Energy-saving method and device for charging vehicle power battery

Abstract

This application relates to a method and apparatus for energy-saving charging of a vehicle power battery. The method involves acquiring the current operating parameters of a wireless charging system for charging the power battery and determining at least one control reference factor for the wireless charging system. Based on the at least one control reference factor, a correction amount is determined for a corresponding target operating parameter in the current operating parameters. The correction amount is used to correct the current operating parameters to obtain the actual operating parameters of the wireless charging system, and the wireless charging system is controlled to charge the power battery according to the actual operating parameters. This application can achieve adaptive adjustment of the operating parameters of the wireless charging system by determining the control reference factor, calculating the correction amount, and correcting the operating parameters. This effectively improves the system's energy transmission efficiency, reduces energy loss and electromagnetic interference, while protecting battery health and extending the service life of the power battery.

Description

Technical Field

[0001] This application relates to the field of new energy vehicle charging technology, specifically to a method and apparatus for energy-saving charging of vehicle power batteries. Background Technology

[0002] In related technologies, wireless charging systems for power batteries can adopt static parameter configuration to charge at a fixed frequency and power, and achieve energy transfer through a fixed magnetic coupling mechanism. When charging multiple vehicles, each system operates independently and uses a constant current / constant voltage mode to charge the battery.

[0003] However, in related technologies, the charging parameters are statically configured and cannot be adaptively adjusted according to changes in battery state of charge, temperature, road surface material, electromagnetic interference, and other operating conditions; the coil spacing and angle of the magnetic coupling mechanism remain fixed, resulting in the actual energy transmission efficiency being significantly lower than the design nominal value; when multiple vehicles are wirelessly charged at the same time, electromagnetic field interference is easily generated, causing additional energy loss; under high temperature or high current charging conditions, the aging process of battery electrode materials is accelerated, and the battery health is damaged, which urgently needs improvement. Summary of the Invention

[0004] The purpose of this application is to provide a charging energy-saving method and device for vehicle power batteries, in order to solve the following technical problems in related technologies: the charging parameters are statically configured and cannot be adaptively adjusted according to changes in battery state of charge, temperature, road surface material, electromagnetic interference, and other operating conditions; the coil spacing and angle of the magnetic coupling mechanism remain fixed, resulting in the actual energy transmission efficiency being significantly lower than the design nominal value; when multiple vehicles are wirelessly charged at the same time, electromagnetic field interference is easily generated, causing additional energy loss; and under high temperature or high current charging conditions, the aging process of battery electrode materials is accelerated, and the battery health is damaged.

[0005] To achieve the above objectives, according to one aspect of this application, a method for charging and saving energy for a vehicle power battery is provided, comprising the following steps: Obtain the current operating parameters of the wireless charging system for charging the power battery, and determine at least one control reference factor of the wireless charging system; Based on the at least one control reference factor, determine the correction amount of the corresponding target operating parameter in the current operating parameters; The current operating parameters are corrected using the correction amount to obtain the actual operating parameters of the wireless charging system, and the wireless charging system is controlled to charge the power battery according to the actual operating parameters.

[0006] Optionally, in one embodiment of this application, determining at least one control reference factor of the wireless charging system includes: acquiring the target performance index, predicted battery life, multi-vehicle cooperative benefits, and road charging performance of the wireless charging system; and determining the at least one control reference factor based on the target performance index, the predicted battery life, the multi-vehicle cooperative benefits, and the road charging performance.

[0007] Optionally, in one embodiment of this application, determining the correction amount of the target operating parameter in the current operating parameters based on the at least one control reference factor includes: randomly generating at least one set of particles based on the target operating parameter, and obtaining the boundary constraints corresponding to the at least one set of particles; constructing a fitness function based on the energy transmission efficiency and system stability of the wireless charging system; determining the target performance index based on the fitness function and the boundary constraints; and determining the correction amount based on the target performance index.

[0008] Optionally, in one embodiment of this application, determining the correction amount of the corresponding target operating parameter in the current operating parameters based on the at least one control reference factor includes: obtaining historical operating parameters of the wireless charging system; determining model parameters of the LSTM (Long Short Term Memory) model based on the historical operating parameters; training the LSTM model based on the model parameters and the historical operating parameters until the prediction accuracy of the LSTM model is greater than a preset threshold to obtain a battery life prediction model, and outputting the predicted battery life; and determining the correction amount based on the predicted battery life.

[0009] Optionally, in one embodiment of this application, determining the correction amount of the corresponding target operating parameter in the current operating parameters based on the at least one control reference factor includes: obtaining the energy transmission efficiency and electromagnetic interference cost of the vehicle and surrounding vehicles based on the target operating parameters; determining a revenue function based on the energy transmission efficiency and the electromagnetic interference cost; determining the multi-vehicle collaborative revenue based on the revenue function; and determining the correction amount based on the multi-vehicle collaborative revenue.

[0010] Optionally, in one embodiment of this application, determining the correction amount of the corresponding target operating parameter in the current operating parameters based on the at least one control reference factor includes: obtaining the corresponding road surface material information based on the target operating parameter; determining the transmission compensation coefficient and the target charging mode based on the road surface material information; calculating the road surface charging performance based on the transmission compensation coefficient and the target charging mode; and determining the correction amount based on the road surface charging performance.

[0011] According to a second aspect of this application, a charging and energy-saving device for a vehicle power battery is provided, comprising: The first determining module is used to acquire the current operating parameters of the wireless charging system for charging the power battery, and to determine at least one control reference factor of the wireless charging system. The second determining module is used to determine the correction amount of the corresponding target operating parameter in the current operating parameters based on the at least one control reference factor; The control module is used to correct the current operating parameters using the correction amount to obtain the actual operating parameters of the wireless charging system, and to control the wireless charging system to charge the power battery according to the actual operating parameters.

[0012] Optionally, in one embodiment of this application, the first determining module includes: a first acquiring unit, configured to acquire the target performance index, predicted battery life, multi-vehicle cooperative benefits, and road charging performance of the wireless charging system; and a first determining unit, configured to determine the at least one control reference factor based on the target performance index, the predicted battery life, the multi-vehicle cooperative benefits, and the road charging performance.

[0013] Optionally, in one embodiment of this application, the second determining module includes: a second obtaining unit, configured to randomly generate at least one set of particles based on the target operating parameters, and obtain the boundary constraints corresponding to the at least one set of particles; a constructing unit, configured to construct a fitness function based on the energy transmission efficiency and system stability of the wireless charging system; a second determining unit, configured to determine the target performance index based on the fitness function and the boundary constraints; and a third determining unit, configured to determine the correction amount based on the target performance index.

[0014] Optionally, in one embodiment of this application, the second determining module includes: a third acquiring unit, used to acquire historical operating parameters of the wireless charging system; a fourth determining unit, used to determine model parameters of the LSTM model based on the historical operating parameters; an output unit, used to train the LSTM model based on the model parameters and the historical operating parameters until the prediction accuracy of the LSTM model is greater than a preset threshold, to obtain a battery life prediction model, and to output the predicted battery life; and a fifth determining unit, used to determine the correction amount based on the predicted battery life.

[0015] Optionally, in one embodiment of this application, the second determining module includes: a fourth obtaining unit, configured to obtain the energy transmission efficiency and electromagnetic interference cost of the vehicle and surrounding vehicles based on the target operating parameters; a sixth determining unit, configured to determine a benefit function based on the energy transmission efficiency and the electromagnetic interference cost; a seventh determining unit, configured to determine the multi-vehicle collaborative benefit based on the benefit function; and an eighth determining unit, configured to determine the correction amount based on the multi-vehicle collaborative benefit.

[0016] Optionally, in one embodiment of this application, the second determining module includes: a fifth obtaining unit, configured to obtain corresponding road surface material information based on the target operating parameters; a ninth determining unit, configured to determine a transmission compensation coefficient and a target charging mode based on the road surface material information; a calculation unit, configured to calculate the road surface charging performance based on the transmission compensation coefficient and the target charging mode; and a tenth determining unit, configured to determine the correction amount based on the road surface charging performance.

[0017] According to a third aspect of this application, a vehicle is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the energy-saving charging method for a vehicle power battery as described in the above embodiments.

[0018] According to a fourth aspect of this application, a computer-readable storage medium is provided that stores a computer program, which, when executed by a processor, implements the above-described method for charging and saving energy of a vehicle power battery.

[0019] According to a fifth aspect of this application, a computer program product is provided, comprising a computer program that, when executed, implements the above-described energy-saving charging method for a vehicle power battery.

[0020] The above technical solution allows for the acquisition of current operating parameters of the wireless charging system for power batteries and the determination of control reference factors. Based on these control reference factors, correction values ​​are then determined, and these correction values ​​are used to adjust the current operating parameters, yielding actual operating parameters. This enables the wireless charging system to charge the power battery. By determining control reference factors, calculating correction values, and adjusting operating parameters, the system achieves adaptive adjustment of its operating parameters, effectively improving energy transmission efficiency, reducing energy loss and electromagnetic interference, while simultaneously protecting battery health and extending battery lifespan. This solves several technical problems in related technologies, including: statically configured charging parameters that cannot be adaptively adjusted based on changes in battery state of charge, temperature, road surface material, and electromagnetic interference; fixed coil spacing and angle in the magnetic coupling mechanism leading to significantly lower actual energy transmission efficiency than the design specifications; electromagnetic interference during simultaneous wireless charging of multiple vehicles causing additional energy loss; and accelerated aging of battery electrode materials and compromised battery health under high-temperature or high-current charging conditions.

[0021] Other features and advantages of this application will be described in detail in the following detailed description section. Attached Figure Description

[0022] The accompanying drawings are provided to further illustrate the present application and form part of the specification. They are used together with the following detailed description to explain the present application, but do not constitute a limitation thereof. In the drawings: The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of a charging energy-saving method for a vehicle power battery according to an embodiment of this application; Figure 2 This is a flowchart illustrating the determination of correction amounts based on target performance indicators according to an embodiment of this application; Figure 3 This is a flowchart illustrating the determination of correction amounts based on predicted battery life according to one embodiment of this application; Figure 4 A flowchart illustrating the working principle of a vehicle power battery charging energy-saving method according to an embodiment of this application; Figure 5 This is a block diagram of a charging energy-saving device for a vehicle power battery provided according to an embodiment of this application; Figure 6 This is a structural schematic diagram of a vehicle provided according to an embodiment of this application.

[0023] Explanation of reference numerals in the attached figures 10-Charging and energy-saving device for vehicle power battery; 100-First determining module, 200-Second determining module, 300-Control module; 601-Memory, 602-Processor, 603-Communication interface. Detailed Implementation

[0024] The specific embodiments of this application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this application.

[0025] In this application, unless otherwise stated, directional terms such as "up," "down," "top," "bottom," "front," "rear," "left," and "right" are generally defined in the context of a vehicle's normal driving state (see reference for details). Figure 1 (As shown), it is only for the convenience of describing this application and simplifying the description, and is not intended to indicate or imply that the device or element referred to must have a specific orientation, or a specific orientation construction and operation, and therefore should not be construed as a limitation of this application. "Inner" and "outer" refer to the inner and outer contours of the corresponding components. In addition, the terms "first," "second," etc., used are to distinguish one element from another and do not have any order or importance.

[0026] In the description of this application, it should also be noted that, unless otherwise expressly specified and limited, the terms "set up," "connect," "link," and "install" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0027] Specifically, Figure 1 This is a flowchart of a charging and energy-saving method for a vehicle power battery according to an embodiment of this application.

[0028] like Figure 1 As shown, the energy-saving charging method for the vehicle's power battery includes the following steps: In step S101, the current operating parameters of the wireless charging system for charging the power battery are obtained, and at least one control reference factor of the wireless charging system is determined.

[0029] It is understood that, in the embodiments of this application, the current operating parameters may include, but are not limited to, state of charge, battery temperature, capacity, internal resistance, capacity decay rate, voltage, current, number of surrounding vehicles, distance between the vehicle and surrounding vehicles, charging start and stop times, power distribution, power adjustment range, road surface material, charging mode, charging frequency, transmission power, coil spacing and coil tilt angle, etc., and this application does not impose specific limitations.

[0030] In some embodiments, the present application embodiments may first obtain the current operating parameters of the wireless charging system for charging the power battery, and then determine at least one control reference factor of the wireless charging system based on the current operating parameters.

[0031] Optionally, in one embodiment of this application, determining at least one control reference factor for the wireless charging system includes: acquiring the target performance index, predicted battery life, multi-vehicle cooperative benefits, and road charging performance of the wireless charging system; and determining at least one control reference factor based on the target performance index, predicted battery life, multi-vehicle cooperative benefits, and road charging performance.

[0032] It can be understood that the control reference factors in the embodiments of this application may include, but are not limited to, target performance indicators, battery predicted life, multi-vehicle cooperative benefits and road charging performance, etc., and this application does not impose specific limitations.

[0033] In some embodiments, the present application embodiments may first obtain the target performance indicators of the wireless charging system, the predicted battery life, the multi-vehicle cooperative benefits, and the road charging performance, and then comprehensively determine at least one control reference factor that the control system needs to refer to when performing dynamic adjustment and cooperative scheduling based on the target performance indicators, the predicted battery life, the multi-vehicle cooperative benefits, and the road charging performance.

[0034] This application embodiment determines control reference factors by comprehensively considering the target performance indicators of the wireless charging system, the predicted battery life, the benefits of multi-vehicle collaboration, and the road charging performance. This enables collaborative optimization control under multi-dimensional constraints, taking into account energy transmission efficiency, battery health life, multi-vehicle collaboration benefits, and adaptability to complex road environments, thereby improving the overall operating performance and reliability of the system.

[0035] In step S102, the correction amount of the corresponding target operating parameter in the current operating parameters is determined based on at least one control reference factor.

[0036] It is understood that, in the embodiments of this application, the correction amount can be understood as the amount of change required to adjust the target operating parameters of the wireless charging system from real-time values ​​to expected values ​​that match the corresponding control reference factors. The target operating parameters are determined based on the corresponding control reference factors. For example, when the control reference factor is a target performance indicator, its target operating parameters may include, but are not limited to, charging frequency, transmission power, coil spacing, and coil tilt angle, etc., and this application does not impose specific limitations. When the control reference factor is predicted battery life, its target operating parameters may include, but are not limited to, charging frequency, charging power, and battery temperature, etc., and this application does not impose specific limitations. When the control reference factor is multi-vehicle cooperative benefits, its target operating parameters may include, but are not limited to, the transmission power of the vehicle and surrounding vehicles, and the distance between the vehicle and surrounding vehicles, etc., and this application does not impose specific limitations. When the control reference factor is road charging performance, its target operating parameters may include, but are not limited to, coil spacing and charging mode, etc., and this application does not impose specific limitations.

[0037] In some embodiments, the present application embodiments can determine the correction amount of the target operating parameter in the current operating parameters based on at least one control reference factor that corresponds to the current operating parameter.

[0038] Optionally, in one embodiment of this application, determining the correction amount of the target operating parameter in the current operating parameters based on at least one control reference factor includes: randomly generating at least one set of particles based on the target operating parameters and obtaining the boundary constraints corresponding to at least one set of particles; constructing a fitness function based on the energy transmission efficiency and system stability of the wireless charging system; determining the target performance index based on the fitness function and the boundary constraints; and determining the correction amount based on the target performance index.

[0039] It is understood that in the optimization algorithms (such as particle swarm optimization, etc., which are not specifically limited in this application) in the embodiments of this application, a particle represents a candidate solution vector, that is, a set of running parameters to be optimized, and the correction amount is determined by iteratively searching for the optimal solution.

[0040] Boundary constraints can be understood as the allowed range of values ​​for each dimension of each particle. For example, charging frequency. : Transmission power : Coil spacing : Coil tilt angle : The values ​​mentioned above are merely examples, and specific values ​​can be set by those skilled in the art according to actual circumstances. This application does not impose any specific restrictions.

[0041] The fitness function is a mathematical function used to evaluate the merits of each particle (candidate solution). In this embodiment, the fitness function uses energy transfer efficiency and system stability as input variables and outputs a fitness value. A higher fitness value indicates that the corresponding combination of control parameters better balances high efficiency and high stability. Therefore, the goal of this embodiment is to maximize the fitness function. The expression for the fitness function can be, but is not limited to, the following: , in, For energy transfer efficiency, As a system stability indicator, , For example, preset weighting coefficients, , The specific settings can be made by those skilled in the art according to the actual situation, and this application does not impose specific restrictions.

[0042] Energy transfer efficiency, also known as power efficiency, can be understood as the ratio of the useful power output by the receiver to the active power input by the transmitter in a wireless charging system, usually expressed as a percentage. It reflects the degree of loss in the electromagnetic energy conversion and transmission process and is one of the core indicators for evaluating wireless charging performance.

[0043] System stability can be understood as the ability of a wireless charging system to maintain key quantities such as output voltage, current and frequency within allowable ranges without oscillation, loss of lock-up and loss of control when subjected to changes in internal parameters (such as coil offset or sudden load changes) or external disturbances (such as foreign objects on the road surface, etc., which are not specifically limited in this application).

[0044] In some embodiments, the present application embodiments can randomly generate at least one set of particle parameters based on the current operating parameters, obtain the boundary constraints corresponding to each set of particle parameters, and then construct a fitness function based on the energy transmission efficiency and system stability of the wireless charging system. Based on the fitness function and boundary constraints, the target performance index of the system is selected and determined, and then the corresponding parameter correction amount is determined based on the difference between the target performance index and the current operating parameters.

[0045] The target performance index can be understood as the expected performance value of the optimal particle obtained by iteratively solving the fitness function through an optimization algorithm (such as particle swarm optimization), representing the ideal operating state that the system should achieve under the current operating conditions.

[0046] For example, embodiments of this application can use a particle swarm optimization algorithm to dynamically adjust the charging frequency, transmission power, coil spacing, and coil tilt angle of the wireless charging system. Through global optimization, it achieves adaptive improvements in energy transfer efficiency and system stability. The main contents are as follows: Figure 2 As shown, it includes: Step S201: Initialize a set of random particles.

[0047] In this embodiment, a set of random particles can be initialized within the allowed parameter space, with each particle representing a set of candidate parameter combinations (including charging frequency, transmission power, coil spacing, and coil tilt angle, etc.).

[0048] Step S202: Iterative optimization.

[0049] In this embodiment, the process of iterative optimization is carried out. In each iteration, the solved operating parameters are substituted into the fitness function to calculate the comprehensive fitness value of energy transmission efficiency and system stability. The historical best position of each particle is compared with the current fitness value and the individual best solution is updated. At the same time, the global best solution is selected from all particles.

[0050] Step S203: Determine the target performance indicators.

[0051] In this embodiment, the velocity-position update formula of the particle swarm optimization algorithm is used to adjust the velocity and position of each particle, combining the individual optimal solution and the global optimal solution. Particles that exceed the boundary constraints are processed, and after multiple iterations until convergence, the particle combination that achieves the best overall energy transfer efficiency and system stability is finally output, thus obtaining the target performance index.

[0052] Step S204: Determine the correction amount.

[0053] In this embodiment, the correction amount can be determined based on the target performance index, thereby achieving adaptive improvement of the wireless charging process.

[0054] This application embodiment generates candidate particles with boundary constraints based on current operating parameters, constructs a fitness function based on energy transfer efficiency and system stability, combines the two to determine the optimal target performance index and calculates parameter correction, thereby realizing intelligent closed-loop optimization of control parameters for wireless charging systems, taking into account both energy transfer efficiency and system operating stability, and significantly improving the dynamic adaptability and robustness of the control strategy.

[0055] Optionally, in one embodiment of this application, determining the correction amount of the corresponding target operating parameter in the current operating parameters based on at least one control reference factor includes: obtaining historical operating parameters of the wireless charging system; determining the model parameters of the LSTM model based on the historical operating parameters; training the LSTM model based on the model parameters and historical operating parameters until the prediction accuracy of the LSTM model is greater than a preset threshold to obtain a battery life prediction model and output the predicted battery life; and determining the correction amount based on the predicted battery life.

[0056] It is understood that, in the embodiments of this application, historical operating parameters can be understood as time-series data related to the charging process recorded and stored by the wireless charging system over a period of time (such as one month, which is not specifically limited in this application). These parameters may include, but are not limited to, charging frequency, charging power, battery temperature, and capacity decay rate, which are not specifically limited in this application.

[0057] Furthermore, embodiments of this application can utilize an LSTM model to predict the battery's cycle life under current operating parameters, thereby determining the predicted battery lifespan. It should be noted that the prediction accuracy of the LSTM model in these embodiments is a prerequisite for quantization. If the LSTM prediction is inaccurate, the model prediction is meaningless. Therefore, embodiments of this application can determine the LSTM model parameters and training data for training the LSTM model based on historical operating parameters, until the LSTM model's prediction accuracy exceeds a preset threshold. The preset threshold can be set by those skilled in the art according to actual conditions, and this application does not impose specific limitations.

[0058] The LSTM model is a special type of recurrent neural network specifically designed to process time-series data with long-term dependencies. By introducing input gates, forget gates, and output gates, LSTM can effectively avoid the vanishing or exploding gradient problem, thereby learning and memorizing historical information over longer time steps. The model parameters may include, but are not limited to, structural parameters and trainable weight parameters. Structural parameters may include, but are not limited to, the number of layers in the LSTM network, the number of hidden units per layer, the time step (length of the input sequence), the learning rate, and the batch size, and need to be preset before training or determined through hyperparameter optimization. Trainable weight parameters may include, but are not limited to, the weight matrix and bias terms of each gate and unit state in the LSTM network. They can be continuously updated during training through backpropagation and optimization algorithms (such as Adam) to make the model fit historical data. The specific values ​​can be determined by historical running parameters and preset thresholds, and this application does not impose specific restrictions.

[0059] In some embodiments, the present application embodiments may first obtain the historical operating parameters of the wireless charging system, configure the model parameters of the LSTM model according to the historical operating parameters, and then train the LSTM model based on the model parameters and the historical operating parameters until the prediction accuracy of the model is greater than a preset threshold, thereby constructing a battery life prediction model to output the predicted battery life, and determining the correction amount based on the predicted battery life.

[0060] For example, embodiments of this application can construct an LSTM model to predict the impact of current operating parameters on battery cycle life and output the predicted battery life. The inputs to the LSTM model may include, but are not limited to, charging frequency (e.g., 80kHz to 100kHz, not specifically limited in this application), charging power (e.g., 3kW to 11kW, not specifically limited in this application), battery temperature (e.g., 15℃ to 55℃, not specifically limited in this application), and capacity decay rate (e.g., 0.01% / cycle to 0.05% / cycle, not specifically limited in this application), etc., which are not specifically limited in this application. The output is the predicted battery life, i.e., the number of remaining charging cycles from the current state to the end of the life, with the window length set to N charging cycles (N is 10, not specifically limited in this application).

[0061] In addition, the LSTM model in this embodiment adopts a two-layer long short-term memory network architecture. The network structure includes two LSTM layers and a Dropout layer to prevent overfitting. Finally, the battery life prediction is output through a fully connected layer.

[0062] Furthermore, in this embodiment of the application, the predicted battery life is predicted using an LSTM model, and the content of the correction amount is as follows: Figure 3 As shown, it mainly includes: Step S301: Determine the model input and output.

[0063] In this embodiment, the wireless charging system can use time-series data acquired over a period of time (such as one month, which is not specifically limited in this application) such as charging frequency, charging power, battery temperature and capacity decay rate as input to the model, and use the corresponding predicted battery life as the output of the model.

[0064] Step S302: Construct the LSTM model.

[0065] In this embodiment, the LSTM model adopts a two-layer long short-term memory network architecture. The network structure includes two LSTM layers and a Dropout layer to prevent overfitting. Finally, the battery life prediction is output through a fully connected layer.

[0066] Step S303: Train the LSTM model to determine the battery life prediction model.

[0067] In this embodiment, the LSTM model can be pre-trained using a publicly available battery dataset. The battery sample consists of 168 18650 lithium batteries, comprising approximately 5000 complete charge-discharge cycles. Each cycle records parameters such as voltage, current, battery temperature, and capacity. The dataset is divided into a training set (70%), a validation set (15%), and a test set (15%). The input feature parameters are normalized to a mean of 0 and a variance of 1. Using mean squared error as the loss function and Adam as the optimizer, the training process ultimately yields the time-series mapping relationship between different charging parameters (such as charging frequency, charging power, and battery temperature) and battery capacity decay. Furthermore, in practical applications, this embodiment can employ a sliding window mechanism to obtain the latest operating parameters in real time. After a set number of charging cycles, the model is incrementally updated using the newly accumulated data to maintain prediction accuracy.

[0068] Furthermore, embodiments of this application can utilize historical operating parameters to perform online predictions on models trained on publicly available battery datasets, thereby achieving dynamic assessment of battery health status, ensuring that the prediction accuracy of the LSTM model is greater than a preset threshold, and obtaining a battery life prediction model.

[0069] Step S304: Utilize the battery life prediction model to output the predicted battery life.

[0070] In this application embodiment, a battery life prediction model with a prediction accuracy greater than a preset threshold can be used to dynamically assess the battery health status and determine the predicted battery life.

[0071] Step S305: Determine the corresponding correction amount.

[0072] In this embodiment, the correction amount of the target operating parameter in the current operating parameters can be determined in reverse based on the battery's predicted lifespan.

[0073] This application embodiment obtains an LSTM battery life prediction model that meets the accuracy requirements by training based on the historical operating parameters of the wireless charging system, and determines the parameter correction amount based on the output battery prediction life. This can achieve deep coupling between the charging control strategy and the battery health status, effectively delaying battery aging while ensuring charging efficiency, and improving the system's full life cycle performance and reliability.

[0074] Optionally, in one embodiment of this application, determining the correction amount of the target operating parameter in the current operating parameters based on at least one control reference factor includes: obtaining the energy transmission efficiency and electromagnetic interference cost of the vehicle and surrounding vehicles based on the target operating parameters; determining the revenue function based on the energy transmission efficiency and electromagnetic interference cost; determining the multi-vehicle collaborative revenue based on the revenue function; and determining the correction amount based on the multi-vehicle collaborative revenue.

[0075] It is understood that, in the embodiments of this application, "surrounding vehicle" can be understood as a vehicle located around this vehicle, also within the wireless charging area or adjacent to the charging parking space, for example, a circular area with a radius of 5-15m centered on this vehicle. The specific value of the radius can be dynamically determined by the electromagnetic interference attenuation distance and the effective communication range. This application does not impose specific restrictions. For example, the radius can be increased when the interference is strong or the vehicles are dense.

[0076] Electromagnetic interference cost can be understood as the quantified cost of the negative impacts on surrounding vehicles, electronic devices, living organisms, or power grids caused by electromagnetic radiation or harmonics generated during the operation of a wireless charging system.

[0077] The revenue function is a mathematical expression that takes the energy transfer efficiency of the vehicle and surrounding vehicles, as well as the electromagnetic interference cost, as input variables. It quantifies the overall benefit obtained by the system under a certain cooperative control strategy. Specifically, when multiple vehicles charge simultaneously, the electromagnetic fields generated by adjacent vehicles interfere with each other, leading to energy waste. In this case, coordinated optimization of power allocation is needed to reduce interference and improve overall energy efficiency. The expression of the revenue function can be, but is not limited to, the following: , in, This indicates that under a given power strategy, this vehicle The higher the profit value, the better for this vehicle. The better the power selection; , The balancing coefficient is used to weigh the weights of energy transfer efficiency and electromagnetic interference costs in the payoff function. , This indicates that in the current scenario, the weight of energy transmission efficiency is slightly higher than that of electromagnetic interference cost, and its value can be dynamically adjusted according to the scenario: it increases when the area is open and there are few vehicles. ,reduce Prioritize charging efficiency; reduce efficiency in dense charging scenarios. ,improve To prioritize the suppression of electromagnetic interference, the specific value can be set by those skilled in the art according to the actual situation, and this application does not impose specific restrictions; This vehicle The energy transfer efficiency function reflects the effective energy transfer level during charging, and its value depends on its own transmission power. ,in, Typically, the change with increasing transmit power is non-linear (e.g., it increases first and then saturates, or there is an optimal efficiency point; this application does not impose specific limitations). This vehicle Received from The summation of electromagnetic interference from all surrounding vehicles (excluding itself) is represented by the summation symbol, which indicates that the interference from all surrounding vehicles (excluding itself) is added together to form the total electromagnetic interference of this vehicle. The total cost of disruption that must be borne; Indicates Zhou Che In power The following is a description of the vehicle. The amount of interference generated is typically related to the distance between the two vehicles, the transmission power, and the electromagnetic attenuation characteristics. Additionally, This vehicle The positive benefits gained from its own charging efficiency encourage improvements in transmission efficiency; This indicates the negative cost of electromagnetic interference caused by this vehicle to surrounding vehicles, and it aims to suppress excessive power increases in the vehicle to avoid interfering with surrounding vehicles.

[0078] Multi-vehicle cooperative benefits refer to the optimization of overall benefits by coordinating the operating parameters of each vehicle (such as transmission power, power distribution, charging start and stop times) under the condition of interaction between the vehicle and at least one surrounding vehicle, thereby achieving higher overall efficiency or lower electromagnetic interference costs.

[0079] In some embodiments, the present application embodiments can obtain the energy transmission efficiency and electromagnetic interference cost of the vehicle and surrounding vehicles in real time based on the target operating parameters, and construct a corresponding revenue function based on the energy transmission efficiency and electromagnetic interference cost. Then, the revenue function is used to calculate the corresponding multi-vehicle collaborative revenue, thereby determining the correction amount of transmission power, power allocation, charging start and stop time, etc.

[0080] For example, embodiments of this application may employ a distributed game theory algorithm, where the charging vehicle communicates only with the surrounding vehicles to perform local interactions and strategy adjustments, coordinate the power allocation of the surrounding vehicles, minimize electromagnetic interference costs based on EMI (Electromagnetic Interference) modeling and pre-training, and achieve multi-vehicle cooperative control in dynamic environments.

[0081] The specific algorithm flow is as follows: First, each vehicle currently charging is defined as a game participant, and the transmission power adjustment range of each vehicle constitutes its strategy space. A payoff function that comprehensively considers energy transmission efficiency and electromagnetic interference costs is constructed. During the iteration process, each vehicle communicates only with surrounding vehicles to obtain their current power strategy. Based on local information, it calculates its own payoff value under the current candidate power and selects the power that maximizes the payoff as the new strategy (such as the vehicle's current transmission power, power adjustment range, etc., which are not specifically limited in this application). This process is repeated until the power adjustment of all vehicles is less than a preset threshold. At this point, the system reaches an equilibrium state and outputs a set of multi-vehicle collaborative payoffs that optimize the overall payoff, minimizing electromagnetic interference while ensuring charging efficiency. The preset threshold can be set by those skilled in the art according to actual conditions, and is not specifically limited in this application.

[0082] It can be understood that in this embodiment of the application, each vehicle that is charging is defined as a game participant, and its transmission power adjustment range is the strategy space. The transmission power, power allocation, charging start and stop times of each vehicle are obtained through local communication between vehicles. Based on the payoff function that comprehensively considers energy transmission efficiency and electromagnetic interference costs, the power value that maximizes its own payoff is iteratively selected, and a stable multi-vehicle collaborative payoff is output.

[0083] This application embodiment constructs a benefit function by obtaining the energy transmission efficiency and electromagnetic interference cost of the vehicle and surrounding vehicles, determines the multi-vehicle collaborative benefit, and calculates the parameter correction amount accordingly. This enables collaborative optimization control in multi-vehicle wireless charging scenarios, effectively avoids electromagnetic interference, improves overall energy transmission efficiency, and maximizes the comprehensive benefits of multi-vehicle collaborative charging.

[0084] Optionally, in one embodiment of this application, determining the correction amount of the corresponding target operating parameter in the current operating parameters based on at least one control reference factor includes: obtaining the corresponding road surface material information based on the target operating parameter; determining the transmission compensation coefficient and the target charging mode based on the road surface material information; calculating the road surface charging performance based on the transmission compensation coefficient and the target charging mode; and determining the correction amount based on the road surface charging performance.

[0085] It is understood that, in this embodiment, road surface material information refers to the physical and electromagnetic properties of the road surface or paving material traversed between the transmitting and receiving coils in the wireless charging system. The road surface material may include, but is not limited to, asphalt / concrete, metal / steel plates, wet / slippery surfaces, paving bricks / stone, sand / gravel, etc., and this application does not impose specific limitations. Different materials have different relative permeability, dielectric constant, conductivity, and thickness, thereby affecting the propagation loss, reflection, and refraction behavior of electromagnetic fields in the road surface. Therefore, this embodiment can determine the corresponding transmission compensation coefficient, i.e., the coil spacing compensation coefficient, through the road surface material information, as shown in Table 1. Table 1 is a schematic table of material compensation parameters for different road surface materials and transmission compensation coefficients according to an embodiment of this application.

[0086] Table 1

[0087] In some embodiments, the present application embodiments may first obtain the road surface material information corresponding to the wireless charging system, then determine the transmission compensation coefficient and target charging mode based on the road surface material information, thereby calculating the road surface charging performance based on the transmission compensation coefficient and target charging mode, and further determining the corresponding correction amount based on the obtained road surface charging performance.

[0088] It should be noted that the embodiments of this application can output probability distribution values ​​corresponding to different road surface materials by using a lightweight convolutional neural network. This lightweight convolutional neural network sequentially includes a convolutional layer, a pooling layer, a flattening layer, a fully connected layer, a dropout layer, and an output layer, as shown in Table 2. Table 2 is a schematic diagram of the structure of a lightweight convolutional neural network provided according to an embodiment of this application.

[0089] Table 2

[0090] As shown in Table 2, the lightweight convolutional neural network in this embodiment has the following characteristics: The first layer is a convolutional layer with a 3×3 kernel, 32 channels, a stride of 1, and ReLU activation function, resulting in an output size of 128×128×32; the second layer is a pooling layer with 2×2 max pooling and a stride of 2, resulting in an output size of 64×64×32; the third layer is a convolutional layer with a 3×3 kernel, 64 channels, a stride of 1, and ReLU activation function, resulting in an output size of 64×64×64; the fourth layer is a pooling layer with 2×2 max pooling and a stride of 2, resulting in an output size of 32×32×64; and the fifth layer is a convolutional layer with a 3×3 kernel and a number of channels... The first layer has 128 neurons with a stride of 1 and uses ReLU activation, resulting in an output size of 32×32×128. The sixth layer is a pooling layer with 2×2 max pooling and a stride of 2, resulting in an output size of 16×16×128. The seventh layer is a flattening layer that flattens the feature map into a one-dimensional feature vector, resulting in an output dimension of 32768. The eighth layer is a fully connected layer with 64 neurons, using ReLU activation, resulting in an output dimension of 64. The ninth layer is a dropout layer with a dropout rate of 0.5 to suppress overfitting, maintaining an output dimension of 64. The tenth layer is the output layer with 3 neurons, using Softmax activation, resulting in an output dimension of 3, used to achieve three-class classification output.

[0091] Furthermore, in this embodiment, the input to the lightweight convolutional neural network is a road surface feature map, such as a road surface feature map fused from radar, camera, and metal detector data, or a road surface feature map obtained through other methods. This application does not impose specific limitations on this method. The output is the probability distribution values ​​of different road surface materials. By collecting sensor data on various road surface materials (e.g., 500 sets each of asphalt, concrete, and metal plates; this application does not impose specific limitations on this method), and after labeling, a classification dataset is constructed. The lightweight convolutional neural network is trained end-to-end using the cross-entropy loss function and the Adam optimizer until the training loss of the lightweight convolutional neural network meets the preset loss condition. The preset loss condition can be set by those skilled in the art according to the actual situation; this application does not impose specific limitations on this method.

[0092] For example, in this application embodiment, a Kalman filter algorithm can be used to fuse the point cloud image projected from the radar point cloud onto the image plane with the RGB image from the camera to obtain a fused road surface feature map, improving the accuracy and robustness of environmental perception. The fused road surface feature map is then input into a pre-trained lightweight convolutional neural network for road surface material identification, obtaining probability distribution values ​​for different road surface materials (such as asphalt, concrete, metal plates, etc., which are not specifically limited in this application). If the probability distribution value is greater than a preset probability value, it is determined to be asphalt, concrete, metal plates, etc., which are not specifically limited in this application, thereby determining the road surface material information. The preset probability value can be set by those skilled in the art according to actual conditions, and is not specifically limited in this application.

[0093] Furthermore, in this embodiment, the target charging mode can be automatically switched according to the road surface material information: if the road surface is metal (such as metal plate / steel plate, waterlogged / slippery road surface, etc.), the target charging mode is determined to be a high-frequency charging mode (such as high-frequency suppression mode, high-frequency compensation mode, etc.), and the coil spacing is reduced to suppress the metal eddy current effect; if the road surface is non-metallic (such as asphalt / concrete, paving brick / stone, sand / gravel, etc.), the target charging mode is determined to be a low-frequency charging mode (such as low-frequency penetration mode, low-frequency penetration mode, etc.), and the coil spacing is increased to enhance penetration. In conjunction with Table 1, the compensation coefficient of the coil spacing monitored in real time is finely adjusted to ensure that the optimal road surface charging performance can be maintained under different road surface materials, thereby determining the corresponding correction amount for coil spacing, charging model, etc.

[0094] This application embodiment determines the coil spacing compensation coefficient by obtaining road surface material information, calculates the road surface charging performance, and determines the parameter correction amount accordingly. This enables the wireless charging system to dynamically adapt to different road surface conditions, effectively compensates for energy loss caused by the road surface, and improves energy transmission efficiency and system stability in complex environments.

[0095] In step S103, the current operating parameters are corrected using the correction amount to obtain the actual operating parameters of the wireless charging system, and the wireless charging system is controlled to charge the power battery according to the actual operating parameters.

[0096] In some embodiments, the present application embodiments can use correction amounts to correct the current operating parameters, thereby obtaining the actual operating parameters of the wireless charging system, and control the wireless charging system to charge the power battery according to the actual operating parameters.

[0097] For example, in this embodiment of the application, when the state of charge is detected to be >80% and the battery temperature is >45°C, the charging power is automatically reduced to 60% of the rated value; in rainy or snowy weather, the charging frequency is adjusted from 85kHz to 100kHz to compensate for energy loss according to the change in road surface material; when multiple vehicles are charging, 80% of the power is allocated to vehicles with a state of charge of <20%, and the remaining vehicles share 20% of the power.

[0098] The working principle of the energy-saving charging method for vehicle power batteries proposed in this application will be introduced below with reference to a specific embodiment.

[0099] in, Figure 4 This is a flowchart illustrating the working principle of a vehicle power battery charging energy-saving method according to an embodiment of this application.

[0100] Step S401: Multi-source data acquisition unit.

[0101] In this application embodiment, the battery status, such as state of charge, battery temperature, internal resistance, etc., can be obtained in real time using a multi-source data acquisition unit, and this application does not impose specific limitations; vehicle coil information, such as coil spacing and coil tilt angle, etc., this application does not impose specific limitations; road surface material information and other multi-source data, and then the current operating parameters of the wireless charging system can be determined based on the multi-source data.

[0102] Step S402: Central Computing Unit.

[0103] The central computing unit in this embodiment includes a parameter optimization module, a battery health prediction module, a multi-vehicle collaborative control module, and an environmental adaptation module.

[0104] The parameter optimization module employs a particle swarm optimization algorithm, using a weighted value of energy transfer efficiency and system stability as the fitness function for optimization. This determines the target performance indicators and dynamically adjusts the charging frequency, transmission power, coil spacing, and coil tilt angle of the wireless charging system based on these indicators, thereby determining the corresponding correction amounts.

[0105] The battery health prediction module uses an LSTM model to process time-series data on charging frequency, transmission power, and battery temperature to predict battery life. Based on the predicted battery life, it determines the correction amounts for the wireless charging system's charging frequency, charging power, and battery temperature.

[0106] The multi-vehicle cooperative control module adopts a distributed game theory algorithm to optimize power allocation to minimize electromagnetic interference through local information interaction between vehicles, determine the optimal multi-vehicle cooperative benefits, and then determine the correction amount for transmission power, power allocation, charging start and stop times, etc.

[0107] The environment adaptive module uses a lightweight convolutional neural network to determine the road surface material information. Based on the road surface material information, it automatically switches to the target charging mode. Combined with Table 1, it fine-tunes the compensation coefficient of the real-time monitored coil spacing to ensure that the optimal road charging performance can be maintained under different road surface materials. Then, based on the road charging performance, it determines the correction amount of the corresponding coil spacing and charging mode.

[0108] Step S403: Dynamic adjustment and optimization.

[0109] In this embodiment, the correction amount of the corresponding target operating parameters can be dynamically generated based on the target performance index, battery predicted life, multi-vehicle cooperative benefits and road charging performance. The correction amount is then used to correct the current operating parameters to obtain the actual operating parameters of the wireless charging system, thereby controlling the wireless charging system to charge the power battery.

[0110] For example, in this embodiment of the application, after the vehicle is parked in the charging space, the LiDAR scan generates three-dimensional point cloud data of the parking space. The central computing unit retrieves the historical operating parameters of the power battery. The A core of the state of charge chip, through the integrated flash memory module, uses a file system (such as LittleFS (Little File System, a lightweight file system, which is not specifically limited in this application) to store the historical operating parameters of the power battery, such as charging frequency, charging power, battery temperature, and capacity decay rate, in a time-series manner. The battery management system algorithm running on the A core collects the current state of charge in real time, quickly retrieves historical operating parameters through memory mapping technology, and analyzes the battery health trend by combining Kalman filtering and LSTM model to achieve closed-loop data management. The storage architecture supports power failure protection and data compression, ensuring 10 years of data traceability. Under standard NEDC (New European Driving Cycle) conditions, the system's average charging efficiency is improved by 12.7% (compared to traditional fixed-parameter systems); battery cycle life is extended by approximately 35%, and the capacity degradation rate is reduced from 2.1% / year to 1.4% / year; electromagnetic interference is reduced by 40% in multi-vehicle collaborative scenarios, and the charging power fluctuation of adjacent vehicles is controlled within ±5%.

[0111] According to the energy-saving charging method for vehicle power batteries proposed in this application, the current operating parameters of the wireless charging system charging the power battery can be obtained first, and control reference factors can be determined. Then, based on the corresponding control reference factors, a correction amount can be determined, and the current operating parameters can be corrected using the correction amount to obtain the actual operating parameters. This allows the wireless charging system to be controlled to charge the power battery. By determining the control reference factors, calculating the correction amount, and correcting the operating parameters, the adaptive adjustment of the operating parameters of the wireless charging system can be achieved, effectively improving the system's energy transmission efficiency, reducing energy loss and electromagnetic interference, while protecting battery health and extending the lifespan of the power battery. This solves the technical problems in related technologies, such as: statically configured charging parameters that cannot be adaptively adjusted according to changes in battery state of charge, temperature, road surface material, electromagnetic interference, etc.; fixed coil spacing and angle of the magnetic coupling mechanism, resulting in actual energy transmission efficiency significantly lower than the design nominal value; electromagnetic field interference when multiple vehicles are wirelessly charged simultaneously, causing additional energy loss; and accelerated aging of battery electrode materials and damage to battery health under high temperature or high current charging conditions.

[0112] Next, referring to the accompanying drawings, a charging and energy-saving device for a vehicle power battery according to an embodiment of this application is described.

[0113] Figure 5 This is a block diagram of a charging and energy-saving device for a vehicle power battery provided according to an embodiment of this application.

[0114] like Figure 5 As shown, the charging and energy-saving device 10 for the vehicle's power battery includes: a first determining module 100, a second determining module 200, and a control module 300.

[0115] The first determining module 100 is used to acquire the current operating parameters of the wireless charging system for charging the power battery, and to determine at least one control reference factor of the wireless charging system.

[0116] The second determining module 200 is used to determine the correction amount of the corresponding target operating parameter in the current operating parameters based on at least one control reference factor.

[0117] The control module 300 is used to correct the current operating parameters using the correction amount to obtain the actual operating parameters of the wireless charging system, and to control the wireless charging system to charge the power battery according to the actual operating parameters.

[0118] Optionally, in one embodiment of this application, the first determining module 100 includes: a first acquiring unit and a first determining unit.

[0119] The first acquisition unit is used to acquire the target performance indicators of the wireless charging system, the predicted battery life, the benefits of multi-vehicle collaboration, and the road charging performance.

[0120] The first determining unit is used to determine at least one control reference factor based on the target performance index, battery predicted life, multi-vehicle cooperative benefits, and road charging performance.

[0121] Optionally, in one embodiment of this application, the second determining module 200 includes: a second acquiring unit, a constructing unit, a second determining unit, and a third determining unit.

[0122] The second acquisition unit is used to randomly generate at least one set of particles based on the target running parameters, and to acquire the boundary constraints corresponding to at least one set of particles.

[0123] The building block is used to construct a fitness function based on the energy transfer efficiency and system stability of the wireless charging system.

[0124] The second determining unit is used to determine the target performance index based on the fitness function and boundary constraints.

[0125] The third determining unit is used to determine the correction amount based on the target performance index.

[0126] Optionally, in one embodiment of this application, the second determining module 200 includes: a third acquiring unit, a fourth determining unit, an output unit, and a fifth determining unit.

[0127] The third acquisition unit is used to acquire historical operating parameters of the wireless charging system.

[0128] The fourth determining unit is used to determine the model parameters of the LSTM model based on historical operating parameters.

[0129] The output unit is used to train the LSTM model based on the model parameters and historical running parameters until the prediction accuracy of the LSTM model is greater than a preset threshold, thereby obtaining the battery life prediction model and outputting the predicted battery life.

[0130] The fifth determining unit is used to determine the correction amount based on the predicted battery life.

[0131] Optionally, in one embodiment of this application, the second determining module 200 includes: a fourth obtaining unit, a sixth determining unit, a seventh determining unit, and an eighth determining unit.

[0132] The fourth acquisition unit is used to acquire the energy transmission efficiency and electromagnetic interference cost of the vehicle and surrounding vehicles based on the target operating parameters.

[0133] The sixth determining unit is used to determine the revenue function based on energy transmission efficiency and electromagnetic interference cost.

[0134] The seventh determining unit is used to determine the multi-vehicle collaborative benefits based on the benefit function.

[0135] The eighth determining unit is used to determine the correction amount based on the benefits of multi-vehicle collaboration.

[0136] Optionally, in one embodiment of this application, the second determining module 200 includes: a fifth acquiring unit, a ninth determining unit, and a calculation unit.

[0137] The fifth acquisition unit is used to acquire the corresponding road surface material information based on the target operating parameters.

[0138] The ninth determining unit is used to determine the transmission compensation coefficient and the target charging mode based on the road surface material information.

[0139] The calculation unit is used to calculate the road surface charging performance based on the transmission compensation coefficient and the target charging mode.

[0140] The tenth determining unit is used to determine the correction amount based on the road surface charging performance.

[0141] It should be noted that the explanation of the above-mentioned embodiment of the charging and energy-saving method for vehicle power batteries also applies to the charging and energy-saving device for vehicle power batteries in this embodiment, and will not be repeated here.

[0142] According to the vehicle power battery charging energy-saving device proposed in the embodiments of this application, the current operating parameters of the wireless charging system charging the power battery can be obtained first, and control reference factors can be determined. Then, based on the corresponding control reference factors, a correction amount can be determined, and the current operating parameters can be corrected using the correction amount to obtain the actual operating parameters. This allows the wireless charging system to be controlled to charge the power battery. By determining the control reference factors, calculating the correction amount, and correcting the operating parameters, the adaptive adjustment of the operating parameters of the wireless charging system can be achieved, effectively improving the system's energy transmission efficiency, reducing energy loss and electromagnetic interference, while protecting battery health and extending the service life of the power battery. This solves the technical problems in related technologies, such as: statically configured charging parameters that cannot be adaptively adjusted according to changes in battery state of charge, temperature, road surface material, electromagnetic interference, etc.; fixed coil spacing and angle of the magnetic coupling mechanism, resulting in actual energy transmission efficiency significantly lower than the design nominal value; electromagnetic field interference when multiple vehicles are wirelessly charged simultaneously, causing additional energy loss; and accelerated aging of battery electrode materials and damage to battery health under high temperature or high current charging conditions.

[0143] Figure 6 This is a schematic diagram of the structure of a vehicle according to an embodiment of this application. The vehicle may include: The memory 601, the processor 602, and the computer program stored on the memory 601 and capable of running on the processor 602.

[0144] When the processor 602 executes the program, it implements the energy-saving charging method for the vehicle power battery provided in the above embodiments.

[0145] Furthermore, the vehicle also includes: Communication interface 603 is used for communication between memory 601 and processor 602.

[0146] The memory 601 is used to store computer programs that can run on the processor 602.

[0147] The memory 601 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0148] If the memory 601, processor 602, and communication interface 603 are implemented independently, then the communication interface 603, memory 601, and processor 602 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0149] Optionally, in a specific implementation, if the memory 601, processor 602, and communication interface 603 are integrated on a single chip, then the memory 601, processor 602, and communication interface 603 can communicate with each other through an internal interface.

[0150] The processor 602 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0151] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described method for charging and saving energy of a vehicle power battery.

[0152] This application also provides a computer program product, including a computer program that, when executed, implements the above-described energy-saving charging method for a vehicle power battery.

[0153] The preferred embodiments of this application have been described in detail above with reference to the accompanying drawings. However, this application is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this application, various simple modifications can be made to the technical solution of this application, and these simple modifications all fall within the protection scope of this application.

[0154] It should also be noted that the various specific technical features described in the above embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, this application will not describe the various possible combinations separately.

[0155] Furthermore, various different implementations of this application can be combined in any way, as long as they do not violate the spirit of this application, they should also be regarded as the content disclosed in this application.

Claims

1. A method for energy-saving charging of a vehicle power battery, characterized in that, Includes the following steps: Obtain the current operating parameters of the wireless charging system for charging the power battery, and determine at least one control reference factor of the wireless charging system; Based on the at least one control reference factor, determine the correction amount of the corresponding target operating parameter in the current operating parameters; The current operating parameters are corrected using the correction amount to obtain the actual operating parameters of the wireless charging system, and the wireless charging system is controlled to charge the power battery according to the actual operating parameters.

2. The method according to claim 1, characterized in that, Determining at least one control reference factor for the wireless charging system includes: Obtain the target performance indicators, predicted battery life, multi-vehicle cooperative benefits, and road charging performance of the wireless charging system; The at least one control reference factor is determined based on the target performance index, the predicted battery life, the multi-vehicle collaborative benefits, and the road charging performance.

3. The method according to claim 2, characterized in that, Determining the correction amount for the corresponding target operating parameter in the current operating parameters based on the at least one control reference factor includes: Based on the target operating parameters, at least one set of particles is randomly generated, and the boundary constraints corresponding to the at least one set of particles are obtained; Based on the energy transmission efficiency and system stability of the wireless charging system, a fitness function is constructed. The target performance index is determined based on the fitness function and the boundary constraints; The correction amount is determined based on the target performance index.

4. The method according to claim 2, characterized in that, Determining the correction amount for the corresponding target operating parameter in the current operating parameters based on the at least one control reference factor includes: Obtain the historical operating parameters of the wireless charging system; Based on the historical operating parameters, the model parameters of the Long Short-Term Memory (LSTM) network model are determined. The LSTM model is trained based on the model parameters and the historical operating parameters until the prediction accuracy of the LSTM model is greater than a preset threshold, thereby obtaining a battery life prediction model and outputting the predicted battery life. The correction amount is determined based on the predicted battery life.

5. The method according to claim 2, characterized in that, Determining the correction amount for the corresponding target operating parameter in the current operating parameters based on the at least one control reference factor includes: Based on the target operating parameters, the energy transmission efficiency and electromagnetic interference cost of the vehicle and surrounding vehicles are obtained; Based on the energy transmission efficiency and the electromagnetic interference cost, determine the revenue function; The revenue from multi-vehicle collaboration is determined based on the revenue function. The correction amount is determined based on the benefits of multi-vehicle collaboration.

6. The method according to claim 2, characterized in that, Determining the correction amount for the corresponding target operating parameter in the current operating parameters based on the at least one control reference factor includes: Based on the target operating parameters, obtain the corresponding road surface material information; Based on the road surface material information, the transmission compensation coefficient and target charging mode are determined; The road surface charging performance is calculated based on the transmission compensation coefficient and the target charging mode; The correction amount is determined based on the road surface charging performance.

7. A charging and energy-saving device for a vehicle power battery, characterized in that, include: The first determining module is used to acquire the current operating parameters of the wireless charging system for charging the power battery, and to determine at least one control reference factor of the wireless charging system. The second determining module is used to determine the correction amount of the corresponding target operating parameter in the current operating parameters based on the at least one control reference factor; The control module is used to correct the current operating parameters using the correction amount to obtain the actual operating parameters of the wireless charging system, and to control the wireless charging system to charge the power battery according to the actual operating parameters.

8. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the energy-saving charging method for a vehicle power battery as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the energy-saving charging method for the vehicle power battery as described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program, which, when executed, is used to implement the energy-saving charging method for a vehicle power battery as described in any one of claims 1-6.

Images