Vehicle charging method, device, equipment, storage medium, program product and vehicle
By obtaining the operation information of new energy vehicle batteries and using machine learning models to adjust the charging mode, the problems of insufficient charging speed and battery protection in the existing technology are solved, and a more efficient and safe charging strategy is achieved, and battery life is extended.
Patent Information
- Application Number
- CN202411419621.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-11
- Publication Date
- 2024-11-26
AI Technical Summary
The existing charging strategies for new energy vehicles lack consideration of the actual situation of vehicle batteries, which leads to difficulty in improving the charging speed and insufficient battery protection.
By obtaining the current operating status of the vehicle battery, using machine learning models to predict the health status, and adjusting the charging mode according to the prediction results, to achieve the appropriate charging strategy of the battery and balance charging speed and protection.
It improves the charging speed and safety of the vehicle battery, extends the battery life, meets users' personalized charging needs, and protects the battery to the greatest extent.
Smart Images

Figure CN119017980A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of vehicle technology, and in particular to a vehicle charging method, device, equipment, storage medium, program product and vehicle. Background Art
[0002] At present, the charging strategy of new energy vehicles is generally to charge the vehicle battery based on a pre-set fixed charging strategy. For vehicle batteries in different life cycles, such as new batteries or batteries that have been used for a long time, the battery charging control process based on the fixed charging strategy is basically unchanged. The problem caused by this is that the charging process of the vehicle battery lacks consideration of the actual situation of the vehicle battery, resulting in the problem of difficulty in further improving the charging speed during the vehicle battery charging process or lack of protection for the vehicle battery. Summary of the invention
[0003] In view of this, the present invention provides a vehicle charging method, device, equipment, storage medium, program product and vehicle to solve the problem in the related art that it is difficult to increase the charging speed or protect the vehicle battery.
[0004] In a first aspect, the present invention provides a vehicle charging method, the method comprising:
[0005] Acquire first operating condition information of a vehicle battery in a current charging mode, where the first operating condition information is used to characterize a current operating condition of the vehicle battery, and the current charging mode is one of a plurality of preset charging modes;
[0006] Predicting second operating condition information using the first operating condition information, the second operating condition information being used as an evaluation indicator of a health status of a vehicle battery;
[0007] The current charging mode is adjusted according to the second operating condition information.
[0008] The present invention evaluates the health status of the vehicle battery through the current operating conditions of the vehicle battery under the current charging mode, and adjusts the current charging mode according to the evaluation results. It can be seen that the present invention uses the actual situation of the vehicle battery as an adjustment factor of the vehicle battery charging control strategy, thereby providing a suitable charging strategy for the vehicle battery in the current life cycle. Specifically, it can find a balance between protecting the vehicle battery and charging more electricity into the vehicle battery. Therefore, compared with the related art, the vehicle charging method provided by the present invention can take into account both battery protection and a suitable charging speed.
[0009] In an optional implementation, the first operating condition information includes a first current, a first state of charge, and a first temperature, and the second operating condition information includes a first voltage and a first cathode potential; and the second operating condition information is predicted using the first operating condition information, including:
[0010] Inputting the first operating condition information into a trained machine learning model to output second operating condition information through the machine learning model;
[0011] Among them, the machine learning model is obtained after training the battery model deployed on the vehicle, and the battery model is a mathematical simulation model of the vehicle battery.
[0012] The present invention can also train the machine learning model through the battery model deployed on the vehicle, so as to predict the first voltage and the first negative electrode potential according to the first current, the first state of charge and the first temperature through the trained machine learning model, thereby optimizing the charging strategy. It can be seen that the present invention can also optimize the specific charging scheme according to the actual battery condition of each vehicle by using the linkage of the battery model and the machine learning model, thereby greatly improving the safety while giving full play to the maximum charging capacity of the battery. Therefore, the present invention can also provide a vehicle charging method based on a battery model and machine learning.
[0013] In an optional implementation, before obtaining the first operating condition information of the vehicle battery in the current charging mode, the method further includes:
[0014] Inputting the third operating condition information into the battery model to output the fourth operating condition information through the battery model; the third operating condition information is historical operating condition information, the third operating condition information includes the second current, the second state of charge and the second temperature, and the fourth operating condition information includes the second voltage and the second negative electrode potential;
[0015] The third operating condition information and the fourth operating condition information are used to train the machine learning model to be trained to obtain a trained machine learning model deployed on the vehicle.
[0016] The present invention calculates the second current, the second state of charge and the second temperature in the historical operating condition information through a battery model, and outputs a second voltage and a second negative electrode potential, thereby training the machine learning model through the second current, the second state of charge, the second temperature, the second voltage and the second negative electrode potential, realizing the digital twin of the battery model and the machine learning model, thereby providing technical support for the machine model to predict the second operating condition information.
[0017] In an optional embodiment, the battery model is one or more of a simplified electrochemical model, a complete electrochemical model, and an equivalent circuit model.
[0018] The present invention can specifically simulate the vehicle battery by using at least one mathematical model among a simplified electrochemical model, a complete electrochemical model, and an equivalent circuit model, so as to simulate the working condition of the vehicle battery with high accuracy, thereby providing a basis for optimizing the vehicle battery charging strategy.
[0019] In an optional embodiment, the method further includes:
[0020] Performing online calibration on the battery model using the first current, the first state of charge, the first temperature, and the corresponding measured voltage and measured negative electrode potential;
[0021] The machine learning model is reinforced with the battery model after online calibration.
[0022] The present invention can also regularly calibrate the battery model online through the battery signal (first current, first state of charge, first temperature and corresponding measured voltage and measured negative electrode potential) at the vehicle end as the battery ages, so as to realize self-optimization of battery model parameters, and then realize the update and iteration of the battery model throughout its life cycle. The machine learning model also synchronously strengthens learning, thereby realizing the digital twin of the battery throughout its life cycle, and then realizing the monitoring of the battery health status and optimization of the charging strategy throughout its life cycle, greatly improving the safety of the vehicle battery. It can be seen that the present invention can also provide a full life cycle intelligent charging method based on electrochemical models and machine learning.
[0023] In an optional implementation, adjusting the current charging mode according to the second operating condition information includes:
[0024] If the second operating condition information indicates that the health state of the vehicle battery is an unsafe state, the current or voltage of the vehicle battery is reduced in the current charging mode.
[0025] The present invention can timely reduce the current or voltage of the vehicle battery upon identifying that the vehicle battery is about to be or is already in an unsafe state, thereby timely and effectively protecting the vehicle battery.
[0026] In an optional implementation, the plurality of preset charging modes include an extreme charging mode, an adaptive mode, and a custom mode, the extreme charging mode indicating a method of charging the vehicle battery according to the fastest charging strategy, the adaptive mode indicating a method of charging the vehicle battery according to a charging strategy determined based on historical charging big data, and the custom mode indicating a method of charging the vehicle battery according to a charging strategy determined based on a charging time set by a user; adjusting the current charging mode according to the second operating condition information includes:
[0027] If the second operating condition information indicates that the health state of the vehicle battery is an unsafe state, adjusting the current charging mode to a target charging mode;
[0028] The current charging mode is one of the extreme charging mode, the adaptive mode and the custom mode, the target charging mode is one of the adaptive mode and the custom mode, and the current charging mode is different from the target charging mode.
[0029] Based on the ultra-fast charging mode, adaptive mode and custom mode, the present invention provides a charging optimization method with a high degree of freedom and based on user habits. The multiple charging modes can protect the vehicle battery to the greatest extent and extend the service life of the vehicle battery while meeting the personalized charging needs of users. Moreover, the present invention can also realize the function of switching between the ultra-fast charging mode, adaptive mode and custom mode, thereby providing users with a more suitable charging strategy and further improving user satisfaction.
[0030] In an optional embodiment, the method further includes:
[0031] If the current charging mode or the target charging mode is a custom mode, determining whether the charging time set by the user in the custom mode is greater than the shortest charging time threshold;
[0032] If the charging time is less than or equal to the shortest charging time threshold, the custom mode is switched to the fast charging mode.
[0033] The present invention identifies and judges the charging time set by the user to ensure that the charging time set by the user is greater than the shortest time required to fully charge the vehicle battery in the extreme charging mode, so as to avoid battery safety problems that may be caused by excessive charging current, improve the safety of the vehicle charging process, and enhance user satisfaction.
[0034] In a second aspect, the present invention provides a vehicle charging device, the device comprising:
[0035] An information acquisition module, used to acquire first operating condition information of a vehicle battery in a current charging mode, the first operating condition information being used to characterize a current operating condition of the vehicle battery, the current charging mode being one of a plurality of preset charging modes;
[0036] An indicator prediction module, used to predict second operating condition information using the first operating condition information, where the second operating condition information is used as an evaluation indicator of the health status of the vehicle battery;
[0037] The mode adjustment module is used to adjust the current charging mode according to the second operating condition information.
[0038] In a third aspect, the present invention provides an electronic device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the vehicle charging method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.
[0039] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the vehicle charging method of the first aspect or any corresponding embodiment thereof.
[0040] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions, wherein the computer instructions are used to enable a computer to execute the vehicle charging method of the first aspect or any corresponding embodiment thereof.
[0041] In a sixth aspect, the present invention provides a vehicle, the vehicle comprising a vehicle controller, the vehicle controller being configured to execute the vehicle charging method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the related technologies, the drawings required for use in the specific embodiments or the related technical descriptions will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0043] Figure 1 4 is a flow chart of a vehicle charging method according to an embodiment of the present invention.
[0044] Figure 2 4 is a flow chart of another vehicle charging method according to an embodiment of the present invention.
[0045] Figure 3 4 is a flow chart of another vehicle charging method according to an embodiment of the present invention.
[0046] Figure 4 4 is a flow chart of yet another vehicle charging method according to an embodiment of the present invention.
[0047] Figure 5 Schematic diagram of the working principle of the vehicle charging method according to an embodiment of the present invention.
[0048] Figure 6 is a structural block diagram of a vehicle charging device according to an embodiment of the present invention.
[0049] Figure 7 It is a schematic diagram of the hardware structure of the electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0050] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
[0051] In the related art, the charging strategies of most new energy vehicles on the market are based on a pre-set charging MAP (i.e., a charging map, which is affected by temperature and state of charge). Due to the "thousands of vehicles with thousands of faces", this fixed charging MAP is difficult to bring into play the maximum charging capacity of the battery on each vehicle. Although improvements can be made on the basis of the fixed charging strategy, such as fast charging of the battery without lithium precipitation according to the actual situation of the vehicle battery, this method is still based on a fixed battery charging method and cannot meet the changing charging needs of the battery throughout its life cycle; or adaptive selection of fast charging control strategies for different users. Although this method can use different fast charging control strategies for different users, it is still limited to the preset fast charging control strategy library data and cannot bring into play the true level of the vehicle battery; or the charging speed of the vehicle battery is continuously optimized, but this method is difficult to effectively protect the vehicle battery and affects the battery life. In some cases, users do not necessarily need to charge the vehicle battery at the fastest charging speed all the time, but are likely to want to charge the vehicle battery gently in a relatively sufficient time.
[0052] According to an embodiment of the present invention, an embodiment of a vehicle charging method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0053] In this embodiment, a vehicle charging method is provided, which can be used in a BMS (Battery Management System). Figure 1 is a flow chart of a vehicle charging method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:
[0054] Step S101, obtaining first operating condition information of a vehicle battery in a current charging mode, where the first operating condition information is used to characterize a current operating condition of the vehicle battery, and the current charging mode is one of a plurality of preset charging modes.
[0055] The vehicle battery in this embodiment can be a new energy vehicle battery. The current charging mode is the charging strategy currently used to charge the vehicle battery. The user can select a preset charging mode as the current charging mode on the vehicle's large screen. The control instructions corresponding to the set current charging mode are sent to the BMS.
[0056] The first operating condition information is the operating condition information of the vehicle battery under the current charging mode, and the number of preset charging modes may be two or more.
[0057] Step S102: predicting second operating condition information using the first operating condition information, where the second operating condition information is used as an evaluation indicator of the health status of the vehicle battery.
[0058] Based on the working status information under the current charging mode, the present invention predicts the health status of the vehicle battery in the current life cycle, thereby achieving an accurate assessment of whether the current charging mode is reasonable.
[0059] Step S103: adjusting the current charging mode according to the second operating condition information.
[0060] Specifically, based on the health status of the vehicle battery being in an unsafe state, the current charging mode is adjusted, such as reducing the charging current, or the current charging mode can be replaced with other safer preset charging modes until the health status of the vehicle battery is in a safe state; and / or, based on the health status of the vehicle battery being in a safe state, the charging current can be appropriately increased according to actual conditions, and the charging current can be gradually increased (for example, increased by 1%) while maintaining the health status of the vehicle battery in a safe state, thereby effectively improving the charging speed under the premise of safe charging.
[0061] The vehicle charging method in this embodiment evaluates the health status of the vehicle battery through the current operating conditions of the vehicle battery under the current charging mode, and adjusts the current charging mode according to the evaluation results. It can be seen that the present invention uses the actual situation of the vehicle battery as an adjustment factor for the vehicle battery charging control strategy, thereby providing a suitable charging strategy for the vehicle battery in the current life cycle. Specifically, it can find a balance between protecting the vehicle battery and charging more electricity into the vehicle battery, thereby achieving the technical purpose of taking into account both the vehicle battery fast charging function and the vehicle battery protection function. Therefore, compared with conventional technical routes, the vehicle charging method provided by the present invention can take into account both battery protection and suitable charging speed.
[0062] In this embodiment, a vehicle charging method is provided, which can be used in a BMS (Battery Management System). Figure 2 is a flow chart of a vehicle charging method according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:
[0063] Step S201, obtaining first operating condition information of the vehicle battery in the current charging mode, the first operating condition information is used to characterize the current operating condition of the vehicle battery, and the current charging mode is one of multiple preset charging modes. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.
[0064] Next, the first operating condition information is used to predict the second operating condition information, and the second operating condition information is used as an evaluation indicator of the health status of the vehicle battery.
[0065] Specifically, the first operating condition information includes a first current, a first state of charge and a first temperature, and the second operating condition information includes a first voltage and a first negative electrode potential. The above process of using the first operating condition information to predict the second operating condition information may specifically include: step S202, inputting the first operating condition information into a trained machine learning model to output the second operating condition information through the machine learning model; wherein the machine learning model is obtained after training with a battery model deployed on the vehicle, and the battery model is a mathematical simulation model of the vehicle battery.
[0066] Among them, the first current is the current of the vehicle battery in the current charging mode, the first state of charge is the state of charge (SOC, State Of Charge) of the vehicle battery in the current charging mode, the first temperature is the temperature of the vehicle battery in the current charging mode, the first voltage is the predicted voltage of the vehicle battery in the current charging mode, and the first negative electrode potential is the negative electrode potential of the vehicle battery in the current charging mode. The battery model is deployed on the actual vehicle after offline calibration. The battery model can be specifically deployed on the BMS, and the machine learning model can be specifically deployed on the vehicle-mounted central computing platform.
[0067] The machine learning model of this embodiment is used to realize input current excitation, output voltage and negative electrode potential information at a specific temperature and SOC.
[0068] It should be understood that the battery model and machine learning model of the present invention are both used to simulate real batteries. The machine learning model is a digital twin of the battery model, but the machine learning model has a faster calculation speed and is used to simulate the working conditions of an equivalent real battery after the battery model and the machine learning model reach a certain maturity.
[0069] This embodiment can also train the machine learning model through the battery model deployed on the vehicle, so that the trained machine learning model can predict the first voltage and the first negative electrode potential according to the first current, the first state of charge and the first temperature, and then optimize the charging strategy. It can be seen that the present invention can also optimize the specific charging scheme according to the actual battery condition of each vehicle by using the linkage of the battery model and the machine learning model, greatly improving the safety while giving full play to the maximum charging capacity of the battery. Therefore, the embodiment of the present invention can also provide a vehicle charging method based on battery model and machine learning.
[0070] In some optional embodiments, the battery model is one or more of a simplified electrochemical model, a complete electrochemical model, and an equivalent circuit model.
[0071] Specifically, the machine learning model may be, for example, a random forest regression model or a support vector regression model. The machine learning model in this embodiment has a faster calculation speed than the battery model. Moreover, the battery model can simulate the battery performance while inputting a large amount of training data into the machine learning model, so that the machine learning model can quickly optimize the optimal charging path. For example, the current current can be judged by the machine learning model. If it is less than the current threshold, it means it is safe, and the current current can be allowed to act on the vehicle battery.
[0072] Compared with conventional technologies, this embodiment can establish a simplified electrochemical model and machine learning model of the entire life cycle of the battery to simulate the vehicle battery, thereby accurately simulating the working conditions of the vehicle battery and providing a basis for optimizing the vehicle battery charging strategy.
[0073] like Figure 5 As shown in the figure, the charging control module, the simplified electrochemical module that has been calibrated offline, and the machine learning model can exchange information with each other. The charging control module collects current, SOC and temperature. The BMS obtains the current, SOC and temperature and inputs them into the simplified electrochemical module for simulation (and the simplified electrochemical model can be calibrated online as the battery ages). The simplified electrochemical module passes the current, SOC and temperature (i.e., historical data) to the machine learning model for training. The machine learning module feeds back its own calculation results (predicted voltage / negative electrode potential) to the charging control module through the current excitation of the charging control module, evaluates the charging strategy, and forms the optimal closed-loop management of the charging current.
[0074] Step S203: Adjust the current charging mode according to the second operating condition information. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.
[0075] In some optional implementations, after step S203, the vehicle charging method further includes step a1 and step a2.
[0076] Step a1, calibrating the battery model online using the first current, the first state of charge, the first temperature and the corresponding measured voltage and measured negative electrode potential.
[0077] Among them, this embodiment performs online calibration on the battery model according to a preset period, and the preset period is, for example, 6 months, 3 months or 1 month, etc. The specific duration of the preset period can be selected according to actual conditions, and this embodiment does not limit this.
[0078] Specifically, as the vehicle battery is used for a longer time, it will gradually age, and the difference between the offline calibrated battery model and the aged vehicle battery will increase. This embodiment overcomes this problem by performing online calibration on the battery model deployed on the vehicle.
[0079] Step a2: Strengthen the machine learning model through the online calibrated battery model.
[0080] This embodiment can also use the battery model after online calibration to perform intensive training on the machine learning model, so that after the battery ages, the machine learning model can still accurately predict the current first voltage and first negative electrode potential.
[0081] Therefore, this embodiment can also regularly calibrate the battery model online through the battery signal (first current, first state of charge, first temperature and corresponding measured voltage and measured negative electrode potential) on the vehicle side as the battery ages, so as to achieve self-optimization of battery model parameters, and then achieve update and iteration of the battery model throughout its life cycle. The machine learning model also synchronously strengthens learning, thereby realizing the digital twin of the battery throughout its life cycle, monitoring the battery health status throughout its life cycle and optimizing the charging strategy, greatly improving the safety of the vehicle battery. It can be seen that the present invention can also provide a full life cycle intelligent charging method based on electrochemical models and machine learning models.
[0082] In this embodiment, a vehicle charging method is provided, which can be used in a BMS (Battery Management System). Figure 3 is a flow chart of a vehicle charging method according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:
[0083] Step S301, input the third operating condition information into the battery model to output the fourth operating condition information through the battery model; the third operating condition information is historical operating condition information, the third operating condition information includes a second current, a second state of charge and a second temperature, and the fourth operating condition information includes a second voltage and a second negative electrode potential.
[0084] Among them, the second current is the historical current of the vehicle battery, the second state of charge is the historical state of charge (SOC, State Of Charge) of the vehicle battery corresponding to the historical current, the second temperature is the historical temperature of the vehicle battery corresponding to the historical current, the second voltage is the predicted voltage of the vehicle battery corresponding to the historical current, the second temperature is the predicted temperature of the vehicle battery corresponding to the historical current, and the battery model after offline calibration is deployed on the vehicle.
[0085] Specifically, the battery model is used to monitor the second voltage and the second negative electrode potential when the vehicle battery is charged.
[0086] Step S302: Use the third operating condition information and the fourth operating condition information to train the machine learning model to be trained to obtain a trained machine learning model deployed on the vehicle.
[0087] In this embodiment, the machine learning model is trained by the second current, the second state of charge, the second temperature, the second voltage and the second cathode potential. The input of the trained machine learning model is the second current, the second state of charge and the second temperature, and the output is the second voltage and the second cathode potential.
[0088] The machine learning model of this embodiment can be deployed on the on-board central computing platform. This embodiment realizes the training of the machine learning model using historical data in the above manner, and specifically calculates the second current, second state of charge and second temperature in the historical operating condition information through the battery model, and outputs the second voltage and the second negative electrode potential, thereby training the machine learning model through the second current, second state of charge, second temperature, second voltage and second negative electrode potential, realizing the digital twin of the battery model and the machine learning model, thereby providing technical support for the machine model to predict the second operating condition information.
[0089] Step S303, obtaining first operating condition information of the vehicle battery in the current charging mode, the first operating condition information is used to characterize the current operating condition of the vehicle battery, and the current charging mode is one of multiple preset charging modes. Figure 2 Step S201 of the illustrated embodiment will not be described in detail here.
[0090] Step S304: Use the first operating condition information to predict the second operating condition information, and the second operating condition information is used as an evaluation indicator of the health status of the vehicle battery. Figure 2 Step S202 of the illustrated embodiment will not be described in detail here.
[0091] Step S305: Adjust the current charging mode according to the second operating condition information. Figure 2 Step S203 of the illustrated embodiment will not be described in detail here.
[0092] In this embodiment, a vehicle charging method is provided, which can be used in a BMS (Battery Management System). Figure 4 is a flow chart of a vehicle charging method according to an embodiment of the present invention. Figure 4 As shown, the process includes the following steps:
[0093] Step S401, obtaining first operating condition information of the vehicle battery in the current charging mode, the first operating condition information is used to characterize the current operating condition of the vehicle battery, and the current charging mode is one of multiple preset charging modes. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.
[0094] Step S402: Use the first operating condition information to predict the second operating condition information, where the second operating condition information is used as an evaluation indicator of the health status of the vehicle battery. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.
[0095] Step S403: adjusting the current charging mode according to the second operating condition information.
[0096] Specifically, the above step S403 includes: if the second operating condition information indicates that the health state of the vehicle battery is an unsafe state, reducing the current or voltage of the vehicle battery in the current charging mode.
[0097] If the second operating condition information indicates that the health state of the vehicle battery is a safe state, the vehicle battery is directly charged using the current charging mode.
[0098] Specifically, when the health status of the vehicle battery is in an unsafe state, taking reducing the current of the vehicle battery as an example, the current of the vehicle battery can be reduced by a preset percentage first, such as 5%, and then the health status is evaluated again. If it is in a safe state, the battery is charged according to the current current. If it is still in an unsafe state, the current of the vehicle battery is reduced by the preset percentage again until the health status is made safe.
[0099] The present invention can timely reduce the current or voltage of the vehicle battery upon identifying that the vehicle battery is about to be or is already in an unsafe state, thereby timely and effectively protecting the vehicle battery.
[0100] Combination Figure 5 As shown, in some optional embodiments, multiple preset charging modes include an extreme charging mode, an adaptive mode, and a custom mode. The extreme charging mode represents a method of charging the vehicle battery according to the fastest charging strategy, the adaptive mode represents a method of charging the vehicle battery according to a charging strategy determined based on historical charging big data, and the custom mode represents a method of charging the vehicle battery according to a charging strategy determined based on a charging time set by a user.
[0101] Among them, in the extreme charging mode, the maximum charging capacity of the vehicle battery in each stage of the entire life cycle can be brought into play, and the battery replenishment can be completed in the shortest time. The extreme charging mode can be the fastest charging strategy optimized by the machine learning model; the adaptive mode is specifically the AI (Artificial Intelligence) adaptive mode. In the adaptive mode, taking the historical charging big data as the statistical result of the past stay time of the charging location as an example, the charging location includes but is not limited to the workplace, the residence, etc., and the charging time covering most situations (for example, 80% of the charging times at the target charging location) is used for charging, and the stay time of the preset number of times (for example, 30 times) at the target charging location in the past is sorted from large to small or from small to large, and the stay time (for example, 1 hour) with a coverage reaching a threshold (for example, ≥30×80%=24 times) is selected. Then, within 1 hour at the target charging location, the vehicle battery is charged with as much electricity as possible or even fully charged, thereby seeking a balance between protecting the battery and charging more electricity; in the custom mode, the user's need to set the charging time can be met.
[0102] Specifically, in response to the user's charging mode selection operation on the vehicle-mounted large screen, the charging control module in the vehicle control system generates a control instruction corresponding to the current charging mode, and sends the control instruction to the BMS and takes effect, for example, the current charging mode is operated by the BMS.
[0103] In the custom mode, the above control instructions also include the charging time set by the user, so that the BMS controls the charging process of the vehicle battery based on the charging time set by the user.
[0104] Based on the ultra-fast charging mode, adaptive mode and custom mode, the embodiment of the present invention provides a charging optimization method with a high degree of freedom and based on user habits. The multiple charging modes can protect the vehicle battery to the greatest extent and extend the service life of the vehicle battery while meeting the personalized charging needs of users. Moreover, the present invention can also realize the function of switching between the ultra-fast charging mode, adaptive mode and custom mode, thereby providing users with a more suitable charging strategy and further improving user satisfaction.
[0105] In some optional embodiments, the above step S403 includes: if the second operating condition information indicates that the health state of the vehicle battery is an unsafe state, the current charging mode is adjusted to the target charging mode; wherein, the current charging mode is one of the extreme charging mode, the adaptive mode and the custom mode, the target charging mode is one of the adaptive mode and the custom mode, and the current charging mode is different from the target charging mode.
[0106] In some optional implementations, the vehicle charging method further includes but is not limited to step b1 and step b2.
[0107] Step b1: if the current charging mode or the target charging mode is the custom mode, it is determined whether the charging time set by the user in the custom mode is greater than the shortest charging time threshold.
[0108] Among them, the shortest charging time threshold can be the shortest time required to fully charge the vehicle battery in the extreme speed charging mode.
[0109] Step b2: If the charging time is less than or equal to the shortest charging time threshold, the custom mode is switched to the fast charging mode. If the charging time set by the user is greater than the shortest charging time threshold, the vehicle battery is charged according to the custom mode.
[0110] This embodiment identifies and determines the charging time set by the user to ensure that the charging time set by the user is greater than the shortest time required to fully charge the vehicle battery in the extreme charging mode, thereby avoiding battery safety problems that may be caused by excessive charging current, improving the safety of the vehicle charging process, and enhancing user satisfaction.
[0111] In summary, the vehicle charging method provided by the present invention carries out the charging process according to user needs and habits, and realizes the optimization of the charging strategy for the entire life cycle of the vehicle battery. It also provides users with a variety of preset charging modes to choose from as needed, thereby improving the freedom of charging while protecting the battery in the best way. Moreover, the battery model and machine learning model constructed by the present invention are two manifestations of the digital twin of the real vehicle battery, which realize the monitoring of the battery health status throughout the life cycle and the optimization of the charging strategy, thereby greatly improving the safety of the vehicle battery.
[0112] In this embodiment, a vehicle charging device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and will not be repeated here. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.
[0113] This embodiment provides a vehicle charging device, such as Figure 6 As shown, including:
[0114] The information acquisition module 601 is used to acquire first operating condition information of the vehicle battery in the current charging mode, where the first operating condition information is used to characterize the current operating condition of the vehicle battery. The current charging mode is one of multiple preset charging modes.
[0115] The indicator prediction module 602 is used to predict the second operating condition information using the first operating condition information, and the second operating condition information is used as an evaluation indicator of the health status of the vehicle battery.
[0116] The mode adjustment module 603 is used to adjust the current charging mode according to the second operating condition information.
[0117] In some optional embodiments, the first operating condition information includes a first current, a first state of charge and a first temperature, and the second operating condition information includes a first voltage and a first negative electrode potential. The indicator prediction module 602 is specifically used to input the first operating condition information into a trained machine learning model to output the second operating condition information through the machine learning model; wherein the machine learning model is obtained after training with a battery model deployed on the vehicle, and the battery model is a mathematical simulation model of the vehicle battery.
[0118] In some optional embodiments, the vehicle charging device further includes an information processing module and a model simulation module.
[0119] The information processing module is used to input the third operating condition information into the battery model to output the fourth operating condition information through the battery model; the third operating condition information is the historical operating condition information, the third operating condition information includes the second current, the second state of charge and the second temperature, and the fourth operating condition information includes the second voltage and the second negative electrode potential.
[0120] The model simulation module is used to train the machine learning model to be trained using the third operating condition information and the fourth operating condition information to obtain a trained machine learning model deployed on the vehicle.
[0121] In some optional embodiments, the battery model is one or more of a simplified electrochemical model, a complete electrochemical model, and an equivalent circuit model.
[0122] In some optional embodiments, the vehicle charging device further includes an online calibration module and an intensive training module.
[0123] The online calibration module is used to perform online calibration on the battery model by using the first current, the first state of charge, the first temperature and the corresponding measured voltage and measured negative electrode potential.
[0124] The enhanced training module is used to perform enhanced training on the machine learning model using the online calibrated battery model.
[0125] In some optional implementations, the mode adjustment module 603 is specifically configured to reduce the current or voltage of the vehicle battery in the current charging mode according to the second operating condition information indicating that the health state of the vehicle battery is an unsafe state.
[0126] In some optional embodiments, the plurality of preset charging modes include an extreme charging mode, an adaptive mode, and a custom mode. The extreme charging mode indicates a method of charging the vehicle battery according to the fastest charging strategy, the adaptive mode indicates a method of charging the vehicle battery according to a charging strategy determined based on historical charging big data, and the custom mode indicates a method of charging the vehicle battery according to a charging strategy determined based on a charging time set by a user. The mode adjustment module 603 can also be specifically used to adjust the current charging mode to a target charging mode according to the second operating condition information indicating that the health state of the vehicle battery is an unsafe state; wherein the current charging mode is one of the extreme charging mode, the adaptive mode, and the custom mode, the target charging mode is one of the adaptive mode and the custom mode, and the current charging mode is different from the target charging mode.
[0127] In some optional implementations, the vehicle charging device further includes a determination module and a switching module.
[0128] The judgment module is used to judge whether the charging time set by the user in the custom mode is greater than the shortest charging time threshold according to the current charging mode or the target charging mode is the custom mode.
[0129] The switching module is used to switch the custom mode to the fast charging mode according to the charging time being less than or equal to the shortest charging time threshold.
[0130] The further functional description of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.
[0131] The vehicle charging device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.
[0132] An embodiment of the present invention further provides a vehicle, the vehicle comprising a vehicle controller, the vehicle controller can be used to execute the vehicle charging method provided in any of the above embodiments. The embodiment of the vehicle controller executing the vehicle charging method is the same as the above corresponding embodiment, and will not be repeated here.
[0133] The vehicle controller may be, for example, a VCU (Vehicle Control Unit). Of course, based on the embodiment of the present invention, the vehicle controller may also be any vehicle-mounted controller that can execute the above-mentioned vehicle charging method.
[0134] The embodiment of the present invention also provides an electronic device having the above Figure 6In the vehicle charging device shown, the electronic device can be any electronic device installed on the vehicle for executing the above-mentioned vehicle charging method.
[0135] See also Figure 7 , Figure 7 is a schematic diagram of the structure of an electronic device provided by an optional embodiment of the present invention, such as Figure 7 As shown, the electronic device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 10 is taken as an example.
[0136] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.
[0137] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.
[0138] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0139] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.
[0140] The electronic device further includes a communication interface 30 for the electronic device to communicate with other devices or a communication network.
[0141] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.
[0142] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.
[0143] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.
Claims
1. A vehicle charging method, characterized in that: The method comprises: Acquire first operating condition information of a vehicle battery in a current charging mode, where the first operating condition information is used to characterize a current operating condition of the vehicle battery, and the current charging mode is one of a plurality of preset charging modes; Predicting second operating condition information using the first operating condition information, where the second operating condition information is used as an evaluation indicator of the health status of the vehicle battery; The current charging mode is adjusted according to the second operating condition information.
2. The method according to claim 1, characterized in that The first operating condition information includes a first current, a first state of charge, and a first temperature, and the second operating condition information includes a first voltage and a first negative electrode potential; and the second operating condition information is predicted using the first operating condition information, including: Inputting the first operating condition information into a trained machine learning model to output the second operating condition information through the machine learning model; Among them, the machine learning model is obtained after training with a battery model deployed on the vehicle, and the battery model is a mathematical simulation model of the vehicle battery.
3. The method according to claim 2, characterized in that Before obtaining the first operating condition information of the vehicle battery in the current charging mode, the method further includes: Inputting third operating condition information into the battery model to output fourth operating condition information through the battery model; the third operating condition information is historical operating condition information, the third operating condition information includes a second current, a second state of charge and a second temperature, and the fourth operating condition information includes a second voltage and a second negative electrode potential; The third operating condition information and the fourth operating condition information are used to train the machine learning model to be trained to obtain the trained machine learning model deployed on the vehicle.
4. The method according to claim 2, characterized in that: The battery model is one or more of a simplified electrochemical model, a complete electrochemical model, and an equivalent circuit model.
5. The method according to claim 2, characterized in that: The method further comprises: Performing online calibration on the battery model using the first current, the first state of charge, the first temperature, and the corresponding measured voltage and measured negative electrode potential; The machine learning model is reinforced trained by the battery model after online calibration.
6. The method according to any one of claims 1 to 5, characterized in that The adjusting the current charging mode according to the second operating condition information includes: If the second operating condition information indicates that the health state of the vehicle battery is an unsafe state, the current or voltage of the vehicle battery is reduced in the current charging mode.
7. The method according to any one of claims 1 to 5, characterized in that The plurality of preset charging modes include an extreme charging mode, an adaptive mode, and a custom mode, wherein the extreme charging mode indicates a mode of charging the vehicle battery according to the fastest charging strategy, the adaptive mode indicates a mode of charging the vehicle battery according to a charging strategy determined based on historical charging big data, and the custom mode indicates a mode of charging the vehicle battery according to a charging strategy determined based on a charging time set by a user; The adjusting the current charging mode according to the second operating condition information includes: If the second operating condition information indicates that the health state of the vehicle battery is an unsafe state, adjusting the current charging mode to a target charging mode; The current charging mode is one of the extreme speed charging mode, the adaptive mode and the custom mode, the target charging mode is one of the adaptive mode and the custom mode, and the current charging mode is different from the target charging mode.
8. The method according to claim 7, characterized in that The method further comprises: If the current charging mode or the target charging mode is the custom mode, determining whether the charging time set by the user in the custom mode is greater than a minimum charging time threshold; If the charging time is less than or equal to the shortest charging time threshold, the custom mode is switched to the extreme speed charging mode.
9. A vehicle charging device, characterized in that: The device comprises: An information acquisition module, used to acquire first operating condition information of a vehicle battery in a current charging mode, wherein the first operating condition information is used to characterize a current operating condition of the vehicle battery, and the current charging mode is one of a plurality of preset charging modes; an indicator prediction module, used to predict second operating condition information using the first operating condition information, wherein the second operating condition information is used as an evaluation indicator of the health status of the vehicle battery; A mode adjustment module is used to adjust the current charging mode according to the second operating condition information.
10. An electronic device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the vehicle charging method according to any one of claims 1 to 8 by executing the computer instructions.
11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the vehicle charging method according to any one of claims 1 to 8.
12. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the vehicle charging method according to any one of claims 1 to 8.
13. A vehicle, characterized in that: The vehicle includes a vehicle controller configured to execute the vehicle charging method according to any one of claims 1 to 8.
Citation Information
Cited By
Battery health state calculation method and system, vehicle and storage medium
CN120446791A
Battery state of health calculation method, system, vehicle, and storage medium
CN120446791B
