Method for predicting remaining charging duration of vehicle, and charging pile and storage medium

Abstract

The present invention relates to the technical field of new energy vehicle charging, and in particular relates to a method for predicting the remaining charging duration of a vehicle, and a charging pile and a storage medium. The method for predicting the remaining charging duration of a vehicle comprises: acquiring first charging feature information, second charging feature information and a charging mode; on the basis of the first charging feature information, determining a target vehicle type of a charging vehicle; on the basis of the target vehicle type and the charging mode, determining a target prediction model; and on the basis of the second charging feature information and the target prediction model, predicting the remaining charging duration of the charging vehicle. In the embodiment, a prediction model is generated for each charging mode of each type of vehicle, and the prediction model corresponding to the current charging mode of a charging vehicle is used to predict the remaining charging duration of the charging vehicle, which is conductive to improving the accuracy of predicting the remaining charging duration, thereby improving the use experience of a vehicle owner.

Description

Vehicle remaining charging duration prediction method, charging pile and storage medium

[0001] The present application claims priority to the Chinese patent application No. 202411374723.8, filed on September 29, 2024, and entitled "Vehicle remaining charging duration prediction method, charging pile and storage medium", the whole content of which is incorporated herein by reference. TECHNICAL FIELD

[0002] The present application relates to the field of new energy vehicle charging technology, in particular to a vehicle remaining charging duration prediction method, a charging pile and a storage medium. BACKGROUND

[0003] When the current charging pile charges the new energy vehicle, the charging pile can generally estimate the remaining charging duration of the new energy vehicle when the new energy vehicle is fully charged or charged to a certain amount of electricity according to the current electricity of the new energy vehicle, the current charging condition and other parameters, so as to facilitate the vehicle owner to reasonably arrange the charging time and the vehicle use time.

[0004] However, the charging efficiency of different vehicle models generally has differences, and even the charging efficiency of the same vehicle model under different charging modes also has differences. Since the current charging pile has not adjusted the prediction strategy of the remaining charging duration for these differences, the current charging pile is generally not accurate enough in predicting the remaining charging duration of the new energy vehicle, thereby affecting the use experience of the vehicle owner. SUMMARY

[0005] An object of the present application is to provide a vehicle remaining charging duration prediction method, a charging pile and a storage medium to solve the technical problem that the prediction of the vehicle remaining charging duration is not accurate enough.

[0006] In a first aspect, an embodiment of the present application provides a vehicle remaining charging duration prediction method, comprising:

[0007] obtaining first charging feature information, second charging feature information and a charging mode;

[0008] determining a target vehicle model of a charging vehicle according to the first charging feature information;

[0009] determining a target prediction model according to the target vehicle model and the charging mode;

[0010] predicting the remaining charging duration of the charging vehicle according to the second charging feature information and the target prediction model.

[0011] Optionally, the determining a target prediction model according to the target vehicle model and the charging mode comprises:

[0012] determining a candidate prediction model according to the target vehicle type;

[0013] determining a target prediction model in the candidate prediction model according to the charging mode.

[0014] Optionally, the predicting the remaining charging duration of the charging vehicle according to the second charging feature information and the target prediction model comprises:

[0015] obtaining a battery temperature of the charging vehicle;

[0016] judging whether the battery temperature is in a preset temperature range, to obtain a judgment result;

[0017] predicting the remaining charging duration of the charging vehicle according to the judgment result, the second charging feature information and the target prediction model.

[0018] Optionally, the target prediction model comprises a normal-temperature charging prediction model, and the predicting the remaining charging duration of the charging vehicle according to the judgment result, the second charging feature information and the target prediction model comprises:

[0019] if the judgment result is that the battery temperature is not in the preset temperature range, inputting the second charging feature information into the normal-temperature charging prediction model to predict the remaining charging duration of the charging vehicle.

[0020] Optionally, the target prediction model further comprises a high-temperature charging prediction model, and the vehicle remaining charging duration prediction method further comprises:

[0021] determining a battery temperature rising rate of the charging vehicle;

[0022] determining a target duration according to the battery temperature, the battery temperature rising rate and a first preset temperature threshold;

[0023] judging whether the target duration is less than the remaining charging duration;

[0024] if the target duration is less than the remaining charging duration, predicting a high-temperature charging duration according to the high-temperature charging prediction model, and updating the remaining charging duration according to the high-temperature charging duration and the target duration.

[0025] Optionally, the predicting the remaining charging duration of the charging vehicle according to the judgment result, the second charging feature information and the target prediction model comprises:

[0026] if the judgment result is that the battery temperature is in the preset temperature range, judging whether the charging vehicle supports a battery pre-heating function according to the target vehicle type;

[0027] when the charging vehicle supports a battery pre-heating function, determining whether the charging vehicle is in a battery pre-heating state;

[0028] when the charging vehicle is in the battery pre-heating state, determining a battery pre-heating mode;

[0029] predicting a remaining charging duration of the charging vehicle according to the battery pre-heating mode, the second charging feature information, and the target prediction model.

[0030] Optionally, the target prediction model comprises a pre-heating prediction model and a normal-temperature charging prediction model, and the predicting the remaining charging duration of the charging vehicle according to the battery pre-heating mode, the second charging feature information, and the target prediction model comprises:

[0031] determining a target pre-heating prediction model according to the battery pre-heating mode, the target pre-heating prediction model comprising a first pre-heating prediction model and a second pre-heating prediction model;

[0032] predicting a pre-heating duration according to the first pre-heating prediction model;

[0033] updating second charging feature information at a time when the battery pre-heating is completed according to the second pre-heating prediction model;

[0034] inputting the updated second charging feature information into the normal-temperature charging prediction model to predict a normal-temperature charging duration;

[0035] predicting the remaining charging duration of the charging vehicle according to the normal-temperature charging duration and the pre-heating duration.

[0036] Optionally, the target prediction model comprises a first low-temperature charging prediction model, a second low-temperature charging prediction model, and a normal-temperature charging prediction model, and the vehicle remaining charging duration prediction method further comprises:

[0037] when the charging vehicle is not in the battery pre-heating state or does not support the battery pre-heating function, predicting a low-temperature charging duration according to the first low-temperature charging prediction model;

[0038] updating second charging feature information at a time when the low-temperature charging is completed according to the second low-temperature charging prediction model;

[0039] inputting the updated second charging feature information into the normal-temperature charging prediction model to predict a normal-temperature charging duration;

[0040] predicting the remaining charging duration of the charging vehicle according to the normal-temperature charging duration and the low-temperature charging duration.

[0041] Optionally, the vehicle remaining charging duration prediction method further comprises:

[0042] determining a battery type of the charging vehicle according to the target vehicle model;

[0043] obtaining a battery health state of the charging vehicle;

[0044] determining a target compensation coefficient according to the battery health state and the battery type;

[0045] compensating the remaining charging duration according to the target compensation coefficient.

[0046] In a second aspect, an embodiment of the present application provides a charging pile, comprising a memory and a processor, the processor being electrically connected with the memory, used for executing one or more computer programs stored in the memory, and when the one or more computer programs are executed, the processor makes the charging pile implement the vehicle remaining charging duration prediction method as described above.

[0047] In a third aspect, an embodiment of the present application provides a computer readable storage medium, the computer readable storage medium storing a computer program, the computer program comprising program instructions, the program instructions making the processor execute the vehicle remaining charging duration prediction method as described above when the processor executes the program instructions.

[0048] Compared with the prior art, the embodiment of the present application provides a vehicle remaining charging duration prediction method, a charging pile and a storage medium, the vehicle remaining charging duration prediction method comprising: obtaining first charging feature information, second charging feature information and a charging mode, determining a target vehicle model of a charging vehicle according to the first charging feature information, determining a target prediction model according to the target vehicle model and the charging mode, and predicting a remaining charging duration of the charging vehicle according to the second charging feature information and the target prediction model. The embodiment generates a prediction model for each charging mode of each vehicle model, and predicts the remaining charging duration of the charging vehicle by using the prediction model corresponding to the current charging mode of the charging vehicle, which is beneficial to improve the prediction accuracy of the remaining charging duration, thereby improving the use experience of the vehicle owner. BRIEF DESCRIPTION OF DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the description of the embodiments of the present application. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without any creative labor.

[0050] FIG. 1 is a schematic diagram of an application scenario of a charging pile provided by an embodiment of the present application;

[0051] Fig. 2 is a flowchart of a vehicle remaining charging duration prediction method according to an embodiment of the present application;

[0052] Fig. 3 is a flowchart of S202 in a vehicle remaining charging duration prediction method according to an embodiment of the present application;

[0053] Fig. 4 is a flowchart of a vehicle remaining charging duration prediction method according to another embodiment of the present application;

[0054] Fig. 5 is a flowchart of S2022 in a vehicle remaining charging duration prediction method according to an embodiment of the present application;

[0055] Fig. 6 is a structural diagram of a vehicle remaining charging duration prediction device according to an embodiment of the present application;

[0056] Fig. 7 is a structural diagram of a second determination module in a vehicle remaining charging duration prediction device according to an embodiment of the present application;

[0057] Fig. 8 is a structural diagram of a vehicle remaining charging duration prediction device according to another embodiment of the present application;

[0058] Fig. 9 is a structural diagram of a first determination module in a vehicle remaining charging duration prediction device according to an embodiment of the present application;

[0059] Fig. 10 is a hardware structural diagram of a charging pile according to an embodiment of the present application. DETAILED DESCRIPTION

[0060] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application 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 only used to explain the present application and do not limit the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0061] It should be noted that the various features in the embodiments of the present application can be combined with each other without conflict, and all fall within the scope of protection of the present application. In addition, although the functional modules are divided in the device schematic diagram, and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from the module division in the device or the order in the flowchart. Furthermore, the "first", "second", "third" and the like used in the present application do not limit the data and execution order, but only distinguish the same items or similar items with basically the same function and effect.

[0062] Please refer to FIG. 1, an application scenario of a charging pile is provided, which includes a power grid 100, a charging pile 200 and a charging vehicle 300.

[0063] The power grid 100 is a power network for transmitting commercial power to the charging pile 200 through a transmission line to supply power to the charging vehicle 300. The commercial power is a power frequency alternating current, which is generally represented by three commonly used quantities of alternating current, i.e. voltage, current and frequency. Generally, the commercial power transmitted by the power grid 100 to the charging pile 200 is three-phase alternating current.

[0064] The charging pile 200 is a device for charging the charging vehicle 300 to supplement the electric quantity of the charging vehicle 300, which works by receiving electric energy from the power grid 100 and transmitting the electric energy to the charging vehicle 300 through a charging line to charge the charging vehicle 300. In some embodiments, the charging pile 200 can be any type of charging pile, such as a direct current charging pile, an alternating current charging pile, an alternating-direct current integrated charging pile, etc.

[0065] The direct current charging pile uses direct current to charge the power battery of the charging vehicle 300, and this charging method is also called "fast charging". The direct current charging pile is electrically connected with the power grid 100, can receive three-phase 380V alternating current input from the power grid 100 and convert the alternating current into direct current, which is delivered to the power battery of the charging vehicle 300 through a standard direct current charging plug and a charging socket to realize direct current charging. The power supply characteristics of the direct current charging pile itself determine that it can output sufficient charging power, and the adjustment range of voltage and current is relatively large, thereby realizing fast charging. The direct current charging pile has the function of a charging machine, can monitor and control the state of the charged power battery in real time, and can also measure the charging capacity.

[0066] The alternating current charging pile is electrically connected with the power grid 100, and is used to provide power output to the charging vehicle 300 through a single or double 220VAC / 380VAC alternating current output interface, so that the on-board charging machine of the charging vehicle 300 can charge the power battery of the charging vehicle 300. This charging method is also called "slow charging". The output power of the alternating current charging pile is generally 5kW (220VAC) / 20kW (380VAC), but the real charging power is restricted by the on-board charging machine, and the on-board charging power of a small electric vehicle is generally between 2kW and 3kW. The on-board charging machine of the charging vehicle 300 can convert the input alternating current into direct current through filtering and rectification, and then store the direct current into the power battery of the charging vehicle 300, thereby charging the charging vehicle 300. This charging method is mainly applied to small pure electric vehicles.

[0067] The input voltage of the AC-DC integrated charging pile is generally three-phase four-wire 380VAC±15%, and the frequency is 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 for the on-board charger of the charging vehicle 300. The AC-DC integrated charging pile can provide a conventional charging mode through the AC output port and a fast charging mode through the DC output port. When there are many charging services during the day, the fast charging mode is used for fast charging. When there are few users of the charging station at night, the conventional charging mode can be used for slow charging. The AC-DC integrated charging pile can realize simultaneous charging of AC and DC, interlocking charging, and modular design for easy maintenance.

[0068] In some embodiments, the charging pile 200 is configured with one or more charging guns, which are interface devices for connecting the charging pile 200 and the charging vehicle 300, and are mainly used to transmit electric energy to the charging vehicle 300 for charging. The charging gun usually has a plug and a connecting line, one end of which is connected to the charging pile, and the other end is inserted into the charging interface of the charging vehicle 300. According to different charging needs and technical standards, the charging gun can be divided into fast charging guns and slow charging guns.

[0069] The fast charging gun is also called a DC fast charging gun, which is usually used in fast charging sites and has a large power output, which can quickly charge the power battery of the charging vehicle 300.

[0070] The slow charging gun is also called an AC charging gun, which is usually used in household charging piles, commercial charging piles and public charging piles, has a low power, and is suitable for charging using ordinary household power, and the charging speed is relatively slow.

[0071] The charging vehicle 300 is in communication connection with the charging pile 200. On the one hand, the charging vehicle 300 can receive the DC power or AC power output by 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, various charging interaction information can be transmitted between the charging vehicle 300 and the charging pile 200.

[0072] The charging process of the charging vehicle 300 can include a charging parameter configuration phase and a charging phase.

[0073] The charging pile 200 is physically connected to the charging vehicle 300 and is powered on, and after checking that the voltage is normal, enters the charging parameter configuration phase. In this phase, the charging interaction information transmitted between the charging vehicle 300 and the charging pile 200 includes handshake messages, identity authentication messages, charging parameter negotiation messages and charging preparation messages.

[0074] 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, which is used to determine whether the handshake is normal between the two parties and indicates that the charging pile 200 is ready to configure the charging parameters. After the battery management system of the charging vehicle 300 receives the handshake request message, it 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, it determines that the handshake between the two parties is normal and establishes a communication connection between the two parties.

[0075] The identity authentication message is used to verify the identity of the charging pile 200. The identity authentication message includes an identity authentication request message and an identity authentication response message. The identity authentication request message is sent by the charging pile 200 to the battery management system of the charging vehicle 300, and the identity authentication request message includes the identity information of the charging pile 200. After the battery management system of the charging vehicle 300 receives the identity authentication request message, it sends an identity 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 the charging pile 200 receives the identity authentication response message, the identity verification of the charging pile 200 is completed.

[0076] The charging parameter negotiation message is used to negotiate the 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, and the charging parameter suggestion message includes the charging parameters suggested by the charging pile 200. The charging parameters include maximum charging voltage, maximum charging current, minimum charging voltage, minimum charging current, charging mode, etc. After the battery management system of the charging vehicle 300 receives the charging parameter suggestion message, it sends a charging parameter confirmation message to the charging pile 200, indicating that the battery management system of the charging vehicle 300 confirms the received charging parameters. After the charging pile 200 receives the charging parameter confirmation message, the charging parameter negotiation is completed.

[0077] The charging preparation message is used to indicate that the charging pile 200 is ready. The charging preparation message is sent by the charging pile 200 to the battery management system of the charging vehicle 300, indicating that the charging pile 200 is ready to start charging.

[0078] In 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 that the charging process proceeds normally. 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.

[0079] The charging control message is used to control the charging process. The charging control message can include a start charging command message, a stop charging command message, and a charging status report message. The start charging command message is sent by the charging pile 200 to the battery management system of the charging vehicle 300, and is used to instruct the battery management system of the charging vehicle 300 to start charging. The stop charging command message is sent by the charging pile 200 to the battery management system of the charging vehicle 300, and is used to instruct the battery management system of the charging vehicle 300 to stop charging. The charging status report message is sent by the battery management system of the charging vehicle 300 to the charging pile 200, and is used to report the charging status of the battery management system of the charging vehicle 300.

[0080] The charging data message is used to transmit charging data. The charging data message includes a charging voltage / current setting message and a battery voltage / current measurement message. The charging voltage / current setting message is sent by the charging pile 200 to the battery management system of the charging vehicle 300, and is used to set the charging voltage value and the charging current value. The battery voltage / current measurement message is sent by the battery management system of the charging vehicle 300 to the charging pile 200, and is used to report the battery voltage value and the battery current value of the charging vehicle 300.

[0081] The charging fault message is used to indicate charging-related faults. The charging fault message includes a charging fault message and a battery fault message. The charging fault message is sent by the charging pile 200 to the battery management system of the charging vehicle 300, and is used to indicate charging fault information. The battery fault message is sent by the battery management system of the charging vehicle 300 to the charging pile 200, and is used to indicate battery fault information.

[0082] The charging vehicle 300 includes any vehicle that can be driven by electric power, including but not limited to pure electric vehicles, hybrid electric vehicles, fuel cell vehicles, etc.

[0083] Referring to FIG. 2, the vehicle remaining charging duration prediction method provided by the embodiment of the present application comprises:

[0084] S201, obtaining first charging feature information, second charging feature information, and a charging mode;

[0085] In this step, the first charging feature information is information used to represent the charging properties or battery properties 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 that is currently using the charging pile for charging. When the charging pile charges the charging vehicle, as described above, the charging pile can receive the charging interaction information sent by the charging vehicle based on the interaction between the charging pile and the charging vehicle, and obtain the first charging feature information according to the charging interaction information.

[0086] The second charging feature information is information for representing a current charging state of the charging vehicle or a charging attribute of the charging pile, wherein the current charging state of the charging vehicle includes a current output power of the charging pile, a current state of charge of the charging vehicle, etc., and the charging attribute of the charging pile includes a maximum output power of the charging pile, etc.

[0087] The charging mode includes various power output modes in various charging types, wherein the charging types include fast charging, slow charging, etc., the power output modes in fast charging include 30kw, 60kw, 120kw, 240kw, 380kw, etc., and the power output modes in slow charging include 3.3kw, 6.6kw, 7kw, etc.

[0088] In S202, a target vehicle model of the charging vehicle is determined according to the first charging feature information.

[0089] In this step, the target vehicle model is a vehicle model number of the charging vehicle, which is a number composed of pinyin letters and Arabic numerals specified for a type of vehicle for identification. It can be understood that one vehicle model can correspond to multiple vehicles, but one vehicle can only correspond to one vehicle model.

[0090] In S203, a target prediction model is determined according to the target vehicle model and the charging mode.

[0091] In this step, the target prediction model is a prediction model corresponding to the current charging mode of the charging vehicle, which is used to predict the remaining charging duration of the charging vehicle. The remaining charging duration is the duration spent by the charging vehicle to charge from the current power to the preset power. The power is usually represented by the state of charge (SOC), which refers to the proportion of the available power in the battery to the nominal capacity. Assuming that the current power of the charging vehicle is 20% and the preset power is 80%, the remaining charging duration of the charging vehicle is the duration spent by the charging vehicle to charge from 20% to 80%. It can be understood that the preset power can be set according to actual needs, including but not limited to 70%, 80%, 90%, 100%, etc. The preset power can be set to one or more. When multiple preset powers are set, the charging pile can predict the remaining charging duration of the charging vehicle from the current power to each preset power according to the target prediction model, for example, the current power is 20%, and the preset powers are 80% and 100%. The charging pile can predict the remaining charging duration of the charging vehicle from 20% to 80% and from 20% to 100% according to the target prediction model, respectively.

[0092] The charging pile pre-acquires feature sample information of the charging vehicle in each charging mode of each vehicle type, classifies the feature sample information according to the vehicle type and the charging mode, for example, classifies the feature sample information of the vehicle type A1 in the charging mode B1 into one category, classifies the feature sample information of the vehicle type A1 in the charging mode B2 into another category, classifies the feature sample information of the vehicle type A2 in the charging mode B3 into another category, and so on. Then, the charging pile can clean the classified feature sample information to filter out data with low or no relevance to the remaining charging duration prediction, so as to more reliably generate a prediction model subsequently. Then, in each category of the cleaned feature sample information, the charging pile can associate the specified feature sample information with the remaining charging duration label to obtain a sample data set of each vehicle type in each charging mode. Finally, the charging pile can train the sample data set according to a preset machine learning algorithm such as a 1D-CNN (one-dimensional convolutional neural network) algorithm to generate a prediction model for each vehicle type in each charging mode.

[0093] In some embodiments, the charging pile can input a part of the sample data into the corresponding prediction model, acquire the remaining charging duration output by each prediction model, and calculate the error amount of the remaining charging duration and the actual remaining charging duration of the corresponding remaining charging duration label. The performance of the prediction model can be tested according to the error amount. It can be understood that when the error amount is small, the charging pile can directly use the prediction model for prediction, and when the error amount is large, the charging pile can retrain the prediction model until the generated prediction model meets the prediction requirements.

[0094] In some embodiments, the charging pile can determine a candidate prediction model according to the target vehicle type, and determine a target prediction model in the candidate prediction model according to the charging mode.

[0095] In this embodiment, the candidate prediction model includes prediction models generated by vehicles of the target vehicle type based on different charging modes. The charging pile can select a prediction model matching the current charging mode of the charging vehicle as the target prediction model in the candidate prediction model.

[0096] S204, predicting the remaining charging duration of the charging vehicle according to the second charging feature information and the target prediction model.

[0097] Therefore, the embodiment generates a prediction model for each charging mode of each vehicle type, and predicts the remaining charging duration of the charging vehicle by using the prediction model corresponding to the current charging mode of the charging vehicle, which is beneficial to improve the prediction accuracy of the remaining charging duration, thereby improving the use experience of the vehicle owner.

[0098] In some embodiments, the charging pile acquires a battery temperature of the charging vehicle, determines whether the battery temperature is in a preset temperature range, obtains a determination result, and predicts the remaining charging duration of the charging vehicle according to the determination result, the second charging feature information, and a target prediction model.

[0099] In this embodiment, the preset temperature range is a range in which the temperature is relatively low for the power battery, for example, the preset temperature range is 0-15 DEG C. The charging pile can select an optimal prediction strategy according to the battery temperature to predict the remaining charging duration of the charging vehicle, thereby improving the prediction accuracy of the remaining charging duration.

[0100] In some embodiments, the target prediction model includes a normal-temperature charging prediction model.

[0101] The normal-temperature charging prediction model is a prediction model for predicting a normal-temperature charging duration of the charging vehicle, and the normal-temperature charging duration is a duration spent by the charging vehicle to charge to a preset power level from a normal battery temperature.

[0102] In some embodiments, if the determination result is that the battery temperature is not in the preset temperature range, the second charging feature information is input to the normal-temperature charging prediction model to predict the remaining charging duration of the charging vehicle.

[0103] If the battery temperature of the charging vehicle does not fall into the preset temperature range, it indicates that the battery temperature is normal. In this case, the charging pile can directly predict the normal-temperature charging duration according to the currently acquired second charging feature information and the normal-temperature charging prediction model, and use the normal-temperature charging duration as the remaining charging duration of the charging vehicle.

[0104] It can be understood that if the charging vehicle is charged after a long time of running and the ambient temperature is relatively high when the charging vehicle is charged, there may be a situation that the battery temperature is too high at a future time point during the charging process of the charging vehicle. The battery temperature that is too high will affect the charging efficiency of the charging vehicle. Therefore, the charging pile can predict the time point at which the battery temperature is too high, divide different charging time periods according to the time point, that is, a charging time period before the battery temperature is too high and a charging time period after the battery temperature is too high, and adjust the remaining charging duration of the charging vehicle in real time according to the charging durations of the different charging time periods.

[0105] In some embodiments, the high-temperature charging prediction model is a prediction model for predicting a high-temperature charging duration of the charging vehicle, and the high-temperature charging duration is a duration spent by the charging vehicle to charge to a preset power level from a state in which the battery temperature is at a high temperature.

[0106] In some embodiments, the charging pile can determine a battery temperature rise rate of the charging vehicle, determine a target duration according to the battery temperature, the battery temperature rise rate, and a first preset temperature threshold, determine whether the target duration is less than a remaining charging duration, if less than the remaining charging duration, predict a high-temperature charging duration according to a high-temperature charging prediction model, and update the remaining charging duration according to the high-temperature charging duration and the target duration.

[0107] In some embodiments, the charging pile can obtain the battery temperature of the charging vehicle at intervals, obtain a temperature difference value by subtracting two adjacent battery temperatures, and obtain the battery temperature rise rate by dividing the temperature difference value by the interval between the times at which the two adjacent battery temperatures are obtained.

[0108] In some embodiments, the target duration is the duration predicted by the charging pile to continuously charge from the current battery temperature until the battery temperature reaches the first preset temperature threshold. The charging pile can obtain a temperature difference value by subtracting the first preset temperature threshold from the current battery temperature, and obtain the target duration by multiplying the temperature difference value by the battery temperature rise rate.

[0109] If the target duration is greater than or equal to the remaining charging duration, it means that there will be no case of excessively high temperature within the remaining charging duration when the charging vehicle charges from the current power to the preset power, so the charging pile does not need to consider the impact of excessively high temperature on the prediction of the remaining charging duration, and can directly use the predicted remaining charging duration.

[0110] If the target duration is less than the remaining charging duration, it means that there may be a case of excessively high temperature within the remaining charging duration when the charging vehicle charges from the current power to the preset power, so the charging pile needs to consider the impact of excessively high temperature on the prediction of the remaining charging duration.

[0111] In some embodiments, the charging pile can input the charging characteristic information such as the state of charge and the battery temperature when the battery temperature is excessively high into the high-temperature charging prediction model to predict the high-temperature charging duration, which is the duration taken by the charging vehicle to charge from the battery power when the battery temperature is excessively high to the preset power. The charging pile can pre-sample the characteristics such as the state of charge and the battery temperature when each vehicle of each vehicle type is in each charging mode during high-temperature charging, associate the characteristic sampling information with the duration label to obtain a sample data set, and train the sample data set according to a preset machine learning algorithm to obtain the high-temperature charging prediction model.

[0112] In some embodiments, the charging pile can update the remaining charging duration by summing the high-temperature charging duration and the target duration.

[0113] For example, the current battery temperature is 40℃, the current power is 25%, the preset power is 80%, the first preset temperature threshold is 60℃, the charging pile currently predicts that the remaining charging time is 2 hours, and the charging pile predicts that the battery temperature reaches 60℃ after 1 hour and 50 minutes of the target time. According to the high-temperature charging prediction model, the charging pile predicts the high-temperature charging time from 60℃ when the battery temperature is 60℃ to the preset power. Assuming that the high-temperature charging time is 20 minutes, the charging pile adds the target time of 1 hour and 50 minutes to the high-temperature charging time of 20 minutes to obtain the updated remaining charging time of 2 hours and 10 minutes.

[0114] Therefore, the embodiment can timely adjust the prediction strategy of the remaining charging time when the battery temperature is too high during the charging process, which is beneficial to improve the prediction reliability and accuracy of the remaining charging time.

[0115] It can be understood that when the ambient temperature is too low, the chemical reaction speed of the power battery of the new energy vehicle will slow down, which may cause the power battery to be unable to fully absorb the charging energy, resulting in insufficient charging and affecting the charging efficiency. In order to improve the charging efficiency of the power battery at low temperature, some new energy vehicles support battery preheating. Through battery preheating, the temperature of the power battery can be adjusted to an appropriate range when the temperature of the power battery is too low, so as to improve the charging efficiency and safety. Since whether the new energy vehicle supports battery preheating and whether the new energy vehicle supporting battery preheating turns on the battery preheating will affect the temperature of the power battery, thereby affecting the charging rate and further affecting the remaining charging time, the charging pile can adopt different prediction strategies for the remaining charging time according to different situations.

[0116] In some embodiments, if the judgment result is that the battery temperature is in the preset temperature range, it is judged whether the charging vehicle supports the battery preheating function according to the target vehicle type. When the charging vehicle supports the battery preheating function, it is judged 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.

[0117] In the embodiment, the battery preheating function is a function for increasing the temperature of the battery to reach an optimal working temperature range. The battery preheating function can be implemented through different battery preheating modes, including an external heating mode, an internal heating mode, and an internal-external heating mode. The external heating mode refers to a mode in which the charging vehicle heats the power battery through a preheating device such as a PTC (Positive Temperature Coefficient) heating element, a heating film, or a liquid circulation heating system. The internal heating mode refers to a mode in which the power battery itself is heated by stimulating the internal chemical substances of the power battery through alternating current. The internal-external heating mode refers to a mode in which the power battery is heated through both the external heating mode and the internal heating mode.

[0118] It should be noted that when the charging vehicle is in the battery preheating state, the charging pile can charge the power battery of the charging vehicle regardless of the current battery preheating mode.

[0119] In some embodiments, the target prediction model includes a preheating prediction model and a normal-temperature charging prediction model.

[0120] The preheating prediction model is a prediction model for predicting the preheating duration of the charging vehicle, which is the duration taken by 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℃. The specific description of the normal-temperature charging prediction model can refer to the above-mentioned embodiments, which will not be repeated here.

[0121] In some embodiments, the charging pile can determine the target preheating prediction model according to 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 according to the first preheating prediction model. The second charging feature information at the time when the battery preheating is completed is updated according to the second preheating prediction model. The updated second charging feature 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 according to the normal-temperature charging duration and the preheating duration.

[0122] In the 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 feature information at the time when the battery preheating is completed. The remaining charging duration of the charging vehicle is the sum of the normal-temperature charging duration and the preheating duration. 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, which is the battery temperature when the battery temperature is normal.

[0123] The charging pile can obtain battery temperature, ambient temperature, state of charge and other characteristic sampling information when each vehicle of each vehicle type is in each battery preheating mode of the battery preheating state. On the one hand, the charging pile associates the characteristic sampling information with a time length label to obtain a sample data set, and trains the sample data set according to a preset machine learning algorithm to obtain a first preheating prediction model. On the other hand, the charging pile associates the characteristic sampling information with a state of charge label to obtain a sample data set, and trains the sample data set according to a preset machine learning algorithm to obtain a second preheating prediction model. The state of charge label is used to identify the state of charge when the battery temperature reaches a second preset temperature threshold.

[0124] 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 length.

[0125] The charging pile can extract charging characteristic information such as state of charge, battery temperature and ambient temperature from the charging interaction information and input the charging characteristic information into the second preheating prediction model to predict the state of charge when the battery preheating is completed and update the second charging characteristic information with the state of charge, for example, update the currently obtained state of charge in the second charging characteristic information to the state of charge when the battery preheating is completed.

[0126] It can be understood that since the preheating time length is different when the same vehicle type vehicle is in different battery preheating modes, and different preheating time lengths will affect the prediction of the remaining charging time length, the charging pile can adopt different preheating time length prediction strategies in combination with different battery preheating modes.

[0127] Therefore, the embodiment can predict the remaining charging time length of the charging vehicle when the charging vehicle is in the battery preheating state, can provide more comprehensive charging services for the vehicle owner, and thus improve the use experience of the vehicle owner.

[0128] It can be understood that when the battery temperature of the charging vehicle is low, if the charging vehicle is not in the battery preheating state or does not support the battery preheating function, the battery temperature of the charging vehicle gradually increases during the charging process of the charging pile. 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 of different charging periods may be affected by different factors, the charging pile can predict the charging time length of different charging periods, and then predict the remaining charging time length of the charging vehicle according to the charging time length of each charging period.

[0129] In some embodiments, 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.

[0130] In the embodiment, the first low-temperature charging prediction model is a prediction model for predicting the charging duration (low-temperature charging duration) of the charging vehicle in a charging period with a low battery temperature, and the second low-temperature charging prediction model is a prediction model for updating the second charging feature information of the charging vehicle at the end of the charging period with a low battery temperature (low-temperature charging completion). The specific description of the normal-temperature charging prediction model can refer to the above embodiments, which will not be described here.

[0131] In some embodiments, if the charging vehicle is not in the battery preheating state or does not support the battery preheating function, the charging pile predicts the low-temperature charging duration according to the first low-temperature charging prediction model, updates the second charging feature information at the low-temperature charging completion according to the second low-temperature charging prediction model, inputs the updated second charging feature information into the normal-temperature charging prediction model, predicts the normal-temperature charging duration, and predicts the remaining charging duration of the charging vehicle according to the normal-temperature charging duration and the low-temperature charging duration.

[0132] In the embodiment, the charging pile can extract charging feature information such as the state of charge, charging power, etc. 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 duration. Then, the charging pile inputs charging feature information such as the state of charge, battery temperature, ambient temperature, etc. into the second low-temperature charging prediction model to predict the state of charge at the low-temperature charging completion and update the second charging feature information by the state of charge, for example, update the current acquired state of charge in the second charging feature information to the state of charge at the low-temperature charging completion, and input the updated second charging feature information into the normal-temperature charging prediction model to predict the normal-temperature charging duration. Finally, the charging pile can take the sum of the normal-temperature charging duration and the low-temperature charging duration as the remaining charging duration of the charging vehicle.

[0133] Therefore, the embodiment can divide the charging process of the charging vehicle into different charging stages according to the battery temperature, predict the charging duration of each charging stage, and predict the remaining charging duration of the charging vehicle according to the charging duration of each charging stage, which is beneficial to more accurately predict the remaining charging duration.

[0134] It can be understood that the charging efficiency of the charging vehicle is usually affected by static parameters such as the type and use of the power battery of the charging vehicle, i.e., different battery types and different use conditions also affect the prediction of the remaining charging duration by the charging pile. Therefore, the charging pile can correct the corrected charging duration in combination with the battery type and use condition of the charging vehicle.

[0135] In some embodiments, the charging pile determines the battery type of the charging vehicle according to the target vehicle model, acquires the battery health status of the charging vehicle, determines the target compensation coefficient according to the battery health status and the battery type, and compensates the remaining charging duration according to the target compensation coefficient.

[0136] For example, the remaining charging duration is 2 hours, the charging pile is configured with a preset mapping relationship table between different battery health statuses and different battery types and compensation coefficients, the charging pile can query the preset mapping relationship table according to the battery type and the battery health status of the charging vehicle, take the compensation coefficient corresponding to the battery type and the battery health status of the charging vehicle in the preset mapping relationship table as the target compensation coefficient, and assume that the target compensation coefficient is 1.1. Then, the charging pile can multiply the remaining charging duration of 2 hours by the target compensation coefficient of 1.1 to obtain 2 hours and 12 minutes, and correct the remaining charging duration of 2 hours to 2 hours and 12 minutes.

[0137] Therefore, the embodiment can correct the remaining charging duration according to the battery condition of the charging vehicle, and improve the prediction reliability and accuracy of the remaining charging duration.

[0138] In some embodiments, referring to FIG. 3, S202 includes:

[0139] S2021, input the first charging feature information into the vehicle model prediction model, and obtain a vehicle model prediction result by prediction.

[0140] In this step, the vehicle model prediction model is an algorithm model for predicting the vehicle model of the charging vehicle. The vehicle model prediction model can be any suitable type of algorithm model, including but not limited to a decision tree model, a random forest model, a logistic regression model, a neural network model, a support vector machine model, etc.

[0141] The vehicle model prediction result is a prediction result output by the vehicle model prediction model. In some embodiments, the vehicle model prediction result includes at least one vehicle model label. The vehicle model label is a classification label for uniquely determining the target vehicle model. The vehicles of each vehicle model correspond to at most one vehicle model label.

[0142] Since the vehicle model label of the vehicle model prediction result can be 1 or more than 1, the number of vehicle model labels will affect the determination strategy of the charging pile for determining the vehicle model of the charging vehicle. Therefore, when the charging pile determines the vehicle model of the charging vehicle according to the vehicle model prediction result, it is necessary to first count the number of vehicle model labels of the vehicle model prediction result.

[0143] It can be understood that when the vehicle type prediction result output by the vehicle type prediction model only includes one vehicle type label, the charging pile can directly determine the vehicle type of the charging vehicle according to the unique vehicle type label, and when the vehicle type prediction result output by the vehicle type prediction model includes more than one vehicle type label, the charging pile fails to directly determine the vehicle type of the charging vehicle, at which time the charging pile needs to further determine the target vehicle type of the charging vehicle.

[0144] For example, A1 vehicle of A brand vehicle manufacturer and B1 vehicle of B brand vehicle manufacturer both use the same battery management system produced by the same equipment manufacturer, and because the same battery management system is used, the first charging feature information carried in the charging interaction information sent to the charging pile when the A1 vehicle and the B1 vehicle are charging may be the same. After the first charging feature information is input into the vehicle type prediction model, the vehicle type prediction result output by the vehicle type prediction model may include the vehicle type label corresponding to the A1 vehicle and the vehicle type label corresponding to the B1 vehicle, at which time the charging pile cannot directly determine whether the charging vehicle is the A1 vehicle or the B1 vehicle.

[0145] It can be understood that the prediction process of the vehicle type prediction model is a vehicle type preliminary identification stage, and in the vehicle type preliminary identification stage, the charging pile can directly locate the vehicle type of the charging vehicle. For example, in the case where the vehicle type prediction result only includes one vehicle type label, the charging pile can also fail to directly locate the vehicle type of the charging vehicle. For example, in the case where the vehicle type prediction result includes more than one vehicle type label.

[0146] S2022, determining the target vehicle type of the charging vehicle according to the vehicle type prediction result.

[0147] In this step, the target vehicle type is the vehicle model of the charging vehicle, and the vehicle model is a number composed of pinyin letters and Arabic numerals specified for a type of vehicle for identifying the vehicle. It can be understood that one vehicle type can correspond to multiple vehicles, but one vehicle can only correspond to one vehicle type.

[0148] Therefore, the embodiment can automatically identify the target vehicle type of the charging vehicle when charging the charging vehicle, which is conducive to subsequently locating a prediction model for predicting the remaining charging duration of the charging vehicle in combination with the target vehicle type, thereby facilitating reliable prediction of the remaining charging duration of the charging vehicle.

[0149] In some embodiments, referring to FIG. 4, before S2021 is performed, the vehicle remaining charging duration prediction method further includes:

[0150] S2023, obtaining feature sampling information of the charging vehicle of each vehicle type;

[0151] In this step, the feature sampling information is the charging feature information obtained by pre-sampling each vehicle model when the charging pile charges or tests each vehicle model. These vehicle models can include vehicles of different brands, vehicles of the same brand but different series, vehicles of the same brand and the same series but different models, vehicles of the same brand, the same series and the same model but different production years, etc.

[0152] S2024, associate the feature sampling information with the preset vehicle model label to obtain a sample data set;

[0153] In this step, the preset vehicle model label is a vehicle model label used to pre-classify different vehicle models. The charging pile associates the feature sampling information obtained from each vehicle model with the preset vehicle model label of the corresponding vehicle model to obtain sample data for each vehicle model. For example, the sample data for one vehicle model is as follows:

[0154] {

[0155] "CC1":"XXX",

[0156] "CC2":XXX,

[0157] "CC3":XXX,

[0158] "CC4":XXX,

[0159] "CC5":XXX,

[0160] "VehicleLabel":"XXX"

[0161] }

[0162] Wherein, CC1, CC2, CC3, CC4 and CC5 represent five feature parameters, and VehicleLabel represents the preset vehicle model label.

[0163] The charging pile aggregates the sample data for various vehicle models to obtain a sample data set.

[0164] S2025, train the sample data set according to the preset machine learning algorithm to obtain a vehicle model prediction model.

[0165] In this step, the type of the preset machine learning algorithm can be set according to actual needs, including but not limited to a decision tree algorithm, a random forest algorithm, a logistic regression algorithm, a neural network algorithm, a support vector machine algorithm, etc. The above 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 data set, and then input the sample data set for training. After the training is completed, the machine learning algorithm library gives an optimal prediction model, which is used as the vehicle type prediction model by the charging pile.

[0166] Since the vehicle type prediction model is trained by the sample data set composed of sample data of various vehicle types, the vehicle type prediction model can cover vehicle type prediction of various vehicle types, and when a new vehicle type appears subsequently, the vehicle type prediction model can be further trained to expand the vehicle type, thereby facilitating the charging pile to accurately and reliably predict the vehicle type of the charging vehicle currently being charged.

[0167] In some embodiments, the vehicle type prediction result includes at least one vehicle type label. Referring to FIG. 5, S2022 includes:

[0168] S20221, determining the number of vehicle type labels of the vehicle type prediction result.

[0169] In this step, as described above, in the vehicle type preliminary identification stage, the number of vehicle type labels of the vehicle type prediction result output by the vehicle type prediction model is one or more than one.

[0170] S20222, determining the target vehicle type of the charging vehicle according to the number of vehicle type labels of the vehicle type prediction result and the vehicle type labels.

[0171] In this step, when the number of vehicle type labels is more than one, the charging pile may not be able to clearly distinguish the specific vehicle type of the charging vehicle. Therefore, after the vehicle type prediction model outputs the vehicle type prediction result, the charging pile needs to determine the number of vehicle type labels of the vehicle type prediction result. When the number of vehicle type labels is one, the vehicle type fine identification stage is not needed, and when the number of vehicle type labels is more than one, the vehicle type fine identification stage is needed, so as to accurately locate the target vehicle type of the charging vehicle.

[0172] In some embodiments, the charging pile determines whether the number of vehicle type labels is greater than one to obtain a determination result, and determines the target vehicle type of the charging vehicle according to the determination result and the vehicle type labels of the vehicle type prediction result.

[0173] Therefore, the embodiment can flexibly select the prediction strategy of the target vehicle type according to the number of vehicle type labels, which is beneficial to improve the reliability and accuracy of the vehicle type prediction of the charging vehicle.

[0174] In some embodiments, the vehicle type label can include vehicle type information, which is information used to uniquely determine a corresponding vehicle type, and can also include vehicle type information and battery pack capacity information, which is information used to indicate the design capacity of a power battery pack of a vehicle type vehicle when it is shipped.

[0175] In some embodiments, if the result of the determination is that the number of vehicle type labels is not greater than 1, the charging pile determines the target vehicle type of the charging vehicle according to the vehicle type information corresponding to the vehicle type label.

[0176] For example, assume that the vehicle type prediction model outputs the following vehicle type prediction results:

[0177] VehicleLabel_1: A1_120kWh

[0178] In the vehicle type label "VehicleLabel_1", A1 is the vehicle type information, and 120kWh is the battery pack capacity information of the A1 vehicle type vehicle.

[0179] Since the vehicle type prediction result only includes one vehicle type label VehicleLabel_1, the charging pile can determine the vehicle type information A1 in the vehicle type label as the target vehicle type of the charging vehicle.

[0180] In some embodiments, if the result of the determination is that the number of vehicle type labels is greater than 1, the battery pack capacity information of each vehicle type label is extracted respectively, and the target vehicle type of the charging vehicle is determined according to the battery pack capacity information and the vehicle type information.

[0181] For example, assume that the vehicle type prediction model outputs the following vehicle type prediction results:

[0182] VehicleLabel_2: B1_70kWh

[0183] VehicleLabel_3: C1_100kWh

[0184] In the vehicle type label "VehicleLabel_2", B1 is the vehicle type information, and 70kWh is the battery pack capacity information of the B1 vehicle type vehicle. In the vehicle type label "VehicleLabel_3", C1 is the vehicle type information, and 100kWh is the battery pack capacity information of the C1 vehicle type vehicle.

[0185] Since the vehicle type prediction result includes two vehicle type labels VehicleLabel_2 and VehicleLabel_3, the number of vehicle type labels is 2, which is greater than 1, the charging pile extracts the battery pack capacity information 70kWh and 100kWh corresponding to the vehicle type labels VehicleLabel_1 and VehicleLabel_2 respectively, and determines the target vehicle type of the charging vehicle according to the two battery pack capacity information and the corresponding vehicle type information.

[0186] Therefore, the embodiment can clearly distinguish the target vehicle type of the charging vehicle when there are multiple vehicle type labels in the vehicle type prediction result, which is beneficial to improve the reliability and accuracy of vehicle type identification.

[0187] In some embodiments, the charging pile can determine whether the battery pack capacity information is different, and determine the target vehicle type of the charging vehicle according to the determination result.

[0188] The difference in battery pack capacity information can be that each battery pack capacity information in the multiple battery pack capacity information is different, or that there are the same battery pack capacity information and different battery pack capacity information in the multiple battery pack capacity information, as long as all the battery pack capacity information is not the same. For example, as described above, the charging pile extracts the battery pack capacity information 70kWh corresponding to the vehicle type label VehicleLabel_2 and the battery pack capacity information 100kWh corresponding to the vehicle type label VehicleLabel_3, and the charging pile can determine that the battery pack capacity information is different.

[0189] For another example, assume that the vehicle type prediction model outputs the following vehicle type prediction result:

[0190] VehicleLabel_4: D1_80kWh

[0191] VehicleLabel_5: E1_80kWh

[0192] Since the battery pack capacity information corresponding to the vehicle type labels VehicleLabel_4 and VehicleLabel_5 is 80kWh, the charging pile can determine that the battery pack capacity information is different.

[0193] If the battery pack capacity information is different, the charging pile can determine the actual battery pack capacity of the charging vehicle, determine the target vehicle type label according to the actual battery pack capacity, and determine the target vehicle type of the charging vehicle according to the vehicle type information corresponding to the target vehicle type label.

[0194] If the battery pack capacity information has no difference, the charging pile can determine a charging curve feature of the charging vehicle, determine a target vehicle model label according to the charging curve feature, and determine a target vehicle model of the charging vehicle according to vehicle model information corresponding to the target vehicle model label.

[0195] In some embodiments, when determining the actual battery pack capacity of the charging vehicle, the charging pile calculates a battery charging capacity required for charging the charging vehicle by a preset percentage of power, averages the battery charging capacity to obtain an average power value, and determines the actual battery pack capacity of the charging vehicle according to the average power value and a preset value.

[0196] In this embodiment, the product of the preset value and the preset percentage is equal to 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 the power of one hundred percent is the state of the charging vehicle being fully charged.

[0197] Taking one percent as the preset percentage for example, first, since the charging current and the charging voltage during the charging process of the charging vehicle are real-time changes, the charging pile can integrate the battery charging capacity in the integral interval of the preset time length. For example, the integral interval is 1 second, and the charging pile can calculate the battery charging capacity charged every second, and then accumulate the battery charging capacity charged every second until the battery charging capacity changes by one percent of the power. In some embodiments, the charging pile can calculate the battery charging capacity required for charging the charging vehicle by a preset percentage of power according to the following formula: Cap = Q1 + Q2 + Q3 + … + Qn Q1 = v1 * c1 * t Q2 = v2 * c2 * t Q3 = v3 * v3 * t Qn = vn * cn * t

[0198] Wherein, Cap represents the battery charging capacity required for charging the charging vehicle by a preset percentage of power, Qn represents the battery charging capacity charged in the nth integral interval, vn represents the charging voltage for charging the charging vehicle during the nth integral interval, cn represents the charging current for charging the charging vehicle during the nth integral interval, and t represents the time length of the integral interval.

[0199] Then, the charging pile can accumulate a plurality of battery charging capacities required for charging the charging vehicle by a preset percentage of power according to actual needs, and average the battery charging capacity to obtain an average power value. In some embodiments, the charging pile can calculate the average power value according to the following formula: Cap av = (Cap1 + Cap2 + … + Capn) / n

[0200] Finally, the charging pile multiplies the average value of the charging power by a preset value to obtain the actual battery pack capacity of the charging vehicle. It can be understood that, as mentioned above, the preset value can be set according to the preset percentage, as long as the product of the preset value and the preset percentage is equal to 1.

[0201] Therefore, by estimating the actual battery pack capacity of the charging vehicle by integrating the charging power, the embodiment avoids introducing estimation errors due to real-time changes in charging current and charging voltage during the charging process of the charging vehicle, thereby more accurately estimating the true battery pack capacity of the charging vehicle, and further facilitating more reliable subsequent vehicle type prediction of the charging vehicle.

[0202] In some embodiments, the charging pile matches the actual battery pack capacity with the battery pack capacity information corresponding to each vehicle type label respectively, and determines that the vehicle type label corresponding to the matching successful battery pack capacity information as the target vehicle type label, and determines the target vehicle type of the charging vehicle according to the vehicle type information corresponding to the target vehicle type label.

[0203] It can be understood that, if the actual battery pack capacity is consistent with the battery capacity information corresponding to a certain vehicle type label, it is determined that the battery capacity information is matching successful battery capacity information, or if the difference between the actual battery pack capacity and the battery capacity information corresponding to a certain vehicle type label is within a preset range, it is determined that the battery capacity information is matching successful battery capacity information.

[0204] For example, the actual battery pack capacity is 99 kWh, as mentioned above, the vehicle type label of the vehicle type prediction result is VehicleLabel_2 and VehicleLabel_3, and the battery pack capacity information corresponding to the two vehicle type labels is 120 kWh, 70 kWh and 100 kWh respectively. Since the difference between the actual battery pack capacity 99 kWh and 100 kWh is within the preset range ± 1 kWh, the charging pile can determine that 100 kWh is the matching successful battery capacity information, and the vehicle type information C1 corresponding to 100 kWh is determined as the target vehicle type of the charging vehicle.

[0205] Since the battery pack capacity of vehicles of different vehicle types is generally different, the charging pile can estimate the actual battery pack capacity of the charging vehicle to uniquely identify the vehicle type of the charging vehicle, which can avoid the charging pile reliably identifying the target vehicle type of the charging vehicle when the charging pile cannot directly obtain the battery pack capacity of the charging vehicle.

[0206] It can be understood that, although there are differences in battery pack capacity information, in the case that the vehicle type prediction model outputs multiple vehicle type labels, there may be a case that the battery pack capacity information corresponding to two or more vehicle type labels is the same. For example, the vehicle type prediction model outputs the following vehicle type prediction results:

[0207] VehicleLabel_6: D1_80kWh

[0208] VehicleLabel_7: E1_80kWh

[0209] VehicleLabel_8: F1_90kWh

[0210] If the actual battery pack capacity estimated by the charging pile is 80kWh, the battery pack capacity information corresponding to the vehicle labels VehicleLabel_6 and VehicleLabel_7 is 80kWh, at this time, the charging pile cannot directly determine whether the vehicle model of the charging vehicle is D1 or E1, therefore, in some embodiments, when the battery pack capacity information is different, but the charging pile cannot determine the target vehicle model of the charging vehicle according to the actual battery pack capacity, the charging pile can determine the charging curve characteristics of the charging vehicle, and determine the target vehicle model of the charging vehicle according to the charging curve characteristics.

[0211] In some embodiments, when determining the charging curve characteristics of the charging vehicle, the charging pile can obtain dynamic charging characteristic information at multiple time points during the process of charging the charging vehicle by a preset percentage of electric quantity (for example, ten percent), and fit the dynamic charging characteristic information into a charging curve according to any suitable curve fitting algorithm, so as to obtain the charging curve characteristics, wherein the dynamic charging characteristic information can include any suitable charging characteristic information such as required current.

[0212] In some embodiments, the charging pile inputs the charging curve characteristics into the auxiliary prediction model, obtains an auxiliary prediction result by prediction, and determines the target vehicle model of the charging vehicle according to the auxiliary prediction result.

[0213] In this embodiment, the auxiliary prediction model is an algorithm model used by the auxiliary vehicle model prediction model to predict the vehicle model of the charging vehicle. In some embodiments, the charging pile pre-obtains dynamic charging characteristic information of the charging vehicle during the charging process of each vehicle model, and fits the dynamic charging characteristic information into a sample charging curve according to any suitable curve fitting algorithm, then associates the sample charging curve with a preset vehicle label to obtain a sample data set, and finally trains the sample data set according to a preset machine learning algorithm to obtain the auxiliary prediction model.

[0214] In some embodiments, the auxiliary prediction result includes at least one auxiliary prediction label, and the auxiliary prediction label 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 according to the vehicle model information corresponding to the auxiliary prediction label.

[0215] In some embodiments, the charging pile can determine the target vehicle model of the charging vehicle according to the vehicle label of the auxiliary prediction result and the vehicle label of the vehicle model prediction result.

[0216] For example, as described above, the vehicle type prediction result includes the following vehicle type labels:

[0217] VehicleLabel_4: D1_80kWh

[0218] VehicleLabel_5: E1_80kWh

[0219] Suppose the auxiliary prediction result includes the following auxiliary prediction labels:

[0220] AuxiliaryLabel_1: E1

[0221] AuxiliaryLabel_2: G1

[0222] The charging pile can extract the vehicle type information corresponding to each vehicle type label and the vehicle type information corresponding to each auxiliary prediction label respectively, and sequentially compare each vehicle type information corresponding to the vehicle type information with the vehicle type information corresponding to each auxiliary prediction label, and take the vehicle type information that is consistent as the target vehicle type of the charging vehicle. As described above, the charging pile can compare the vehicle type information D1 with the vehicle type information E1 and G1 respectively, at this time, the vehicle type information fails to be consistent, then the charging pile can compare the vehicle type information E1 with the vehicle type information E1 and G1 respectively, at this time, the vehicle type information E1 is consistent, and the charging pile can determine that the vehicle type information E1 is the target vehicle type of the charging vehicle.

[0223] Therefore, the embodiment can verify the vehicle type label of the auxiliary prediction result and the vehicle type label of the vehicle type prediction result, and determine the target vehicle type of the charging vehicle according to the verification result, so as to more accurately and reliably identify the target vehicle type of the charging vehicle.

[0224] It should be noted that in the above various embodiments, there is no certain sequence between the above steps, and those skilled in the art can understand from the description of the embodiments of the present application that the above steps can have different execution sequences in different embodiments, that is, they can be executed in parallel, or they can be executed in exchange, etc.

[0225] As another aspect of the embodiments of the present application, the embodiments of the present application provide a vehicle remaining charging duration prediction device. The vehicle remaining charging duration prediction device can be a software module, which includes a plurality of instructions stored in a memory, and a processor can access the memory to call and execute the instructions to complete the vehicle remaining charging duration prediction method described in the above various embodiments.

[0226] In some embodiments, the vehicle remaining charging duration prediction apparatus can be built by hardware devices, for example, the vehicle remaining charging duration prediction apparatus can be built by one or more chips, and each chip can work in coordination with each other to complete the vehicle remaining charging duration prediction method described in each of the above embodiments. For another example, the vehicle remaining charging duration prediction apparatus can also be built by a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a single-chip microcomputer, an ARM (Acorn RISC Machine), a programmable logic device, a discrete gate or transistor logic, a discrete hardware component, or any combination of these components.

[0227] In some embodiments, referring to FIG. 6, the vehicle remaining charging duration prediction apparatus 600 provided by the embodiment of the present application includes a first acquisition module 601, a first determination module 602, a second determination module 603, and a prediction module 604.

[0228] The first acquisition module 601 is configured to acquire first charging feature information, second charging feature information, and a charging mode, the first determination module 602 is configured to determine a target vehicle model of a charging vehicle according to the first charging feature information, the second determination module 603 is configured to determine a target prediction model according to the target vehicle model and the charging mode, and the prediction module 604 is configured to predict a remaining charging duration of the charging vehicle according to the second charging feature information and the target prediction model.

[0229] In some embodiments, referring to FIG. 7, the second determination module 603 includes a first determination unit 6031 and a second determination unit 6032.

[0230] The first determination unit 6031 is configured to determine a candidate prediction model according to the target vehicle model, and the second determination unit 6032 is configured to determine the target prediction model from the candidate prediction model according to the charging mode.

[0231] In some embodiments, referring to FIG. 8, the vehicle remaining charging duration prediction apparatus 600 further includes a third determination module 605, a second acquisition module 606, a fourth determination module 607, and a compensation module 608.

[0232] The third determination module 605 is configured to determine a battery type of the charging vehicle according to the target vehicle model, the second acquisition module 606 is configured to acquire a battery health state of the charging vehicle, the fourth determination module 607 is configured to determine a target compensation coefficient according to the battery health state and the battery type, and the compensation module 608 is configured to compensate the remaining charging duration according to the target compensation coefficient.

[0233] In some embodiments, referring to FIG. 9, the first determination module 602 includes a prediction unit 6021 and a third determination unit 6022.

[0234] The prediction unit 6021 is configured to input the first charging feature information into a vehicle model prediction model, and predict a vehicle model prediction result. The third determination unit 6022 is configured to determine a target vehicle model of the charging vehicle according to the vehicle model prediction result.

[0235] It should be noted that the vehicle remaining charging duration prediction device can perform the vehicle remaining charging duration prediction method provided in the embodiments of the present application, and has the function modules and beneficial effects corresponding to the execution method. Technical details not described in detail in the vehicle remaining charging duration prediction device embodiments can be referred to the vehicle remaining charging duration prediction method provided in the embodiments of the present application.

[0236] Please refer to FIG. 10, which is a schematic diagram of a hardware structure of a charging pile according to an embodiment of the present application. As shown in FIG. 10, the charging pile includes one or more processors 1001 and memories 1002, and FIG. 10 takes one processor 1001 as an example.

[0237] The processor 1001 is configured to support the computer device to perform the corresponding functions in the methods in the above method embodiments. The processor 1001 can be a central processing unit (CPU), a network processor (NP), a hardware chip or any combination thereof. The hardware chip can be an application specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof. The PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof.

[0238] The memory 1002 is configured to store program codes. The memory 1002 can include a volatile memory (VM), for example, a random access memory (RAM); the memory can also include a non-volatile memory (NVM), for example, a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD); and the memory 1002 can also include a combination of the above-mentioned memories.

[0239] The memory 1002 can be configured to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions / modules corresponding to the vehicle remaining charging duration prediction method in the embodiments of the present application. The processor 1001 executes various functional applications and data processing of the vehicle remaining charging duration prediction method and the vehicle remaining charging duration prediction device by running the non-volatile software programs, instructions, and modules stored in the memory 1002, that is, realizes the functions of each module or unit of the vehicle remaining charging duration prediction method and the vehicle remaining charging duration prediction device provided by the above method embodiments.

[0240] The memory 1002 can include a program storage area and a data storage area, where the program storage area can store an operating system and at least one application required by a function. The data storage area can store data created according to the use of the vehicle remaining charging duration prediction device, etc. In some embodiments, the memory 1002 can optionally include a memory remotely arranged with respect to the processor, and these remote memories can be connected to the vehicle remaining charging duration prediction device through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0241] The one or more modules are stored in the memory 1002, and when executed by the one or more processors 1001, perform the vehicle remaining charging duration prediction method in any of the above method embodiments, for example, perform the method steps described in the above method embodiments, and realize the functions of the modules described in the above device embodiments.

[0242] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program, the computer program including program instructions, the program instructions causing a computer to execute the method as described in the foregoing embodiments when executed by the computer.

[0243] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware by a computer program, and the program can be stored in a computer readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiment methods. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM) or a random access memory (RAM), etc.

[0244] Finally, it should be pointed out that the present application can be implemented in many different forms and is not limited to the embodiments described in the specification, which are not intended to be additional limitations on the content of the present application. The purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive. And under the idea of the present application, the above technical features continue to be combined with each other, and there are many other changes of different aspects of the present application as described above, which are considered to be within the scope of the present application. Further, for those skilled in the art, the above-mentioned embodiments can be improved or changed according to the above-mentioned description, and all these improvements and changes shall be within the scope of protection of the claims of the present application.

Claims

1. A method for predicting a remaining charging duration of a vehicle, characterized by, The method comprises: obtaining first charging feature information, second charging feature information and a charging mode; determining a target vehicle model of a charging vehicle according to the first charging feature information; determining a target prediction model according to the target vehicle model and the charging mode; predicting a remaining charging duration of the charging vehicle according to the second charging feature information and the target prediction model.

2. The vehicle remaining charge duration prediction method according to claim 1, characterized by, The determining of the target prediction model according to the target vehicle model and the charging mode comprises: determining a candidate prediction model according to the target vehicle model; determining the target prediction model in the candidate prediction model according to the charging mode.

3. The vehicle remaining charge duration prediction method according to claim 1, characterized by, The predicting of the remaining charging duration of the charging vehicle according to the second charging feature information and the target prediction model comprises: obtaining a battery temperature of the charging vehicle; judging whether the battery temperature is in a preset temperature range to obtain a judgment result; predicting the remaining charging duration of the charging vehicle according to the judgment result, the second charging feature information and the target prediction model.

4. The method according to claim 3, characterized by, The target prediction model comprises a normal-temperature charging prediction model, and the predicting of the remaining charging duration of the charging vehicle according to the judgment result, the second charging feature information and the target prediction model comprises: if the judgment result is that the battery temperature is not in the preset temperature range, inputting the second charging feature information into the normal-temperature charging prediction model to predict the remaining charging duration of the charging vehicle.

5. The method according to claim 4, characterized by, The target prediction model further comprises a high-temperature charging prediction model, and the vehicle remaining charging duration prediction method further comprises: determining a battery temperature rising rate of the charging vehicle; determining a target duration according to the battery temperature, the battery temperature rising rate and a first preset temperature threshold; judging whether the target duration is less than the remaining charging duration; if the target duration is less than the remaining charging duration, predicting a high-temperature charging duration according to the high-temperature charging prediction model, and updating the remaining charging duration according to the high-temperature charging duration and the target duration.

6. The method of claim 3, wherein The predicting of the remaining charging duration of the charging vehicle according to the judgment result, the second charging feature information and the target prediction model comprises: if the judgment result is that the battery temperature is in the preset temperature range, judging whether the charging vehicle supports a battery preheating function according to the target vehicle model; when the charging vehicle supports the battery preheating function, judging whether the charging vehicle is in a battery preheating state; when the charging vehicle is in the battery preheating state, determining a battery preheating mode; predicting the remaining charging duration of the charging vehicle according to the battery preheating mode, the second charging feature information and the target prediction model.

7. The method according to claim 6, characterized by, The target prediction model comprises a preheating prediction model and a normal-temperature charging prediction model, and the predicting of the remaining charging duration of the charging vehicle according to the battery preheating mode, the second charging feature information and the target prediction model comprises: determining a target preheating prediction model according to the battery preheating mode, the target preheating prediction model comprising a first preheating prediction model and a second preheating prediction model; predicting a preheating duration according to the first preheating prediction model; updating second charging feature information at the time when the battery preheating is completed according to the second preheating prediction model; inputting the updated second charging feature information into the normal-temperature charging prediction model to predict a normal-temperature charging duration; predicting the remaining charging duration of the charging vehicle according to the normal-temperature charging duration and the preheating duration.

8. The method of claim 6, wherein, The target prediction model comprises a first low-temperature charging prediction model, a second low-temperature charging prediction model and a normal-temperature charging prediction model, and the vehicle remaining charging duration prediction method further comprises: when the charging vehicle is not in a battery preheating state or does not support a battery preheating function, predicting a low-temperature charging duration according to the first low-temperature charging prediction model; updating second charging feature information at the time when the low-temperature charging is completed according to the second low-temperature charging prediction model; inputting the updated second charging feature information into the normal-temperature charging prediction model to predict a normal-temperature charging duration; predicting the remaining charging duration of the charging vehicle according to the normal-temperature charging duration and the low-temperature charging duration.

9. The method according to any one of claims 1 to 8, characterized in that, The vehicle remaining charging duration prediction method further comprises: determining the battery type of the charging vehicle according to the target vehicle type; obtaining the battery health state of the charging vehicle; determining a target compensation coefficient according to the battery health state and the battery type; compensating the remaining charging duration according to the target compensation coefficient.

10. A charging post, characterized in that, The charging pile comprises a memory and a processor, the processor is electrically connected with the memory, is used for executing one or more computer programs stored in the memory, and when the one or more computer programs are executed, makes the charging pile implement the vehicle remaining charging duration prediction method in any one of claims 1 to 9.

11. A computer readable storage medium, characterized in that, The computer readable storage medium stores a computer program, the computer program comprises program instructions, and the program instructions make the processor execute the vehicle remaining charging duration prediction method in any one of claims 1 to 9 when the processor executes the program instructions. The computer readable storage medium stores a computer program, the computer program comprises program instructions, and the program instructions make the processor execute the vehicle remaining charging duration prediction method in any one of claims 1 to 9 when the processor executes the program instructions.

Images