A method for predicting remaining charging time for vehicles, a charging pile, and a storage medium.

Abstract

This invention relates to the field of new energy vehicle charging technology, specifically to a method for predicting remaining charging time for vehicles, a charging pile, and a storage medium. The method for predicting remaining charging time includes: acquiring first charging characteristic information, second charging characteristic information, and a charging mode; determining the target vehicle model based on the first charging characteristic information; determining a target prediction model based on the target vehicle model and charging mode; and predicting the remaining charging time of the vehicle based on the second charging characteristic information and the target prediction model. This embodiment improves the accuracy of remaining charging time prediction by generating a prediction model for each vehicle model and each charging mode, and using the prediction model corresponding to the current charging mode of the vehicle. This enhances the user experience for vehicle owners.

Description

Technical Field

[0001] This invention relates to the field of new energy vehicle charging technology, specifically to a method for predicting the remaining charging time of a vehicle, a charging pile, and a storage medium. Background Technology

[0002] When charging new energy vehicles, current charging stations can generally estimate the remaining charging time when the vehicle is fully charged or has been charged to a certain level based on parameters such as the vehicle's current battery level and charging conditions. This allows car owners to make reasonable arrangements for charging and vehicle usage.

[0003] However, the charging efficiency of different vehicle models generally varies, and even the charging efficiency of the same vehicle model can vary under different charging modes. Since current charging piles do not have a strategy to adjust the prediction of remaining charging time to account for these differences, the current prediction of the remaining charging time of new energy vehicles is usually not accurate enough, which affects the user experience of car owners. Summary of the Invention

[0004] One objective of this invention is to provide a method for predicting the remaining charging time of a vehicle, a charging pile, and a storage medium, in order to solve the technical problem that the prediction of the remaining charging time of a vehicle is not accurate enough.

[0005] In a first aspect, embodiments of the present invention provide a method for predicting the remaining charging time of a vehicle, comprising:

[0006] Acquire the first charging characteristic information, the second charging characteristic information, and the charging mode;

[0007] The target vehicle model for charging is determined based on the first charging feature information;

[0008] Determine the target prediction model based on the target vehicle model and the charging mode;

[0009] The remaining charging time of the vehicle is predicted based on the second charging feature information and the target prediction model.

[0010] Optionally, determining the target prediction model based on the target vehicle model and the charging mode includes:

[0011] Candidate prediction models are determined based on the target vehicle model;

[0012] Based on the charging mode, a target prediction model is determined from the candidate prediction models.

[0013] Optionally, the step of predicting the remaining charging time of the charging vehicle based on the second charging feature information and the target prediction model includes:

[0014] Obtain the battery temperature of the charging vehicle;

[0015] Determine whether the battery temperature is within a preset temperature range, and obtain the determination result;

[0016] The remaining charging time of the vehicle is predicted based on the judgment result, the second charging feature information, and the target prediction model.

[0017] Optionally, the target prediction model includes a normal temperature charging prediction model, and the step of predicting the remaining charging time of the charging vehicle based on the judgment result, the second charging feature information, and the target prediction model includes:

[0018] If the determination result is that the battery temperature is not within the preset temperature range, then the second charging characteristic information is input into the normal temperature charging prediction model to predict the remaining charging time of the charging vehicle.

[0019] Optionally, the target prediction model further includes a high-temperature charging prediction model, and the method for predicting the remaining charging time of the vehicle further includes:

[0020] Determine the rate of temperature rise of the battery in the charging vehicle;

[0021] The target duration is determined based on the battery temperature, the battery temperature rise rate, and a first preset temperature threshold.

[0022] Determine whether the target duration is less than the remaining charging duration;

[0023] If the remaining charging time is less than the remaining charging time, the high-temperature charging time is predicted according to the high-temperature charging prediction model, and the remaining charging time is updated according to the high-temperature charging time and the target time.

[0024] Optionally, the step of predicting the remaining charging time of the charging vehicle based on the judgment result, the second charging feature information, and the target prediction model includes:

[0025] If the determination result is that the battery temperature is within the preset temperature range, then determine whether the charging vehicle supports the battery preheating function based on the target vehicle model;

[0026] When the charging vehicle supports the battery preheating function, determine whether the charging vehicle is in the battery preheating state.

[0027] When the charging vehicle is in a battery preheating state, a battery preheating mode is determined.

[0028] The remaining charging time of the charging vehicle is predicted based on the battery preheating mode, the second charging characteristic information, and the target prediction model.

[0029] Optionally, the target prediction model includes a preheating prediction model and a normal temperature charging prediction model, and the prediction of the remaining charging time of the charging vehicle based on the battery preheating mode, the second charging feature information and the target prediction model includes:

[0030] A target preheating prediction model is determined based on the battery preheating mode, and the target preheating prediction model includes a first preheating prediction model and a second preheating prediction model.

[0031] The preheating duration is predicted based on the first preheating prediction model;

[0032] Update the second charging characteristic information when battery preheating is completed based on the second preheating prediction model;

[0033] The updated second charging feature information is input into the room temperature charging prediction model to predict the room temperature charging time.

[0034] The remaining charging time of the vehicle is predicted based on the ambient temperature charging time and the preheating time.

[0035] Optionally, the target prediction model includes a first low-temperature charging prediction model, a second low-temperature charging prediction model, and a normal-temperature charging prediction model, and the method for predicting the remaining charging time of the vehicle further includes:

[0036] When the charging vehicle is not in a battery preheating state or does not support the battery preheating function, the low-temperature charging time is predicted according to the first low-temperature charging prediction model.

[0037] Update the second charging characteristic information when the low-temperature charging is completed based on the second low-temperature charging prediction model;

[0038] The updated second charging feature information is input into the room temperature charging prediction model to predict the room temperature charging time.

[0039] The remaining charging time of the vehicle is predicted based on the normal temperature charging time and the low temperature charging time.

[0040] Optionally, the method for predicting the remaining charging time of the vehicle further includes:

[0041] The battery type of the vehicle to be charged is determined based on the target vehicle model;

[0042] Obtain the battery health status of the charging vehicle;

[0043] The target compensation coefficient is determined based on the battery health status and the battery type.

[0044] The remaining charging time is compensated according to the target compensation coefficient.

[0045] In a second aspect, embodiments of the present invention provide a charging pile, including a memory and a processor, wherein the processor is electrically connected to the memory and is used to execute one or more computer programs stored in the memory, and when executing the one or more computer programs, causes the charging pile to implement the vehicle remaining charging time prediction method as described above.

[0046] In a third aspect, embodiments of the present invention provide a computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the vehicle remaining charging time prediction method as described above.

[0047] Compared with existing technologies, this invention provides a method for predicting remaining charging time for vehicles, a charging pile, and a storage medium. The method includes: acquiring first charging characteristic information, second charging characteristic information, and a charging mode; determining the target vehicle model based on the first charging characteristic information; determining a target prediction model based on the target vehicle model and charging mode; and predicting the remaining charging time of the vehicle based on the second charging characteristic information and the target prediction model. This embodiment improves the accuracy of remaining charging time prediction by generating a prediction model for each charging mode of each vehicle model and using the prediction model corresponding to the current charging mode of the vehicle. This enhances the user experience for vehicle owners. Attached Figure Description

[0048] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a schematic diagram of an application scenario for a charging pile provided by an embodiment of the present invention;

[0050] Figure 2 This is a flowchart illustrating a method for predicting remaining charging time for a vehicle, provided in an embodiment of the present invention.

[0051] Figure 3 This is a flowchart illustrating step S202 of a method for predicting remaining charging time for a vehicle provided in an embodiment of the present invention.

[0052] Figure 4A flowchart illustrating a method for predicting remaining charging time for a vehicle, provided in another embodiment of the present invention;

[0053] Figure 5 This is a flowchart illustrating step S2022 of a method for predicting remaining charging time for a vehicle provided in an embodiment of the present invention.

[0054] Figure 6 This is a schematic diagram of a vehicle remaining charging time prediction device provided in an embodiment of the present invention;

[0055] Figure 7 This is a schematic diagram of the structure of the second determining module in a vehicle remaining charging time prediction device provided in an embodiment of the present invention;

[0056] Figure 8 This is a schematic diagram of a vehicle remaining charging time prediction device provided in another embodiment of the present invention;

[0057] Figure 9 This is a schematic diagram of the structure of the first determining module in a vehicle remaining charging time prediction device provided in an embodiment of the present invention;

[0058] Figure 10 This is a schematic diagram of the hardware structure of a charging pile provided in an embodiment of the present invention. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention.

[0060] It should be noted that, unless otherwise specified, the various features in the embodiments of this invention can be combined with each other, all of which are within the protection scope of this invention. Furthermore, although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than the module division in the device or the order in the flowchart. Moreover, the terms "first," "second," and "third" used in this invention do not limit the data or execution order, but only distinguish identical or similar items with essentially the same function and effect.

[0061] Please see Figure 1 This invention provides a schematic diagram of an application scenario for a charging pile, which includes a power grid 100, a charging pile 200, and a charging vehicle 300.

[0062] Power grid 100 is a power network used to transmit mains electricity through transmission lines to charging pile 200 to supply power to charging vehicle 300. Mains electricity is industrial frequency alternating current, generally characterized by the three common quantities of alternating current: voltage, current, and frequency. Generally, the mains electricity transmitted from power grid 100 to charging pile 200 is three-phase alternating current.

[0063] The charging pile 200 is a device used to charge the vehicle 300 to replenish its power. Its working principle is to receive electrical energy from the power grid 100 and then transmit the electrical energy to the vehicle 300 through a charging cable to charge the vehicle 300. In some embodiments, the charging pile 200 can be any type of charging pile, such as a DC charging pile, an AC charging pile, or an AC / DC integrated charging pile.

[0064] The DC charging station uses direct current (DC) to charge the power battery of the vehicle 300; this charging method is also known as "fast charging." The DC charging station is electrically connected to the power grid 100, receiving three-phase 380V AC power from the grid and converting it to DC. This DC power is then delivered to the vehicle 300's power battery through a standard DC charging plug and socket, thus achieving DC charging. The power supply characteristics of the DC charging station itself allow it to output sufficient charging power, with a wide range of voltage and current adjustment, enabling rapid charging. The DC charging station also functions as a charger, capable of monitoring and controlling the status of the battery being charged in real time, and can also measure the amount of electricity charged.

[0065] The AC charging pile is connected to the power grid 100 and provides power to the charging vehicle 300 using a single or dual 220VAC / 380VAC AC output interface. The charging vehicle 300 then uses its onboard charger to charge its battery; this charging method is also known as "slow charging." The output power of the AC charging pile is generally 5kW (220VAC) / 20kW (380VAC), but the actual charging power is limited by the onboard charger, which typically has a power output of 2-3kW for small electric vehicles. The onboard charger of the charging vehicle 300 converts the input AC power into DC power through filtering and rectification, and then stores the DC power in the charging vehicle 300's battery, thus charging the vehicle 300. This charging method is mainly used in small pure electric vehicles.

[0066] The input voltage of an AC / DC integrated charging pile is generally three-phase four-wire 380VAC±15% at a frequency of 50Hz. The AC / DC integrated charging pile includes a DC output port and an AC output port. The DC output port outputs adjustable DC power to charge the power battery of the charging vehicle 300. The charging power is generally 10-40kW. The AC output port outputs 220VAC (5kW) / 380VAC (20kW) AC power to provide charging power to the on-board charger of the charging vehicle 300. The AC / DC integrated charging pile can provide conventional charging through the AC output port and fast charging through the DC output port. During peak charging hours in the daytime, fast charging is used; at night when there are fewer users, conventional charging can be used for slow charging. The AC / DC integrated charging pile can achieve simultaneous AC and DC charging and interlocked charging. Its modular design facilitates maintenance.

[0067] In some embodiments, the charging pile 200 is configured with one or more charging guns. The charging guns are interface devices connecting the charging pile 200 and the charging vehicle 300, primarily used to transmit electrical energy to the charging vehicle 300 for charging. The charging gun typically has a plug and a connecting cable, one end of which connects to the charging pile, and the other end is inserted into the charging port of the charging vehicle 300. Depending on different charging requirements and technical standards, charging guns can be categorized into fast-charging charging guns and slow-charging charging guns.

[0068] Fast charging guns, also known as DC fast charging guns, are typically used at fast charging stations. They have a large power output and can quickly charge the power batteries of 300 vehicles.

[0069] Slow charging guns, also known as AC charging guns, are typically used in home charging stations, commercial charging stations, and public charging stations. They have lower power and are suitable for charging with ordinary household power supplies, resulting in a relatively slow charging speed.

[0070] The charging vehicle 300 is communicatively connected to the charging pile 200. On the one hand, the charging vehicle 300 can receive DC or AC power output from the charging pile 200. On the other hand, the charging vehicle 300 can interact with the charging pile 200. When the charging vehicle 300 interacts with the charging pile 200, they can send and receive various charging interaction information.

[0071] The charging process of the charging vehicle 300 can include a charging parameter configuration stage and a charging stage.

[0072] After the charging pile 200 is physically connected to the charging vehicle 300 and powered on, and the voltage is checked to be normal, the charging parameter configuration stage begins. During this stage, the charging interaction information sent and received between the charging vehicle 300 and the charging pile 200 includes handshake messages, authentication messages, charging parameter negotiation messages, and charging preparation messages.

[0073] The handshake message is used to establish a communication connection between the charging pile 200 and the battery management system of the charging vehicle 300. The handshake message includes a handshake request message and a handshake response message. The handshake request message is sent by the charging pile 200 to the battery management system of the charging vehicle 300 to determine whether the handshake between the two parties is normal and to indicate that the charging pile 200 is ready to configure charging parameters. After receiving the handshake request message, the battery management system of the charging vehicle 300 sends a handshake response message to the charging pile 200, indicating that the battery management system of the charging vehicle 300 is ready to accept the charging parameter configuration. If the charging pile 200 receives the handshake response message, the charging pile 200 determines that the handshake between the two parties is normal and establishes a communication connection between them.

[0074] The authentication message is used to verify the identity of the charging pile 200. The authentication message includes an authentication request message and an authentication response message. The authentication request message is sent by the charging pile 200 to the battery management system of the charging vehicle 300. The authentication request message includes the identity information of the charging pile 200. After receiving the authentication request message, the battery management system of the charging vehicle 300 sends an authentication response message to the charging pile 200, indicating that the battery management system of the charging vehicle 300 has verified the identity of the charging pile 200. After receiving the authentication response message, the charging pile 200 completes its identity verification.

[0075] The charging parameter negotiation message is used to negotiate charging parameters. The charging parameter negotiation message includes a charging parameter suggestion message and a charging parameter confirmation message. The charging parameter suggestion message is sent by the charging pile 200 to the battery management system of the charging vehicle 300. This message includes the charging parameters suggested by the charging pile 200, such as maximum charging voltage, maximum charging current, minimum charging voltage, minimum charging current, and charging mode. After receiving the charging parameter suggestion message, the battery management system of the charging vehicle 300 sends a charging parameter confirmation message to the charging pile 200, indicating that the battery management system of the charging vehicle 300 acknowledges the received charging parameters. Upon receiving the charging parameter confirmation message, the charging pile 200 completes the charging parameter negotiation.

[0076] The charging preparation message is used to indicate that the charging station 200 is ready. The charging preparation message is sent by the charging station 200 to the battery management system of the charging vehicle 300, indicating that the charging station 200 is ready to start charging.

[0077] During the charging phase, the charging pile 200 adjusts the charging voltage and charging current according to the charging requirements of the battery management system of the charging vehicle 300 to ensure the normal operation of the charging process. The charging interaction information exchanged between the charging vehicle 300 and the charging pile 200 includes charging control messages, charging data messages, and charging fault messages.

[0078] Charging control messages are used to control the charging process. These messages may include a start charging command message, a stop charging command message, and a charging status report message. The start charging command message is sent from the charging pile 200 to the battery management system of the charging vehicle 300 to instruct the battery management system of the charging vehicle 300 to begin charging. The stop charging command message is sent from the charging pile 200 to the battery management system of the charging vehicle 300 to instruct the battery management system of the charging vehicle 300 to stop charging. The charging status report message is sent from the battery management system of the charging vehicle 300 to the charging pile 200 to report the charging status of the battery management system of the charging vehicle 300.

[0079] Charging data messages are used to transmit charging data. These messages include charging voltage / current setting messages and battery voltage / current measurement messages. The charging voltage / current setting message is sent from the charging pile 200 to the battery management system of the charging vehicle 300 to set the charging voltage and charging current values. The battery voltage / current measurement message is sent from the battery management system of the charging vehicle 300 to the charging pile 200 to report the battery voltage and battery current values ​​of the charging vehicle 300.

[0080] Charging fault messages are used to indicate charging-related faults. These messages include charging fault messages and battery fault messages. Charging fault messages are sent from the charging pile 200 to the battery management system of the charging vehicle 300 to indicate charging fault information, while battery fault messages are sent from the battery management system of the charging vehicle 300 to the charging pile 200 to indicate battery fault information.

[0081] The term "chargeable vehicle 300" includes any vehicle that can be driven by electricity, including but not limited to pure electric vehicles, hybrid electric vehicles, fuel cell vehicles, etc.

[0082] Please see Figure 2 This invention provides a method for predicting the remaining charging time of a vehicle, which includes:

[0083] S201. Obtain the first charging characteristic information, the second charging characteristic information, and the charging mode;

[0084] In this step, the first charging characteristic information is information used to characterize the charging attributes or battery attributes of the charging vehicle, such as the maximum allowable charging voltage, current, and charging power of the charging vehicle. The charging vehicle is a vehicle currently being charged using a charging station. When the charging station charges the charging vehicle, as described above, the charging station can receive charging interaction information sent by the charging vehicle based on the interaction with the charging vehicle, and obtain the first charging characteristic information based on the charging interaction information.

[0085] The second charging characteristic information is information used to characterize the current charging status of the charging vehicle or the charging attribute of the charging pile. The current charging status of the charging vehicle includes the current output power of the charging pile and the current state of charge of the charging vehicle. The charging attribute of the charging pile includes the maximum output power of the charging pile.

[0086] The charging modes include various power output modes under various charging types. Among them, the charging types include fast charging and slow charging. The power output modes under fast charging include 30kW, 60kW, 120kW, 240kW, 380kW, etc., and the power output modes under slow charging include 3.3kW, 6.6kW, 7kW, etc.

[0087] S202. Determine the target vehicle model for charging based on the first charging characteristic information;

[0088] In this step, the target vehicle model is the model number of the charging vehicle. The model number is a unique identifier, consisting of letters and numbers, assigned to a class of vehicles for identification purposes. It's understood that one model number can correspond to multiple vehicles, but one vehicle can only correspond to one model number.

[0089] S203. Determine the target prediction model based on the target vehicle model and charging mode;

[0090] In this step, the target prediction model is a prediction model corresponding to the current charging mode of the charging vehicle, used to predict the remaining charging time of the charging vehicle. The remaining charging time is the time it takes for the charging vehicle to charge from its current charge level to a preset charge level. The charge level is usually represented by the State of Charge (SOC), which refers to the proportion of usable charge in the battery relative to its nominal capacity. Assuming the current charge level of the charging vehicle is 20% and the preset charge level is 80%, then the remaining charging time of the charging vehicle is the time it takes to charge from 20% to 80%. It is understandable that the preset battery level can be set according to actual needs, including but not limited to 70%, 80%, 90%, 100%, etc. One or more preset battery levels can be set. When multiple preset battery levels are set, the charging pile can predict the remaining charging time of the vehicle from the current battery level to each preset battery level according to the target prediction model. For example, if the current battery level is 20% and the preset battery levels are 80% and 100%, the charging pile can predict the remaining charging time of the vehicle from 20% to 80% and from 20% to 100% according to the target prediction model.

[0091] The charging station pre-acquires feature sampling information of each vehicle model in various charging modes. This feature sampling information is then categorized according to the vehicle model and charging mode. For example, feature sampling information of vehicle model A1 in charging mode B1 is assigned to one category, feature sampling information of vehicle model A1 in charging mode B2 is assigned to another category, and feature sampling information of vehicle model A2 in charging mode B3 is assigned to yet another category, and so on. Next, the charging station cleans the categorized feature sampling information to filter out data with low or no correlation to the remaining charging time prediction, allowing for a more reliable prediction model generation. Then, within each category of cleaned feature sampling information, the charging station associates specified feature sampling information with a remaining charging time label, obtaining sample datasets for each vehicle model in various charging modes. Finally, the charging station trains the sample dataset using pre-defined machine learning algorithms such as 1D-CNN (one-dimensional convolutional neural network) to generate a prediction model for each vehicle model in each charging mode.

[0092] In some embodiments, the charging pile can input a portion of sample data into the corresponding prediction model, obtain the remaining charging time output by each prediction model, and calculate the error between the remaining charging time and the actual remaining charging time of the corresponding remaining charging time label. The performance of the prediction model is tested based on the error. It can be understood that when the error is small, the charging pile can directly use the prediction model for prediction. When the error is large, the charging pile can retrain the prediction model until the generated prediction model meets the prediction requirements.

[0093] In some embodiments, the charging station can determine candidate prediction models based on the target vehicle model, and determine the target prediction model from the candidate prediction models based on the charging mode.

[0094] In this embodiment, the candidate prediction model includes prediction models generated for the target vehicle model based on different charging modes. The charging pile can select the prediction model that matches the current charging mode of the charging vehicle from the candidate prediction models as the target prediction model.

[0095] S204. The remaining charging time of the charging vehicle is predicted based on the second charging characteristic information and the target prediction model.

[0096] Therefore, this embodiment generates a prediction model for each charging mode of each vehicle type and uses the prediction model corresponding to the current charging mode of the charging vehicle to predict the remaining charging time of the charging vehicle, which helps to improve the accuracy of the prediction of the remaining charging time and thus improves the user experience of the car owner.

[0097] In some embodiments, the charging pile acquires the battery temperature of the charging vehicle, determines whether the battery temperature is within a preset temperature range, obtains a determination result, and predicts the remaining charging time of the charging vehicle based on the determination result, the second charging feature information, and the target prediction model.

[0098] In this embodiment, the preset temperature range is a relatively low temperature range compared to the power battery, for example, a preset temperature range of 0°C to 15°C. The charging pile can select the optimal prediction strategy based on the battery temperature to predict the remaining charging time of the vehicle, thereby improving the accuracy of the remaining charging time prediction.

[0099] In some embodiments, the target prediction model includes a room temperature charging prediction model.

[0100] The ambient temperature charging prediction model is a prediction model used to predict the ambient temperature charging time of a charging vehicle. The ambient temperature charging time is the time it takes for a charging vehicle to charge from the battery level when the battery temperature is normal to the preset level.

[0101] In some embodiments, if the determination result is that the battery temperature is not within the preset temperature range, the second charging characteristic information is input into the normal temperature charging prediction model to predict the remaining charging time of the charging vehicle.

[0102] If the battery temperature of the charging vehicle does not fall within the preset temperature range, it indicates that the battery temperature is normal. At this time, the charging station can directly predict the normal temperature charging time based on the currently acquired second charging characteristic information and the normal temperature charging prediction model, and use the normal temperature charging time as the remaining charging time of the charging vehicle.

[0103] It is understandable that if a vehicle is charged after running for a long time, and the ambient temperature is relatively high during charging, the battery temperature may become too high at some point in the charging process. This high battery temperature will affect the charging efficiency of the vehicle. Therefore, the charging station can predict the time when the battery temperature will become too high and divide the charging into different charging periods based on this time: the charging period before the battery temperature becomes too high and the charging period after the battery temperature becomes too high. Then, the remaining charging time of the vehicle can be adjusted in real time according to the charging duration of different charging periods.

[0104] In some embodiments, the high-temperature charging prediction model is a prediction model for predicting the high-temperature charging time of a charging vehicle, where the high-temperature charging time is the time it takes for the charging vehicle to charge from the battery temperature when it is at a high temperature to a preset charge.

[0105] In some embodiments, the charging pile can determine the battery temperature rise rate of the charging vehicle, determine the target duration based on the battery temperature, the battery temperature rise rate and a first preset temperature threshold, determine whether the target duration is less than the remaining charging duration, and if it is less than the remaining charging duration, predict the high-temperature charging duration based on the high-temperature charging prediction model, and update the remaining charging duration based on the high-temperature charging duration and the target duration.

[0106] In some embodiments, the charging pile can acquire the battery temperature of the charging vehicle at regular intervals, calculate the difference between two adjacent battery temperatures to obtain a temperature difference value, and then divide the temperature difference value by the acquisition time interval between the two adjacent battery temperatures to obtain the battery temperature rise rate.

[0107] In some embodiments, the target duration is the time that the charging pile predicts will take from the current battery temperature to the battery temperature reaching a first preset temperature threshold. The charging pile can subtract the first preset temperature threshold from the current battery temperature to obtain a temperature difference value, and then multiply the temperature difference value by the battery temperature rise rate to obtain the target duration.

[0108] If the target charging time is greater than or equal to the remaining charging time, it means that the charging vehicle will not experience excessively high temperatures during the remaining charging time from its current charge level to the preset charge level. Therefore, the charging station does not need to consider the impact of excessively high temperatures on the prediction of the remaining charging time and can directly use the predicted remaining charging time.

[0109] If the target charging time is less than the remaining charging time, it means that the charging vehicle may experience excessively high temperatures during the remaining charging time from its current charge level to the preset charge level. Therefore, the charging station needs to consider the impact of excessively high temperatures on the prediction of the remaining charging time.

[0110] In some embodiments, the charging pile can input charging characteristic information such as the state of charge and battery temperature when the battery temperature is too high into a high-temperature charging prediction model to predict the high-temperature charging time. The high-temperature charging time is the time it takes for the charging vehicle to charge from the battery level when the battery temperature is too high to a preset level. The charging pile can pre-acquire feature sampling information such as the state of charge and battery temperature for each vehicle model under each charging mode during high-temperature charging, associate this feature sampling information with a time label to obtain a sample dataset, and train the high-temperature charging prediction model on the sample dataset according to a preset machine learning algorithm.

[0111] In some embodiments, the charging station can update the remaining charging time by summing the high-temperature charging time with the target time.

[0112] For example, the current battery temperature is 40℃, the current charge level is 25%, the preset charge level is 80%, the first preset temperature threshold is 60℃, and the charging pile currently predicts that the remaining charging time is 2 hours. However, the charging pile predicts that the battery temperature will reach 60℃ after the target time of 1 hour and 50 minutes. Based on the high-temperature charging prediction model, the charging pile predicts the high-temperature charging time when the battery temperature drops from 60℃ to the preset charge level. Assuming that the high-temperature charging time is 20 minutes, the charging pile adds the high-temperature charging time of 20 minutes to the target time of 1 hour and 50 minutes to obtain the updated remaining charging time of 2 hours and 10 minutes.

[0113] Therefore, this embodiment can predict the remaining charging time by adjusting the prediction strategy in a timely manner when the battery temperature is expected to be too high during the charging process, which helps to improve the reliability and accuracy of the prediction of the remaining charging time.

[0114] Understandably, when the ambient temperature is too low, causing the battery temperature to drop, the chemical reaction rate of the power battery in new energy vehicles slows down. This may prevent the power battery from fully absorbing charging energy, leading to insufficient charging and affecting charging efficiency. To improve the charging efficiency of the power battery at low temperatures, some new energy vehicles support battery preheating. Battery preheating can regulate the battery temperature to a suitable range when the power battery temperature is too low, thereby improving charging efficiency and safety. Since whether a new energy vehicle supports battery preheating and whether or not preheating is activated in vehicles that support it both affect the power battery temperature, thus affecting the charging rate and consequently the remaining charging time, charging stations can adopt different remaining charging time prediction strategies based on different situations.

[0115] In some embodiments, if the determination result is that the battery temperature is within a preset temperature range, then it is determined whether the charging vehicle supports the battery preheating function according to the target vehicle model. When the charging vehicle supports the battery preheating function, it is determined whether the charging vehicle is in the battery preheating state. When the charging vehicle is in the battery preheating state, the battery preheating mode is determined, and the remaining charging time of the charging vehicle is predicted according to the battery preheating mode, the second charging characteristic information and the target prediction model.

[0116] In this embodiment, the battery preheating function is used to raise the battery temperature to its optimal operating temperature range. The battery preheating function can be implemented through different battery preheating modes, including external heating mode, internal heating mode, and internal-external heating mode. External heating mode refers to the charging vehicle heating the power battery by activating preheating devices such as PTC (Positive Temperature Coefficient) heating elements, heating films, or liquid circulation heating systems. Internal heating mode refers to the mode that uses alternating current to stimulate the chemical substances inside the power battery, causing the power battery itself to heat up. Internal-external heating mode refers to the mode that simultaneously heats the power battery using both external and internal heating modes.

[0117] It is worth noting that when the charging vehicle is in the battery preheating state, the charging station can charge the vehicle's power battery regardless of the current battery preheating mode.

[0118] In some embodiments, the target prediction model includes a preheating prediction model and a room temperature charging prediction model.

[0119] The preheating prediction model is used to predict the preheating time of a charging vehicle. The preheating time is the time it takes for the battery of the charging vehicle to heat from the current temperature to a second preset temperature threshold. The second preset temperature threshold can be set according to actual needs, for example, the second preset temperature threshold is 15℃. For a detailed description of the room temperature charging prediction model, please refer to the above embodiment, which will not be repeated here.

[0120] In some embodiments, the charging pile can determine a target preheating prediction model based on the battery preheating mode. The target preheating prediction model includes a first preheating prediction model and a second preheating prediction model. The preheating duration is predicted based on the first preheating prediction model. The second charging characteristic information when the battery preheating is completed is updated based on the second preheating prediction model. The updated second charging characteristic information is input into the normal temperature charging prediction model to predict the normal temperature charging duration. The remaining charging duration of the charging vehicle is predicted based on the normal temperature charging duration and the preheating duration.

[0121] In this embodiment, the first preheating prediction model is used to predict the preheating duration, and the second preheating prediction model is used to update the second charging characteristic information when battery preheating is completed. The remaining charging time of the charging vehicle is the sum of the normal temperature charging time and the preheating time. If the charging vehicle is in the battery preheating state, the battery preheating is completed when the battery temperature of the charging vehicle reaches the second preset temperature threshold. The second preset temperature threshold is the battery temperature when the battery temperature is normal, and the completion of battery preheating is when the battery temperature is normal.

[0122] The charging pile can acquire feature sampling information such as battery temperature, ambient temperature, and state of charge for each type of vehicle in each battery preheating mode. On the one hand, the charging pile associates the feature sampling information with duration tags to obtain a sample dataset, and trains the sample dataset according to a preset machine learning algorithm to obtain a first preheating prediction model. On the other hand, the charging pile associates the feature sampling information with state of charge tags to obtain a sample dataset, and trains the sample dataset according to a preset machine learning algorithm to obtain a second preheating prediction model. The state of charge tag is used to identify the state of charge when the battery temperature reaches a second preset temperature threshold.

[0123] The charging pile can extract charging characteristic information such as state of charge and charging power from the charging interaction information and input the charging characteristic information into the first preheating prediction model to predict the preheating time.

[0124] The charging pile can extract charging feature information such as state of charge, battery temperature, and ambient temperature from the charging interaction information and input the charging feature information into the second preheating prediction model to predict the state of charge when the battery preheating is completed. The charging feature information is then updated using the state of charge. For example, the currently obtained state of charge in the second charging feature information is updated to the state of charge when the battery preheating is completed.

[0125] It is understandable that the preheating time is different for the same vehicle model when it is in different battery preheating modes, and different preheating times will affect the prediction of the remaining charging time. Therefore, charging piles can adopt different preheating time prediction strategies in combination with different battery preheating modes.

[0126] Therefore, this embodiment can predict the remaining charging time of the vehicle when the battery is in the preheating state, which can provide the owner with a more comprehensive charging service and improve the owner's user experience.

[0127] Understandably, when the battery temperature of a charging vehicle is low, if the vehicle is not in a battery preheating state or does not support battery preheating, the battery temperature of the charging vehicle will gradually rise during the charging process. During the charging period when the battery temperature is low, the charging efficiency is low, and during the charging period when the battery temperature is high, the charging efficiency is high. Since the charging efficiency at different charging periods may be affected by different factors, the charging station can predict the charging time for different charging periods separately, and then predict the remaining charging time of the vehicle based on the charging time of each charging period.

[0128] In some embodiments, the target prediction model includes a first low-temperature charging prediction model, a second low-temperature charging prediction model, and a room-temperature charging prediction model.

[0129] In this embodiment, the first low-temperature charging prediction model is a prediction model used to predict the charging duration (low-temperature charging duration) of the charging vehicle during the charging period when the battery temperature is low, and the second low-temperature charging prediction model is a prediction model used to update the second charging characteristic information of the charging vehicle when the charging period when the battery temperature is low ends (low-temperature charging is completed). The specific description of the normal temperature charging prediction model can be referred to the above embodiment, and will not be repeated here.

[0130] In some embodiments, if the charging vehicle is not in a battery preheating state or does not support the battery preheating function, the charging pile predicts the low-temperature charging time according to the first low-temperature charging prediction model, updates the second charging characteristic information when low-temperature charging is completed according to the second low-temperature charging prediction model, inputs the updated second charging characteristic information into the normal temperature charging prediction model, predicts the normal temperature charging time, and predicts the remaining charging time of the charging vehicle based on the normal temperature charging time and the low-temperature charging time.

[0131] In this embodiment, the charging pile can extract charging feature information such as state of charge and charging power from the charging interaction information and input the charging feature information into the first low-temperature charging prediction model to predict the low-temperature charging time. Then, the charging pile inputs charging feature information such as state of charge, battery temperature, and ambient temperature into the second low-temperature charging prediction model to predict the state of charge when low-temperature charging is completed and updates the second charging feature information based on the state of charge. For example, the currently obtained state of charge in the second charging feature information is updated to the state of charge when low-temperature charging is completed. The updated second charging feature information is then input into the normal temperature charging prediction model to predict the normal temperature charging time. Finally, the charging pile can use the sum of the normal temperature charging time and the low-temperature charging time as the remaining charging time of the vehicle.

[0132] Therefore, this embodiment can divide the charging process of the charging vehicle into different charging stages based on the battery temperature, predict the charging time of each charging stage, and then predict the remaining charging time of the charging vehicle based on the charging time of each charging stage, which is beneficial to more accurately predict the remaining charging time.

[0133] It is understandable that the charging efficiency of a vehicle is usually affected by static parameters such as the type and usage of the vehicle's power battery. In other words, different battery types and different usage conditions will also affect the charging station's prediction of the remaining charging time. Therefore, the charging station can adjust the charging time based on the battery type and usage of the vehicle.

[0134] In some embodiments, the charging pile determines the battery type of the vehicle being charged based on the target vehicle model, obtains the battery health status of the vehicle being charged, determines a target compensation coefficient based on the battery health status and battery type, and compensates for the remaining charging time based on the target compensation coefficient.

[0135] For example, if the remaining charging time is 2 hours, and the charging station is equipped with a preset mapping table between different battery health states and different battery types and compensation coefficients, the charging station can query the preset mapping table according to the battery type and battery health state of the vehicle being charged. The compensation coefficient corresponding to the battery type and battery health state of the vehicle being charged in the preset mapping table is used as the target compensation coefficient. Assuming the target compensation coefficient is 1.1, the charging station can multiply the remaining charging time of 2 hours by the target compensation coefficient of 1.1 to get 2 hours and 12 minutes, and then correct the remaining charging time of 2 hours to 2 hours and 12 minutes.

[0136] Therefore, this embodiment can adjust the remaining charging time according to the battery status of the charging vehicle, thereby improving the reliability and accuracy of the remaining charging time prediction.

[0137] In some embodiments, please refer to Figure 3 S202 includes:

[0138] S2021. Input the first charging feature information into the vehicle prediction model to obtain the vehicle prediction result;

[0139] In this step, the vehicle model prediction model is an algorithmic model used to predict the vehicle model of the charging vehicle. The vehicle model prediction model can be any suitable type of algorithmic model, including but not limited to decision tree model, random forest model, logistic regression model, neural network model, support vector machine model, etc.

[0140] Vehicle model prediction results are the prediction results output by the vehicle model prediction model. In some embodiments, the vehicle model prediction results include at least one vehicle model label, which is a classification label used to uniquely identify the target vehicle model. Each vehicle model corresponds to at most one vehicle model label.

[0141] Since the vehicle model prediction result can have one or more vehicle model tags, the number of vehicle model tags will affect the charging pile's strategy for determining the vehicle model of the vehicle being charged. Therefore, when the charging pile determines the vehicle model of the vehicle being charged based on the vehicle model prediction result, it needs to first count the number of vehicle model tags in the vehicle model prediction result.

[0142] Understandably, when the vehicle model prediction model outputs a vehicle model prediction result that includes only one vehicle model label, the charging station can directly determine the vehicle model of the vehicle being charged based on that unique vehicle model label. However, when the vehicle model prediction model outputs a vehicle model prediction result that includes more than one vehicle model label, the charging station cannot directly determine the vehicle model of the vehicle being charged, and in this case, the charging station needs to further determine the target vehicle model of the vehicle being charged.

[0143] For example, both Model A1 from Brand A and Model B1 from Brand B use the same battery management system manufactured by the same equipment manufacturer. Because they use the same battery management system, the first charging feature information carried in the charging interaction information sent to the charging station when Model A1 and Model B1 are charging may be the same. After inputting the first charging feature information into the model prediction model, the model prediction result output by the model prediction model may include the model label corresponding to Model A1 and the model label corresponding to Model B1. At this time, the charging station cannot directly determine whether the vehicle being charged is Model A1 or Model B1.

[0144] It is understandable that the prediction process of the vehicle model prediction model is the initial vehicle identification stage. In the initial vehicle identification stage, the charging pile can directly locate the vehicle model of the vehicle being charged. For example, if the vehicle model prediction result only includes one vehicle model label, the charging pile may not be able to directly locate the vehicle model of the vehicle being charged. For example, if the vehicle model prediction result includes more than one vehicle model label.

[0145] S2022. Determine the target vehicle model for charging based on the vehicle model test results.

[0146] In this step, the target vehicle model is the model number of the charging vehicle. The model number is a unique identifier, consisting of letters and numbers, assigned to a class of vehicles for identification purposes. It's understood that one model number can correspond to multiple vehicles, but one vehicle can only correspond to one model number.

[0147] Therefore, this embodiment can automatically identify the target model of the charging vehicle when charging the charging vehicle, which is beneficial for subsequently combining the target model to locate the prediction model used to predict the remaining charging time of the charging vehicle, thereby facilitating the reliable prediction of the remaining charging time of the charging vehicle.

[0148] In some embodiments, please refer to Figure 4 Prior to the implementation of S2021, the methods for predicting the remaining charging time of vehicles also included:

[0149] S2023. Obtain feature sampling information of charging vehicles for each vehicle type;

[0150] In this step, the feature sampling information refers to the charging feature information obtained by the charging pile in advance by sampling each type of vehicle when charging or testing each type of vehicle. These vehicle types can include vehicles from different brands, vehicles of the same brand but different series, vehicles of the same brand and series but different models, and vehicles of the same brand, series, and model but different production years, etc.

[0151] S2024. Associate the feature sampling information with the preset vehicle model label to obtain the sample dataset;

[0152] In this step, the preset vehicle model label is a label used to pre-classify different vehicle models. The charging station associates the feature sampling information obtained from each vehicle model with the corresponding preset vehicle model label to obtain sample data for each vehicle model. For example, the sample data for one vehicle model is as follows:

[0153] {

[0154] "CC1":"XXX",

[0155] "CC2":XXX,

[0156] "CC3":XXX,

[0157] "CC4":XXX,

[0158] "CC5":XXX,

[0159] "VehicleLabel":"XXX"

[0160] }

[0161] Among them, CC1, CC2, CC3, CC4 and CC5 represent five feature parameters, and VehicleLabel represents the preset vehicle model label.

[0162] The charging stations will aggregate sample data from various vehicle models to obtain a sample dataset.

[0163] S2025. Train the sample dataset according to the preset machine learning algorithm to obtain the vehicle model prediction model.

[0164] In this step, the types of preset machine learning algorithms can be set according to actual needs, including but not limited to decision tree algorithms, random forest algorithms, logistic regression algorithms, neural network algorithms, support vector machine algorithms, etc. These algorithms can be combined to form a machine learning algorithm library. The charging pile can call the machine learning algorithm library, adjust the optimal algorithm parameters according to the data characteristics of the sample dataset, and then input the sample dataset for training. After training, the machine learning algorithm library will provide an optimal prediction model, which the charging pile will use as the vehicle model prediction model.

[0165] Since the vehicle model prediction model is trained using a sample dataset consisting of sample data for various vehicle models, it can cover the prediction of various vehicle models. Furthermore, when new vehicle models appear in the future, the model can be further trained to expand the range of vehicle models, thus enabling charging stations to make accurate and reliable vehicle model predictions for the vehicles currently being charged.

[0166] In some embodiments, the vehicle model prediction result includes at least one vehicle model label. See [link / reference] Figure 5 S2022 includes:

[0167] S20221. Determine the number of vehicle model tags in the vehicle model prediction results;

[0168] In this step, as mentioned earlier, during the initial vehicle identification stage, the number of vehicle labels in the vehicle prediction results output by the vehicle prediction model is one or more.

[0169] S20222. Determine the target vehicle model for charging based on the number of vehicle model tags and the vehicle model tags in the vehicle model prediction results.

[0170] In this step, when there is more than one vehicle model tag, the charging pile may not be able to clearly distinguish the specific vehicle model of the vehicle being charged. Therefore, after the vehicle model prediction model outputs the vehicle model prediction result, the charging pile needs to determine the number of vehicle model tags in the vehicle model prediction result. When there is only one vehicle model tag, it is not necessary to enter the vehicle model fine identification stage. However, when there is more than one vehicle model tag, it is necessary to enter the vehicle model fine identification stage in order to accurately locate the target vehicle model of the vehicle being charged.

[0171] In some embodiments, the charging pile determines whether the number of vehicle model tags is greater than 1, obtains the determination result, and determines the target vehicle model of the charging vehicle based on the determination result and the vehicle model prediction result of the vehicle model tags.

[0172] Therefore, this embodiment can flexibly select the prediction strategy for the target vehicle model based on the number of vehicle model tags, which is beneficial to improving the reliability and accuracy of vehicle model prediction for charging vehicles.

[0173] In some embodiments, the vehicle model label may include vehicle model information, which is information used to uniquely identify the corresponding vehicle model. The vehicle model label may also include vehicle model information and battery pack capacity information, which is information used to indicate the design capacity of the power battery pack of the vehicle model corresponding to the vehicle model label at the time of manufacture.

[0174] In some embodiments, if the determination result is that the number of vehicle model tags is not greater than 1, the charging pile determines the target vehicle model of the charging vehicle based on the vehicle model information corresponding to the vehicle model tag.

[0175] For example, suppose the vehicle model prediction model outputs the following vehicle prediction results:

[0176] VehicleLabel_1:A1_120kWh

[0177] In the vehicle label “VehicleLabel_1”, A1 is the vehicle model information, and 120kWh is the battery pack capacity information for vehicle model A1.

[0178] Since the vehicle model prediction result only includes one vehicle model label, VehicleLabel_1, the charging station can identify the vehicle model information A1 in this vehicle model label as the target vehicle model for charging.

[0179] In some embodiments, if the determination result is that the number of vehicle model tags is greater than 1, the battery pack capacity information of each vehicle model tag is extracted, and the target vehicle model of the charging vehicle is determined based on the battery pack capacity information and the vehicle model information.

[0180] For example, suppose the vehicle model prediction model outputs the following vehicle prediction results:

[0181] VehicleLabel_2:B1_70kWh

[0182] VehicleLabel_3:C1_100kWh

[0183] In the vehicle label “VehicleLabel_2”, B1 is the vehicle information and 70kWh is the battery pack capacity information for vehicle B1. In the vehicle label “VehicleLabel_3”, C1 is the vehicle information and 100kWh is the battery pack capacity information for vehicle C1.

[0184] Since the vehicle model prediction results include two vehicle model labels, VehicleLabel_2 and VehicleLabel_3, and the number of vehicle model labels is 2 (2 is greater than 1), the charging station extracts the battery pack capacity information of 70kWh and 100kWh corresponding to the vehicle model labels VehicleLabel_1 and VehicleLabel_2, respectively, and determines the target vehicle model of the charging vehicle based on these two battery pack capacity information and the corresponding vehicle model information.

[0185] Therefore, this embodiment can clearly distinguish the target vehicle model of the charging vehicle even when there are multiple vehicle model labels in the vehicle model prediction results, which helps to improve the reliability and accuracy of vehicle model identification.

[0186] In some embodiments, the charging station can determine whether there is a discrepancy in the battery pack capacity information and determine the target vehicle model for charging based on the determination result.

[0187] Discrepancies in battery pack capacity information can occur if the capacity of each battery pack in multiple battery pack capacity information sets is different, or if multiple battery pack capacity information sets contain both identical and different capacity information, as long as all battery pack capacity information sets are not completely identical. For example, as mentioned earlier, if the charging station extracts battery pack capacity information of 70kWh corresponding to the vehicle model label VehicleLabel_2 and 100kWh corresponding to VehicleLabel_3, the charging station can determine that there is a discrepancy in the battery pack capacity information.

[0188] For another example, suppose the vehicle model prediction model outputs the following vehicle prediction results:

[0189] VehicleLabel_4:D1_80kWh

[0190] VehicleLabel_5: E1_80kWh

[0191] Since the battery pack capacity information corresponding to both VehicleLabel_4 and VehicleLabel_5 is 80kWh, the charging station can determine that there is no difference in the battery pack capacity information.

[0192] If there is a discrepancy in the battery pack capacity information, the charging station can determine the actual battery pack capacity of the vehicle being charged, determine the target vehicle model label based on the actual battery pack capacity, and determine the target vehicle model based on the vehicle model information corresponding to the target vehicle model label.

[0193] If there is no difference in battery pack capacity information, the charging station can determine the charging curve characteristics of the charging vehicle, determine the target vehicle model label based on the charging curve characteristics, and determine the target vehicle model based on the vehicle model information corresponding to the target vehicle model label.

[0194] In some embodiments, when determining the actual battery pack capacity of a charging vehicle, the charging pile calculates the amount of battery charge required to charge the vehicle for each preset percentage of battery capacity, averages the amount of battery charge to obtain an average charge value, and determines the actual battery pack capacity of the charging vehicle based on the average charge value and a preset value.

[0195] In this embodiment, the product of the preset value and the preset percentage equals 1. For example, when the preset percentage is one percent, the preset value is 100, and when the preset percentage is two percent, the preset value is 50. It can be understood that 100% battery capacity means the vehicle is fully charged.

[0196] Taking a preset percentage of one percent as an example, firstly, since the charging current and charging voltage of the charging vehicle change in real time during the charging process, the charging pile can integrate the battery charging capacity over a preset time interval. For example, if the integration interval is one second, the charging pile can calculate the battery charging capacity per second and then accumulate the battery charging capacity per second until the battery charging capacity changes by one percent. In some embodiments, the charging pile can calculate the battery charging capacity required to charge the vehicle to each preset percentage of capacity according to the following formula:

[0197] Cap = Q1 + Q2 + Q3 + ... + Qn

[0198] Q1 = v1 * c1 * t

[0199] Q2=v2*c2*t

[0200] Q3=v3*v3*t

[0201] Qn=vn*cn*t

[0202] Where Cap represents the amount of battery charge required to charge the vehicle to a preset percentage of its capacity, Qn represents the amount of battery charge received in the nth integration interval, vn represents the charging voltage used to charge the vehicle during the nth integration interval, cn represents the charging current used to charge the vehicle during the nth integration interval, and t represents the duration of the integration interval.

[0203] Next, the charging station can accumulate multiple battery charging amounts required to charge a vehicle to a preset percentage of its capacity, and then average these amounts to obtain an average charge level. In some embodiments, the charging station can calculate the average charge level using the following formula:

[0204] Cap_av=(Cap1+Cap2+……+Capn) / n

[0205] Finally, the charging station multiplies the average charge amount by a preset value to obtain the actual battery pack capacity of the vehicle being charged. As mentioned earlier, the preset value can be set based on a preset percentage, as long as the product of the preset value and the preset percentage equals 1.

[0206] Therefore, this embodiment estimates the actual battery pack capacity of the charging vehicle by integrating the charging power, avoiding estimation errors introduced by real-time changes in charging current and charging voltage during the charging process. This allows for a more accurate estimation of the true battery pack capacity of the charging vehicle, which in turn facilitates more reliable prediction of the vehicle model in the future.

[0207] In some embodiments, the charging pile matches the actual battery pack capacity with the battery pack capacity information corresponding to each vehicle model label and determines the vehicle model label corresponding to the successfully matched battery pack capacity information as the target vehicle model label. The target vehicle model of the charging vehicle is then determined based on the vehicle model information corresponding to the target vehicle model label.

[0208] Understandably, if the actual battery pack capacity matches the battery capacity information corresponding to a certain vehicle model label, then the battery capacity information is determined to be a successfully matched battery capacity information. Alternatively, if the difference between the actual battery pack capacity and the battery capacity information corresponding to a certain vehicle model label is within a preset range, then the battery capacity information is determined to be a successfully matched battery capacity information.

[0209] For example, if the actual battery pack capacity is 99kWh, as mentioned earlier, the vehicle model prediction results are labeled Vehicl eLabe l_2 and Vehicl eLabe l_3. The battery pack capacity information corresponding to these two vehicle model labels are 120kWh, 70kWh, and 100kWh, respectively. Since the difference between the actual battery pack capacity of 99kWh and 100kWh is within the preset range of ±1kWh, the charging station can determine that 100kWh is the successfully matched battery pack capacity information and use the vehicle model information C1 corresponding to 100kWh as the target vehicle model for charging.

[0210] Since the battery pack capacity of different vehicle models is generally different, the charging station can estimate the actual battery pack capacity of the vehicle being charged to uniquely identify the vehicle model. This can help the charging station reliably identify the target vehicle model when it cannot directly obtain the battery pack capacity of the vehicle being charged.

[0211] It is understandable that, although there are differences in battery pack capacity information, when the vehicle model prediction model outputs multiple vehicle model labels, there may be two or more vehicle model labels corresponding to the same battery pack capacity information. For example, the vehicle model prediction model outputs the following vehicle model prediction results:

[0212] VehicleLabel_6:D1_80kWh

[0213] VehicleLabel_7: E1_80kWh

[0214] VehicleLabel_8: F1_90kWh

[0215] If the actual battery pack capacity estimated by the charging pile is 80kWh, and the battery pack capacity information corresponding to VehicleLabel_6 and VehicleLabel_7 is also 80kWh, the charging pile cannot directly determine whether the vehicle model is D1 or E1. Therefore, in some embodiments, when there is a difference in battery pack capacity information, but the charging pile cannot determine the target vehicle model based on the actual battery pack capacity, the charging pile can determine the charging curve characteristics of the vehicle and determine the target vehicle model based on the charging curve characteristics.

[0216] In some embodiments, when determining the charging curve characteristics of a charging vehicle, the charging pile can acquire dynamic charging characteristic information at multiple time points during the continuous charging of the charging vehicle to a preset percentage of electricity (e.g., 10%), and fit the dynamic charging characteristic information into a charging curve according to any suitable curve fitting algorithm, thereby obtaining the charging curve characteristics. The dynamic charging characteristic information may include any suitable charging characteristic information such as the demand current.

[0217] In some embodiments, the charging pile inputs the charging curve features into the auxiliary prediction model to obtain the auxiliary prediction result, and determines the target vehicle model for charging based on the auxiliary prediction result.

[0218] In this embodiment, the auxiliary prediction model is an algorithm model used to assist the vehicle model prediction model in predicting the vehicle model of the charging vehicle. In some embodiments, the charging pile pre-acquires dynamic charging feature information during the charging process of each vehicle model and fits the dynamic charging feature information into a sample charging curve according to any suitable curve fitting algorithm. Then, the sample charging curve is associated with a preset vehicle model label to obtain a sample dataset. Finally, the sample dataset is trained according to a preset machine learning algorithm to obtain the auxiliary prediction model.

[0219] In some embodiments, the auxiliary prediction result includes at least one auxiliary prediction label, which includes vehicle model information. When the number of auxiliary prediction labels is 1, the charging pile can determine the target vehicle model of the charging vehicle based on the vehicle model information corresponding to the auxiliary prediction label.

[0220] In some embodiments, the charging station can determine the target vehicle model of the vehicle being charged based on the vehicle model label from the auxiliary prediction result and the vehicle model label from the vehicle model prediction result.

[0221] For example, as mentioned earlier, the vehicle model prediction results include the following vehicle model tags:

[0222] VehicleLabel_4:D1_80kWh

[0223] VehicleLabel_5: E1_80kWh

[0224] Assume the auxiliary prediction results include the following auxiliary prediction labels:

[0225] AuxiliaryLabel_1:E1

[0226] AuxiliaryLabel_2:G1

[0227] The charging station can extract the vehicle information corresponding to each vehicle model tag and the vehicle information corresponding to each auxiliary prediction tag. It then compares each vehicle model information with the vehicle information corresponding to each auxiliary prediction tag sequentially, identifying the matching vehicle model as the target vehicle model for charging. As mentioned earlier, the charging station can compare vehicle information D1 with vehicle information E1 and G1 respectively. If they do not match, the charging station can then compare vehicle information E1 with vehicle information E1 and G1 respectively. If vehicle information E1 matches, the charging station can determine that vehicle information E1 is the target vehicle model for charging.

[0228] Therefore, this embodiment can use the vehicle model label of the auxiliary prediction result and the vehicle model label of the vehicle model prediction result for verification, and determine the target vehicle model of the charging vehicle based on the verification result, so as to identify the target vehicle model of the charging vehicle more accurately and reliably.

[0229] It should be noted that in the above embodiments, there is no necessarily a certain order between the steps. Those skilled in the art can understand from the description of the embodiments of the present invention that the above steps may have different execution orders in different embodiments, that is, they may be executed in parallel or in turn, etc.

[0230] As another aspect of this invention, this embodiment provides a vehicle remaining charging time prediction device. The vehicle remaining charging time prediction device can be a software module, which includes several instructions stored in a memory. A processor can access the memory, call the instructions, and execute them to complete the vehicle remaining charging time prediction method described in the above embodiments.

[0231] In some embodiments, the vehicle remaining charging time prediction device can be constructed from hardware devices. For example, the vehicle remaining charging time prediction device can be constructed from one or more chips, and the chips can work together to complete the vehicle remaining charging time prediction method described in the various embodiments above. As another example, the vehicle remaining charging time prediction device can also be constructed from components such as general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), microcontrollers, ARM (Acorn RISC Machines), programmable logic devices, discrete gate or transistor logic, discrete hardware components, or any combination of these components.

[0232] In some embodiments, please refer to Figure 6 The vehicle remaining charging time prediction device 600 provided in this embodiment of the invention includes a first acquisition module 601, a first determination module 602, a second determination module 603 and a prediction module 604.

[0233] The first acquisition module 601 is used to acquire first charging feature information, second charging feature information and charging mode; the first determination module 602 is used to determine the target vehicle model of the charging vehicle based on the first charging feature information; the second determination module 603 is used to determine the target prediction model based on the target vehicle model and charging mode; and the prediction module 604 is used to predict the remaining charging time of the charging vehicle based on the second charging feature information and the target prediction model.

[0234] In some embodiments, please refer to Figure 7 The second determining module 603 includes a first determining unit 6031 and a second determining unit 6032.

[0235] The first determining unit 6031 is used to determine candidate prediction models based on the target vehicle model, and the second determining unit 6032 is used to determine the target prediction model from the candidate prediction models based on the charging mode.

[0236] In some embodiments, please refer to Figure 8 The vehicle remaining charging time prediction device 600 also includes a third determination module 605, a second acquisition module 606, a fourth determination module 607, and a compensation module 608.

[0237] The third determining module 605 is used to determine the battery type of the charging vehicle based on the target vehicle model; the second obtaining module 606 is used to obtain the battery health status of the charging vehicle; the fourth determining module 607 is used to determine the target compensation coefficient based on the battery health status and battery type; and the compensation module 608 is used to compensate for the remaining charging time based on the target compensation coefficient.

[0238] In some embodiments, please refer to Figure 9 The first determining module 602 includes a prediction unit 6021 and a third determining unit 6022.

[0239] The prediction unit 6021 is used to input the first charging feature information into the vehicle model prediction model to predict the vehicle model prediction result, and the third determination unit 6022 is used to determine the target vehicle model of the charging vehicle based on the vehicle model prediction result.

[0240] It should be noted that the above-mentioned vehicle remaining charging time prediction device can execute the vehicle remaining charging time prediction method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects of the method. Technical details not described in detail in the embodiments of the vehicle remaining charging time prediction device can be found in the vehicle remaining charging time prediction method provided in the embodiments of the present invention.

[0241] Please see Figure 10 , Figure 10 This is a schematic diagram of the hardware structure of a charging pile provided in an embodiment of the present invention. Figure 10 As shown, the charging station includes one or more processors 1001 and a memory 1002. Figure 10 Take processor 1001 as an example.

[0242] Processor 1001 is configured to support the computer device in performing the corresponding functions in the methods described in the above method embodiments. Processor 1001 may be a central processing unit (CPU), a network processor (NP), a hardware chip, or any combination thereof. The aforementioned hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The aforementioned PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0243] Memory 1002 is used to store program code. Memory 1002 may include volatile memory (VM), such as random access memory (RAM); memory may also include non-volatile memory (NVM), such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid-state drive (SSD); memory 1002 may also include combinations of the above types of memory.

[0244] The memory 1002 can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the vehicle remaining charging time prediction method in the embodiments of the present invention. The processor 1001 executes various functional applications and data processing of the vehicle remaining charging time prediction method and the vehicle remaining charging time prediction device by running the non-volatile software programs, instructions, and modules stored in the memory 1002, that is, it realizes the functions of each module or unit of the vehicle remaining charging time prediction method and the vehicle remaining charging time prediction device provided in the above method embodiments.

[0245] The memory 1002 may include a program storage area and a data storage area, wherein the program storage area may store the operating system and applications required for at least one function. The data storage area may store data created based on the use of the vehicle's remaining charging time prediction device. In some embodiments, the memory 1002 may optionally include memory remotely configured relative to the processor, which can be connected to the vehicle's remaining charging time prediction device via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0246] The one or more modules are stored in the memory 1002. When executed by the one or more processors 1001, they execute the vehicle remaining charging time prediction method in any of the above method embodiments. For example, they execute the method steps described in the above method embodiments to realize the functions of the modules described in the above device embodiments.

[0247] This invention also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, which, when executed by a computer, cause the computer to perform the method described in the foregoing embodiments.

[0248] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0249] Finally, it should be noted that the present invention can be implemented in many different forms and is not limited to the embodiments described in this specification. These embodiments are not intended to impose additional limitations on the content of the present invention; their purpose is to provide a more thorough and comprehensive understanding of the disclosure of the present invention. Furthermore, within the framework of the present invention, the above-described technical features can be combined with each other, and many other variations of different aspects of the present invention as described above exist, all of which are considered to be within the scope of the present invention specification. Moreover, those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. A method for predicting remaining charging time for a vehicle, characterized in that, include: Acquire first charging feature information, second charging feature information, and charging mode. The first charging feature information is information used to characterize the charging attributes or battery attributes of the charging vehicle, and the second charging feature information is information used to characterize the current charging status of the charging vehicle or the charging attributes of the charging pile. The target vehicle model for charging is determined based on the first charging feature information; A target prediction model is determined based on the target vehicle model and the charging mode. The target prediction model includes a preheating prediction model and a normal temperature charging prediction model. Obtain the battery temperature of the charging vehicle; Determine whether the battery temperature is within a preset temperature range, and obtain the determination result; The remaining charging time of the charging vehicle is predicted based on the judgment result, the second charging feature information, and the target prediction model. The step of predicting the remaining charging time of the charging vehicle based on the judgment result, the second charging feature information, and the target prediction model includes: If the determination result is that the battery temperature is within the preset temperature range, then determine whether the charging vehicle supports the battery preheating function based on the target vehicle model; When the charging vehicle supports the battery preheating function, determine whether the charging vehicle is in the battery preheating state. When the charging vehicle is in a battery preheating state, a battery preheating mode is determined. A target preheating prediction model is determined based on the battery preheating mode, and the target preheating prediction model includes a first preheating prediction model and a second preheating prediction model. The preheating duration is predicted based on the first preheating prediction model; Update the second charging characteristic information when battery preheating is completed based on the second preheating prediction model; The updated second charging feature information is input into the room temperature charging prediction model to predict the room temperature charging time. The remaining charging time of the vehicle is predicted based on the ambient temperature charging time and the preheating time.

2. The method for predicting remaining charging time of a vehicle according to claim 1, characterized in that, The step of determining the target prediction model based on the target vehicle model and the charging mode includes: Candidate prediction models are determined based on the target vehicle model; Based on the charging mode, a target prediction model is determined from the candidate prediction models.

3. The method for predicting remaining charging time of a vehicle according to claim 1, characterized in that, The step of predicting the remaining charging time of the charging vehicle based on the judgment result, the second charging feature information, and the target prediction model further includes: If the determination result is that the battery temperature is not within the preset temperature range, then the second charging characteristic information is input into the normal temperature charging prediction model to predict the remaining charging time of the charging vehicle.

4. The method for predicting remaining charging time of a vehicle according to claim 1, characterized in that, The target prediction model also includes a high-temperature charging prediction model, and the method for predicting the remaining charging time of the vehicle also includes: Determine the rate of temperature rise of the battery in the charging vehicle; The target duration is determined based on the battery temperature, the battery temperature rise rate, and a first preset temperature threshold. Determine whether the target duration is less than the remaining charging duration; If the remaining charging time is less than the remaining charging time, the high-temperature charging time is predicted according to the high-temperature charging prediction model, and the remaining charging time is updated according to the high-temperature charging time and the target time.

5. The method for predicting remaining charging time of a vehicle according to claim 1, characterized in that, The target prediction model further includes a first low-temperature charging prediction model and a second low-temperature charging prediction model, and the method for predicting the remaining charging time of the vehicle further includes: When the charging vehicle is not in a battery preheating state or does not support the battery preheating function, the low-temperature charging time is predicted according to the first low-temperature charging prediction model. Update the second charging characteristic information when the low-temperature charging is completed based on the second low-temperature charging prediction model; The updated second charging feature information is input into the room temperature charging prediction model to predict the room temperature charging time. The remaining charging time of the vehicle is predicted based on the normal temperature charging time and the low temperature charging time.

6. The method for predicting remaining charging time of a vehicle according to any one of claims 1 to 5, characterized in that, The method for predicting the remaining charging time of a vehicle also includes: The battery type of the vehicle to be charged is determined based on the target vehicle model; Obtain the battery health status of the charging vehicle; The target compensation coefficient is determined based on the battery health status and the battery type. The remaining charging time is compensated according to the target compensation coefficient.

7. A charging pile, characterized in that, The device includes a memory and a processor, the processor being electrically connected to the memory for executing one or more computer programs stored in the memory, and, when executing the one or more computer programs, causing the charging pile to implement the vehicle remaining charging time prediction method as described in any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the vehicle remaining charging time prediction method as described in any one of claims 1 to 6.

Images