[0040] In one embodiment, such as Figure 2 As shown, a method for determining vehicle dynamic parameters is provided, which can be applied to... Figure 1 Taking the vehicle-mounted terminal 102 as an example, the explanation includes the following steps:
[0041] S201, Obtain multi-dimensional operating condition data corresponding to the target vehicle.
[0042] When it is necessary to obtain multi-dimensional operating condition data corresponding to a target vehicle, data can be collected from the target vehicle through pre-configured on-board sensors to obtain the multi-dimensional operating condition data corresponding to the target vehicle.
[0043] Among them, multidimensional operating condition data can be vehicle-related parameters used to reflect the current operating condition of the target vehicle; multidimensional operating condition data can include, but is not limited to: ambient temperature of the vehicle, ambient humidity of the vehicle, road slope of the vehicle, current driving speed of the vehicle, and brake pedal opening of the vehicle.
[0044] When it is necessary to obtain multi-dimensional operating condition data corresponding to a target vehicle, the target vehicle can be pre-configured in terms of hardware. The hardware to be configured may include: 28-channel CAN (Controller Area Network) bus interface (interface standard: CAN 2.0B; Ethernet 100BASE-T1; 5G NR), sampling frequency 100Hz; 5G communication module; 56 vehicle sensors, etc. In this way, data collection of vehicle-related parameters corresponding to the current operating condition of the target vehicle can be achieved to obtain multi-dimensional operating condition data of the target vehicle.
[0045] S202, Perform vehicle status analysis based on the multi-dimensional operating condition data to obtain the vehicle status of the target vehicle.
[0046] Among them, vehicle status is used to characterize the specific status information of the target vehicle at present; as an example, vehicle status may include, but is not limited to: vehicle driving status, vehicle stationary status, vehicle fault status, etc.; among them, vehicle fault status can be further divided into vehicle power system fault status, vehicle chassis fault status, tire pressure and tire fault status, etc.
[0047] In one embodiment of this application, after obtaining the multi-dimensional operating condition data corresponding to the target vehicle, the multi-dimensional operating condition data can be analyzed based on a pre-trained state analysis model to obtain the vehicle state of the target vehicle.
[0048] The training process of the state analysis model includes: acquiring at least one sample working condition data and labeling the sample state corresponding to each sample working condition data through manual annotation or other means; then, training the initial model based on each sample working condition data with labeled sample states to obtain the trained state analysis model.
[0049] Specifically, the state analysis model can be a deep neural network architecture that integrates feature extraction and state classification; it includes an input layer, an encoding layer, a hidden feature layer, and a classification output layer; wherein, the input layer is used to receive multi-dimensional operating condition data corresponding to the target vehicle; the encoding layer is used to extract and analyze features from the multi-dimensional operating condition data; the hidden feature layer is used to further nonlinearly combine the features obtained by the encoding layer based on the coupling relationship between different dimensions of operating condition data; the classification output layer is used to receive the high-dimensional features output by the hidden feature layer, map them to predefined vehicle state categories, output a probability distribution, and finally obtain the vehicle state of the target vehicle based on the probability distribution.
[0050] S203 identifies the driving conditions of the target vehicle based on multi-dimensional operating condition data to obtain the target operating conditions corresponding to the target vehicle.
[0051] Among them, the target operating condition corresponding to the target vehicle is used to characterize the working status of the target vehicle during normal driving or power-on process; specifically, according to the actual situation of the target vehicle, the target operating condition includes at least one of the following: urban congestion operating condition, scenic mountain road operating condition, high-speed cruising operating condition, plateau environment operating condition, and low temperature environment operating condition.
[0052] In one embodiment of this application, identifying the driving conditions of a target vehicle based on multi-dimensional driving condition data to obtain the target driving conditions corresponding to the target vehicle may include the following: quantizing and analyzing the multi-dimensional driving condition data to obtain quantization parameters corresponding to at least one target dimension; wherein, the target dimension includes at least one of environmental dimension, road dimension, vehicle dimension, and driving dimension; identifying the driving conditions of the target vehicle based on the quantization parameters corresponding to each target dimension to obtain the target driving conditions corresponding to the target vehicle.
[0053] S204, based on the target operating conditions and the vehicle status of the target vehicle, determine the target power parameters corresponding to the target vehicle.
[0054] Among them, the target dynamic parameters are used to characterize the specific quantitative indicators corresponding to the target vehicle's power system.
[0055] In one embodiment of this application, when determining the target power parameters corresponding to the target vehicle based on the target operating conditions and the vehicle state of the target vehicle, the following may be included: determining the initial power parameters corresponding to the target vehicle based on the target operating conditions and the vehicle state of the target vehicle using a federated reinforcement learning model; adjusting the initial power parameters according to the target operating conditions to obtain the target power parameters.
[0056] The aforementioned method for determining vehicle power parameters involves acquiring multi-dimensional operating condition data and the vehicle status of the target vehicle; identifying the driving conditions of the target vehicle based on the multi-dimensional operating condition data to obtain the target operating conditions; and then determining the target power parameters of the target vehicle based on the target operating conditions and the vehicle status. As can be seen from the above, in the process of determining vehicle power parameters, this application first acquires multi-dimensional operating condition data and the vehicle status of the target vehicle. This multi-dimensional operating condition data and vehicle status characterize the operating conditions and vehicle status of the target vehicle, providing a data foundation for subsequent identification of the driving conditions of the target vehicle and determination of the target power parameters. Furthermore, by acquiring the target operating conditions of the target vehicle, this application achieves the determination of the target power parameters based on the target operating conditions and the vehicle status of the target vehicle, ensuring that the determined target power parameters conform to the target operating conditions of the target vehicle. This enables the target vehicle to cope with the current driving environment, ensuring that the power parameters of the target vehicle have a certain degree of adaptability during driving, and guaranteeing the driving stability and safety of the target vehicle.
[0057] In one embodiment, such as Figure 3 As shown, based on the target operating conditions and the vehicle status of the target vehicle, the target power parameters corresponding to the target vehicle are determined, which may include the following:
[0058] S301, based on a federated reinforcement learning model, determines the initial power parameters of the target vehicle according to the target operating conditions and the vehicle state of the target vehicle.
[0059] The initial power parameters may include, but are not limited to: motor output torque, battery SOC (State of Charge) target value, and gearbox ratio.
[0060] In one embodiment of this application, the federated reinforcement learning technology includes a federated learning framework, a reinforcement learning model, and an adaptive learning mechanism. By using federated reinforcement learning technology, the collaborative utilization of multi-vehicle data is achieved without directly sharing the original data, thereby reducing the risk of user privacy leakage and avoiding the problem that cross-vehicle and cross-regional collaborative learning cannot be achieved due to the independent storage of data from different car manufacturers.
[0061] Specifically, the federated learning framework adopts a "center-edge" architecture, where the central server is responsible for model aggregation and the edge nodes (vehicles) are responsible for local training. The federated learning framework achieves collaborative utilization of multi-vehicle data through the aggregation of multiple edge nodes without directly sharing the original data. It breaks down the barrier that "data from different car companies cannot achieve collaborative learning across vehicle models and regions due to independent storage," enabling the model to learn from data scattered across different vehicles and improving the model's generalization ability.
[0062] The state space of the reinforcement learning model includes four-dimensional operating condition coordinates and vehicle state parameters, specifically: temperature, humidity, altitude, and air pressure in the environmental dimension; slope, curvature, adhesion coefficient, and road type in the road dimension; vehicle speed, acceleration, battery SOC, and motor temperature in the vehicle dimension; and throttle opening, brake pedal opening, steering angle, and driving style in the driving dimension. The action space of the reinforcement learning model includes 12 control parameters such as motor output torque, target battery SOC value, and transmission ratio. The reinforcement learning model calculates the optimal initial power parameters for the target vehicle in real time based on relevant parameters (target operating conditions and the vehicle state of the target vehicle).
[0063] The adaptive learning mechanism comprises three parts: incremental learning, forgetting mechanism, and dynamic adjustment. Incremental learning refers to updating only the incremental part of the model with new data, reducing computational resource consumption and ensuring that the entire model does not need to be trained from scratch when the vehicle collects new operating data. The forgetting mechanism is based on importance assessment using the Fisher information matrix, ensuring that the model does not forget the old content it has already mastered while learning new content. Dynamic adjustment refers to adaptively adjusting the learning rate and training cycle according to changes in data volume and environment, realizing automatic adjustment of the model's learning pace to cope with different data volume and environmental changes.
[0064] S302, adjust the initial power parameters according to the target working conditions to obtain the target power parameters.
[0065] In one embodiment, step S302 may include: adjusting the initial power parameters according to the target operating condition to obtain candidate power parameters; obtaining the historical driving style of the target vehicle; and adaptively adjusting the candidate power parameters according to the historical driving style to obtain the target power parameters.
[0066] Among them, driving style can include, but is not limited to, aggressive, normal, and mild; therefore, when adaptively adjusting candidate power parameters based on historical driving style, candidate power parameters such as power response sensitivity and shift timing can be dynamically adjusted according to driving style to improve user satisfaction with personalized matching of target power parameters.
[0067] In one embodiment, when adjusting the initial power parameters according to the target operating condition to obtain candidate power parameters, the following may be included: determining the optimization target corresponding to the target operating condition; wherein, the target operating condition includes at least one of urban congestion operating condition, scenic mountain road operating condition, high-speed cruise operating condition, plateau environment operating condition, and low temperature environment operating condition; adjusting the initial power parameters according to the optimization target to obtain candidate power parameters.
[0068] In one embodiment of this application, the optimization objectives for urban congestion conditions include minimizing energy consumption and maximizing ride comfort. Therefore, when adjusting the initial power parameters according to the optimization objectives, the control strategy used is: Pulse & Glide optimization, operating within the motor efficiency range; thereby reducing the energy consumption of the target vehicle and improving following comfort.
[0069] In one embodiment of this application, the optimization objectives for mountain road conditions in scenic areas include: sufficient power and high braking safety. Therefore, when adjusting the initial power parameters according to the optimization objectives, the control strategy is: torque pre-distribution based on slope prediction and maximization of braking energy recovery; thereby improving the target vehicle's climbing ability and downhill safety.
[0070] In one embodiment of this application, the optimization objectives for high-speed cruising include: high economy and high stability. Therefore, when adjusting the initial power parameters according to the optimization objectives, the control strategy is: optimal speed range control and speed planning to minimize wind resistance; thereby reducing the energy consumption of the target vehicle at high speed and improving driving stability.
[0071] In one embodiment of this application, the optimization objectives for high-altitude environmental conditions include: maintaining power and controlling emissions; therefore, the control strategy used when adjusting the initial power parameters according to the optimization objectives is: altitude-based air-fuel ratio correction and adaptive adjustment of turbocharger pressure; thereby reducing the power decay and emissions of the target vehicle.
[0072] In one embodiment of this application, the optimization objectives for low-temperature operating conditions include: improving range and enhancing comfort. Therefore, the control strategy used when adjusting the initial power parameters according to the optimization objectives is: waste heat recovery and utilization, battery insulation control, and energy distribution optimization. This reduces the range degradation of the target vehicle and improves heating comfort.
[0073] The aforementioned method for determining vehicle power parameters, by determining the initial power parameters corresponding to the target vehicle, adjusts these initial power parameters according to the target operating conditions to obtain the target power parameters. This ensures that the determined target power parameters conform to the target operating conditions of the target vehicle, enabling the target vehicle to cope with the current driving environment. It also guarantees that the power parameters of the target vehicle have a certain degree of adaptability to operating conditions during operation, thus ensuring the driving stability and safety of the target vehicle.
[0074] In one embodiment, such as Figure 4 As shown, when it is necessary to identify the driving conditions of a target vehicle based on multi-dimensional operating condition data to obtain the target operating conditions corresponding to the target vehicle, the following can be included:
[0075] S401 performs quantitative analysis on multi-dimensional working condition data to obtain at least one quantitative parameter corresponding to the target dimension.
[0076] The target dimension includes at least one of the following: environmental dimension, road dimension, vehicle dimension, and driving dimension.
[0077] In one embodiment of this application, when it is necessary to quantize and analyze multidimensional working condition data, a working condition coordinate system transformation can be performed on the multidimensional working condition data. This working condition coordinate system is a multidimensional coordinate system composed of at least one target dimension, such as... Figure 5 As shown, the mathematical model of this working condition coordinate system is expressed as: G=(E (environment dimension), R (road dimension), V (vehicle dimension), D (driving dimension)). Furthermore, the transformed working condition coordinate system represents the quantitative parameters corresponding to at least one target dimension.
[0078] As an example, the quantification parameters corresponding to the environmental dimension include temperature, humidity, altitude, and atmospheric pressure. Temperature can be quantified using 16-bit AD sampling with a resolution of 0.0625℃, a sampling frequency of 1 Hz, and a data range of -40℃ to 85℃. Noise can be extracted using wavelet transform and sliding window averaging. Humidity can be quantified using a capacitive humidity sensor with a sampling frequency of 1 Hz and a data range of 0% to 100%RH. Feature extraction can be performed using exponential smoothing filtering. Altitude can be quantified using a barometric pressure sensor with an accuracy of ±0.1m, a sampling frequency of 1 Hz, and a data range of -500m to 5000m. Feature extraction can be performed using Kalman filtering. Atmospheric pressure can be quantified using an absolute pressure sensor with a sampling frequency of 1 Hz and a data range of 50kPa to 110kPa. Feature extraction can be performed using first-order low-pass filtering.
[0079] As an example, the quantification parameters corresponding to the environmental dimension include slope, curvature, road adhesion coefficient, and road type. Slope can be quantified using a dual-axis accelerometer with a sampling frequency of 10 Hz and a data range of -30° to 30°. Feature extraction can be performed using complementary filtering, slope fusion algorithms, and other methods. Curvature can be quantified using GPS positioning and electronic map data with a sampling frequency of 1 Hz and a data range of 0 to 0.1 rad / m. Feature extraction can be performed using polynomial fitting and other methods. Road adhesion coefficient can be quantified using wheel speed difference and torque with a sampling frequency of 10 Hz and a data range of 0.1 to 1.2. Feature extraction can be performed using extended Kalman filtering. Road type can be quantified using high-definition map matching with a sampling frequency of 0.1 Hz. The data range can include highway / urban / rural / off-road, and feature extraction can be performed using semantic segmentation algorithms.
[0080] As an example, the quantification parameters corresponding to the vehicle dimension include vehicle speed, acceleration, battery SOC, and motor temperature. Vehicle speed can be quantified using wheel speed sensor fusion, with a sampling frequency of 100 Hz and a data range of 0–250 km / h. Feature extraction can be performed using weighted fusion algorithms. Acceleration can be quantified using a triaxial accelerometer, with a sampling frequency of 100 Hz and a data range of -5 m / s² to 5 m / s². Feature extraction can be performed using sliding window variance methods. Battery SOC can be quantified using ampere-hour integration plus open-circuit voltage correction, with a sampling frequency of 1 Hz and a data range of 0%–100%. Feature extraction can be performed using extended Kalman filtering methods. Motor temperature can be quantified using an NTC thermistor, with a sampling frequency of 10 Hz and a data range of -40℃ to 150℃. Feature extraction can be performed using temperature field interpolation methods.
[0081] As an example, the quantitative parameters corresponding to the driving dimension include throttle opening, brake pedal opening, steering angle, and driving style. Specifically, throttle opening can be quantified using a 0-5V analog input with a sampling frequency of 100Hz and a data range of 0%-100%, and feature extraction can be performed using methods such as first-order derivative calculation. Brake pedal opening can also be quantified using a 0-5V analog input with a sampling frequency of 100Hz and a data range of 0%-100%, and feature extraction can be performed using edge detection algorithms. Steering angle can be quantified using a Hall effect sensor with a sampling frequency of 50Hz and a data range of -720° to 720°, and feature extraction can be performed using methods such as low-pass filtering. Driving style can be quantified through behavioral feature extraction with a sampling frequency of 0.1Hz, and the data range can include aggressive / normal / mild, and feature extraction can be performed using methods such as fuzzy logic classification.
[0082] S402, based on the quantitative parameters corresponding to each target dimension, identify the driving conditions of the target vehicle to obtain the target conditions corresponding to the target vehicle.
[0083] When it is necessary to identify the driving conditions of a target vehicle based on the quantitative parameters corresponding to each target dimension, and obtain the target conditions corresponding to the target vehicle, the following can be included: based on the quantitative parameters corresponding to each target dimension, determine the probability distribution of the target vehicle's affiliation to at least one candidate condition; based on the affiliation probability distribution, take the candidate condition with the highest affiliation probability as the target condition corresponding to the target vehicle.
[0084] In one embodiment of this application, when the candidate working condition with the highest belonging probability is taken as the target working condition corresponding to the target vehicle according to the belonging probability distribution, since the belonging probability distribution contains the belonging probability of the target vehicle belonging to each candidate working condition, the candidate working condition with the highest belonging probability in the belonging probability distribution is taken as the target working condition corresponding to the target vehicle.
[0085] A pre-trained Deep Belief Network (DBN) driving condition classification model can be implemented. The model structure includes: an input layer with 32 4-dimensional feature parameters; three hidden layers with 128, 64, and 32 nodes respectively; an output layer containing probability distributions for 200 typical driving conditions; a training algorithm using contrastive divergence (CD) with a learning rate of 0.01 and 1000 iterations; and an optimization method using Dropout regularization to prevent overfitting with a dropout rate of 0.3. Furthermore, the DBN model is used to identify the driving conditions of a target vehicle based on multi-dimensional driving condition data, thus obtaining the target driving condition corresponding to the target vehicle.
[0086] The aforementioned method for determining vehicle dynamic parameters, through quantization parameters corresponding to at least one target dimension, identifies the driving conditions of the target vehicle based on the quantization parameters corresponding to each target dimension, thereby obtaining the target driving conditions corresponding to the target vehicle and ensuring the successful acquisition of the target driving conditions.
[0087] In one embodiment, accurate prediction of operating conditions within a future period (e.g., 5-100 seconds) can also be achieved based on predictive matching technology driven by digital twins.
[0088] The digital twin system consists of four core technologies: multi-domain physical model, multi-scale prediction algorithm, model predictive control (MPC) strategy and dynamic correction mechanism. Specifically, the multi-domain physical model includes (1) battery model: equivalent circuit + electrochemical model hybrid modeling, considering temperature, aging, and charge / discharge rate effects; (2) motor model: high-precision electromagnetic model based on finite element analysis, considering iron loss, copper loss and magnetic saturation characteristics; (3) transmission system model: multi-body dynamics model including gear meshing loss and bearing friction loss; (4) thermal management model: three-dimensional fluid dynamics (CFD) heat conduction model with an accuracy of 0.5℃.
[0089] Multi-scale prediction algorithms can perform prediction operations at different levels, specifically divided into short-term prediction, medium-term prediction, and long-term prediction. Among them, short-term prediction (5-10s): deterministic prediction based on current operating conditions and driver behavior, using LSTM neural network, with prediction accuracy ≥95%; medium-term prediction (10-30s): probabilistic prediction combining high-precision map and vehicle trajectory, using attention mechanism + Bayesian network, with confidence ≥90%; long-term prediction (30-100s): trend prediction based on historical statistics and route planning, using Markov chain model, with error rate ≤15%.
[0090] The model predictive control strategy aims to minimize energy consumption, maximize power response, and ensure ride comfort. The constraints of the model predictive control strategy are: battery SOC range, motor temperature limit, and system impact threshold. The optimization algorithm of the model predictive control strategy is the interior point method, with a solution time ≤ 5ms.
[0091] The dynamic correction mechanism consists of three parts: model adaptation, error compensation, and learning optimization. Model adaptation refers to the online identification of model parameters based on Kalman filtering, which is updated every 100ms. Error compensation refers to the real-time comparison of the output differences between the physical system and the digital twin, using a PID compensation algorithm. Learning optimization refers to the continuous optimization of the prediction model based on the prediction error feedback of reinforcement learning.
[0092] Predictive matching technology driven by digital twins can predict potential dangers that a target vehicle may encounter during subsequent driving, thereby enabling the target vehicle to respond promptly to subsequent dangers, effectively reducing response delays and improving the driving comfort of the target vehicle.
[0093] In one embodiment, such as Figure 6 As shown, when it is necessary to determine the target power parameters corresponding to the target vehicle, the following can be included:
[0094] S601, acquire the multi-dimensional operating condition data and vehicle status of the target vehicle.
[0095] S602, perform quantitative analysis on multi-dimensional working condition data to obtain quantitative parameters corresponding to at least one target dimension; wherein, the target dimension includes at least one of the environmental dimension, road dimension, vehicle dimension and driving dimension.
[0096] S603, based on the quantization parameters corresponding to each target dimension, determine the probability distribution of the target vehicle's affiliation to at least one candidate working condition.
[0097] S604. Based on the attribution probability distribution, the candidate operating condition with the highest attribution probability is taken as the target operating condition corresponding to the target vehicle.
[0098] S605 is a federated reinforcement learning model pre-trained based on federated reinforcement learning technology. It determines the initial power parameters of the target vehicle according to the target operating conditions and the vehicle state of the target vehicle.
[0099] S606, determine the optimization objective corresponding to the target operating condition; wherein, the target operating condition includes at least one of the following: urban congestion operating condition, scenic mountain road operating condition, high-speed cruise operating condition, plateau environment operating condition, and low temperature environment operating condition.
[0100] S607, based on the optimization objective, the initial dynamic parameters are adjusted to obtain candidate dynamic parameters.
[0101] S608, obtain the target vehicle's historical driving style.
[0102] S609 adaptively adjusts candidate power parameters based on historical driving styles to obtain target power parameters.
[0103] The aforementioned method for determining vehicle power parameters involves acquiring multi-dimensional operating condition data and the vehicle status of the target vehicle; identifying the driving conditions of the target vehicle based on the multi-dimensional operating condition data to obtain the target operating conditions; and then determining the target power parameters of the target vehicle based on the target operating conditions and the vehicle status. As can be seen from the above, in the process of determining vehicle power parameters, this application first acquires multi-dimensional operating condition data and the vehicle status of the target vehicle. This multi-dimensional operating condition data and vehicle status characterize the operating conditions and vehicle status of the target vehicle, providing a data foundation for subsequent identification of the driving conditions of the target vehicle and determination of the target power parameters. Furthermore, by acquiring the target operating conditions of the target vehicle, this application achieves the determination of the target power parameters based on the target operating conditions and the vehicle status of the target vehicle, ensuring that the determined target power parameters conform to the target operating conditions of the target vehicle. This enables the target vehicle to cope with the current driving environment, ensuring that the power parameters of the target vehicle have a certain degree of adaptability during driving, and guaranteeing the driving stability and safety of the target vehicle.
[0104] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.
[0105] Based on the same inventive concept, this application also provides a vehicle power parameter determining device for implementing the vehicle power parameter determining method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more vehicle power parameter determining device embodiments provided below can be found in the limitations of the vehicle power parameter determining method described above, and will not be repeated here.
[0106] In one embodiment, such as Figure 7 As shown, a vehicle dynamic parameter determination device is provided, comprising: an acquisition module 10, an identification module 20, an identification module 30, and a determination module 40, wherein:
[0107] The acquisition module 10 is used to acquire multi-dimensional operating condition data corresponding to the target vehicle.
[0108] The identification module 20 is used to analyze the vehicle status based on multi-dimensional working condition data to obtain the vehicle status of the target vehicle.
[0109] The identification module 30 is used to identify the driving conditions of the target vehicle based on multi-dimensional working condition data, and obtain the target working conditions corresponding to the target vehicle.
[0110] The determination module 40 is used to determine the target power parameters corresponding to the target vehicle based on the target operating conditions and the vehicle status of the target vehicle.
[0111] In one embodiment, a federated reinforcement learning model pre-trained based on federated reinforcement learning technology determines the initial power parameters corresponding to the target vehicle according to the target working conditions and the vehicle state of the target vehicle.
[0112] The initial dynamic parameters are adjusted according to the target operating conditions to obtain the target dynamic parameters.
[0113] In one embodiment, the initial power parameters are adjusted according to the target operating condition to obtain candidate power parameters;
[0114] Obtain the target vehicle's historical driving style;
[0115] The candidate power parameters are adaptively adjusted based on historical driving styles to obtain the target power parameters.
[0116] In one embodiment, an optimization objective corresponding to a target operating condition is determined; wherein, the target operating condition includes at least one of urban congestion operating condition, scenic mountain road operating condition, high-speed cruising operating condition, plateau environment operating condition, and low temperature environment operating condition;
[0117] Based on the optimization objective, the initial dynamic parameters are adjusted to obtain candidate dynamic parameters.
[0118] In one embodiment, multidimensional working condition data is quantized and analyzed to obtain quantization parameters corresponding to at least one target dimension; wherein, the target dimension includes at least one of environmental dimension, road dimension, vehicle dimension and driving dimension;
[0119] The driving conditions of the target vehicle are identified based on the quantitative parameters corresponding to each target dimension, thus obtaining the target driving conditions corresponding to the target vehicle.
[0120] In one embodiment, the probability distribution of the target vehicle's affiliation to at least one candidate working condition is determined based on the quantization parameters corresponding to each target dimension.
[0121] Based on the probability distribution of attribution, the candidate working condition with the highest attribution probability is taken as the target working condition corresponding to the target vehicle.
[0122] The aforementioned vehicle power parameter determination device acquires multi-dimensional operating condition data and vehicle status of the target vehicle; identifies the driving conditions of the target vehicle based on the multi-dimensional operating condition data to obtain the target operating conditions corresponding to the target vehicle; and then determines the target power parameters corresponding to the target vehicle based on the target operating conditions and vehicle status. As can be seen from the above, in the process of determining vehicle power parameters, this application first acquires multi-dimensional operating condition data and vehicle status of the target vehicle, thereby characterizing the operating conditions and vehicle status of the target vehicle through the multi-dimensional operating condition data and vehicle status, providing a data foundation for subsequent identification of the driving conditions of the target vehicle and determination of the target power parameters corresponding to the target vehicle. Furthermore, by acquiring the target operating conditions corresponding to the target vehicle, this application achieves the determination of the target power parameters based on the target operating conditions and vehicle status of the target vehicle, ensuring that the determined target power parameters conform to the target operating conditions of the target vehicle, enabling the target vehicle to cope with the current driving environment, ensuring that the power parameters of the target vehicle have a certain degree of adaptability during driving, and guaranteeing the driving stability and safety of the target vehicle.
[0123] The various modules in the aforementioned vehicle dynamic parameter determination device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.
[0124] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 8As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for determining vehicle dynamic parameters. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.
[0125] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0126] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:
[0127] Obtain multi-dimensional operating condition data corresponding to the target vehicle;
[0128] The vehicle status is obtained by analyzing the multi-dimensional operating condition data.
[0129] The driving conditions of the target vehicle are identified based on multi-dimensional operating condition data to obtain the target operating conditions corresponding to the target vehicle.
[0130] Based on the target operating conditions and the vehicle status of the target vehicle, determine the target power parameters corresponding to the target vehicle.
[0131] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0132] The federated reinforcement learning model, pre-trained based on federated reinforcement learning technology, determines the initial power parameters of the target vehicle according to the target working conditions and the vehicle state of the target vehicle.
[0133] The initial dynamic parameters are adjusted according to the target operating conditions to obtain the target dynamic parameters.
[0134] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0135] The initial dynamic parameters are adjusted according to the target working condition to obtain candidate dynamic parameters;
[0136] Obtain the target vehicle's historical driving style;
[0137] The candidate power parameters are adaptively adjusted based on historical driving styles to obtain the target power parameters.
[0138] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0139] Determine the optimization objectives corresponding to the target operating conditions; wherein, the target operating conditions include at least one of the following: urban congestion operating conditions, scenic mountain road operating conditions, high-speed cruising operating conditions, plateau environment operating conditions, and low-temperature environment operating conditions;
[0140] Based on the optimization objective, the initial dynamic parameters are adjusted to obtain candidate dynamic parameters.
[0141] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0142] Quantitative analysis is performed on multidimensional working condition data to obtain quantitative parameters corresponding to at least one target dimension; wherein, the target dimension includes at least one of the following: environmental dimension, road dimension, vehicle dimension, and driving dimension;
[0143] The driving conditions of the target vehicle are identified based on the quantitative parameters corresponding to each target dimension, thus obtaining the target driving conditions corresponding to the target vehicle.
[0144] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0145] Based on the quantitative parameters corresponding to each target dimension, determine the probability distribution of the target vehicle's affiliation to at least one candidate working condition.
[0146] Based on the probability distribution of attribution, the candidate working condition with the highest attribution probability is taken as the target working condition corresponding to the target vehicle.
[0147] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:
[0148] Obtain multi-dimensional operating condition data corresponding to the target vehicle;
[0149] The vehicle status is obtained by analyzing the multi-dimensional operating condition data.
[0150] The driving conditions of the target vehicle are identified based on multi-dimensional operating condition data to obtain the target operating conditions corresponding to the target vehicle.
[0151] Based on the target operating conditions and the vehicle status of the target vehicle, determine the target power parameters corresponding to the target vehicle.
[0152] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0153] The federated reinforcement learning model, pre-trained based on federated reinforcement learning technology, determines the initial power parameters of the target vehicle according to the target working conditions and the vehicle state of the target vehicle.
[0154] The initial dynamic parameters are adjusted according to the target operating conditions to obtain the target dynamic parameters.
[0155] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0156] The initial dynamic parameters are adjusted according to the target working condition to obtain candidate dynamic parameters;
[0157] Obtain the target vehicle's historical driving style;
[0158] The candidate power parameters are adaptively adjusted based on historical driving styles to obtain the target power parameters.
[0159] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0160] Determine the optimization objectives corresponding to the target operating conditions; wherein, the target operating conditions include at least one of the following: urban congestion operating conditions, scenic mountain road operating conditions, high-speed cruising operating conditions, plateau environment operating conditions, and low-temperature environment operating conditions;
[0161] Based on the optimization objective, the initial dynamic parameters are adjusted to obtain candidate dynamic parameters.
[0162] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0163] Quantitative analysis is performed on multidimensional working condition data to obtain quantitative parameters corresponding to at least one target dimension; wherein, the target dimension includes at least one of the following: environmental dimension, road dimension, vehicle dimension, and driving dimension;
[0164] The driving conditions of the target vehicle are identified based on the quantitative parameters corresponding to each target dimension, thus obtaining the target driving conditions corresponding to the target vehicle.
[0165] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0166] Based on the quantitative parameters corresponding to each target dimension, determine the probability distribution of the target vehicle's affiliation to at least one candidate working condition.
[0167] Based on the probability distribution of attribution, the candidate working condition with the highest attribution probability is taken as the target working condition corresponding to the target vehicle.
[0168] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:
[0169] Obtain multi-dimensional operating condition data corresponding to the target vehicle;
[0170] The vehicle status is obtained by analyzing the multi-dimensional operating condition data.
[0171] The driving conditions of the target vehicle are identified based on multi-dimensional operating condition data to obtain the target operating conditions corresponding to the target vehicle.
[0172] Based on the target operating conditions and the vehicle status of the target vehicle, determine the target power parameters corresponding to the target vehicle.
[0173] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0174] The federated reinforcement learning model, pre-trained based on federated reinforcement learning technology, determines the initial power parameters of the target vehicle according to the target working conditions and the vehicle state of the target vehicle.
[0175] The initial dynamic parameters are adjusted according to the target operating conditions to obtain the target dynamic parameters.
[0176] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0177] The initial dynamic parameters are adjusted according to the target working condition to obtain candidate dynamic parameters;
[0178] Obtain the target vehicle's historical driving style;
[0179] The candidate power parameters are adaptively adjusted based on historical driving styles to obtain the target power parameters.
[0180] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0181] Determine the optimization objectives corresponding to the target operating conditions; wherein, the target operating conditions include at least one of the following: urban congestion operating conditions, scenic mountain road operating conditions, high-speed cruising operating conditions, plateau environment operating conditions, and low-temperature environment operating conditions;
[0182] Based on the optimization objective, the initial dynamic parameters are adjusted to obtain candidate dynamic parameters.
[0183] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0184] Quantitative analysis is performed on multidimensional working condition data to obtain quantitative parameters corresponding to at least one target dimension; wherein, the target dimension includes at least one of the following: environmental dimension, road dimension, vehicle dimension, and driving dimension;
[0185] The driving conditions of the target vehicle are identified based on the quantitative parameters corresponding to each target dimension, thus obtaining the target driving conditions corresponding to the target vehicle.
[0186] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0187] Based on the quantitative parameters corresponding to each target dimension, determine the probability distribution of the target vehicle's affiliation to at least one candidate working condition.
[0188] Based on the probability distribution of attribution, the candidate working condition with the highest attribution probability is taken as the target working condition corresponding to the target vehicle.
[0189] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.
[0190] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.
[0191] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0192] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.
Claims
1. A method for determining vehicle dynamic parameters, characterized in that, The method includes: Obtain multi-dimensional operating condition data corresponding to the target vehicle; The vehicle status is analyzed based on the multi-dimensional operating condition data to obtain the vehicle status of the target vehicle. The driving conditions of the target vehicle are identified based on the multi-dimensional operating condition data to obtain the target operating conditions corresponding to the target vehicle. Based on the target operating conditions and the vehicle status of the target vehicle, the target power parameters corresponding to the target vehicle are determined.
2. The method according to claim 1, characterized in that, Determining the target power parameters corresponding to the target vehicle based on the target operating condition and the vehicle status of the target vehicle includes: The initial power parameters of the target vehicle are determined by the federated reinforcement learning model based on the target operating conditions and the vehicle state of the target vehicle. The initial power parameters are adjusted according to the target operating condition to obtain the target power parameters.
3. The method according to claim 2, characterized in that, The step of adjusting the initial power parameters according to the target operating condition to obtain the target power parameters includes: The initial power parameters are adjusted according to the target operating condition to obtain candidate power parameters; Obtain the historical driving style of the target vehicle; The candidate power parameters are adjusted based on the historical driving style to obtain the target power parameters.
4. The method according to claim 3, characterized in that, The step of adjusting the initial power parameters according to the target working condition to obtain candidate power parameters includes: Determine the optimization objective corresponding to the target operating condition; wherein, the target operating condition includes at least one of the following: urban congestion operating condition, scenic mountain road operating condition, high-speed cruising operating condition, plateau environment operating condition, and low temperature environment operating condition; The initial dynamic parameters are adjusted according to the optimization objective to obtain candidate dynamic parameters.
5. The method according to any one of claims 1-4, characterized in that, The step of identifying the driving conditions of the target vehicle based on the multi-dimensional operating condition data to obtain the target operating conditions corresponding to the target vehicle includes: The multidimensional working condition data is quantitatively analyzed to obtain at least one quantitative parameter corresponding to a target dimension; wherein, the target dimension includes at least one of the following: environmental dimension, road dimension, vehicle dimension, and driving dimension. The driving conditions of the target vehicle are identified based on the quantization parameters corresponding to each target dimension, thereby obtaining the target driving conditions corresponding to the target vehicle.
6. The method according to claim 5, characterized in that, The step of identifying the driving conditions of the target vehicle based on the quantization parameters corresponding to each target dimension to obtain the target driving conditions corresponding to the target vehicle includes: Based on the quantization parameters corresponding to each of the target dimensions, determine the probability distribution of the target vehicle's affiliation to at least one candidate working condition; Based on the attribution probability distribution, the candidate operating condition with the highest attribution probability is taken as the target operating condition corresponding to the target vehicle.
7. A device for determining vehicle dynamic parameters, characterized in that, The device includes: The acquisition module is used to acquire multi-dimensional operating condition data corresponding to the target vehicle. The identification module is used to analyze the vehicle status based on the multi-dimensional working condition data to obtain the vehicle status of the target vehicle. The identification module is used to identify the driving conditions of the target vehicle based on the multi-dimensional operating condition data, and obtain the target operating conditions corresponding to the target vehicle. The determination module is used to determine the target power parameters corresponding to the target vehicle based on the target operating conditions and the vehicle status of the target vehicle.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.