Vehicle charging remaining time determination method and device and vehicle end control equipment

Abstract

The invention relates to a vehicle charging remaining time determination method and device, vehicle end control equipment, a computer readable storage medium and a computer program product. The method comprises the steps that the initial charging remaining time of a vehicle at the current charging moment in the charging process and the charging remaining time influence characteristics of the vehicle in the charging process are acquired; and correcting the initial charging remaining time by using the charging remaining time influence characteristics to obtain the target charging remaining time of the vehicle at the current charging moment. By adopting the method, the change factors in the charging process can be evaluated more accurately through the obtained charging remaining time influence characteristics of the vehicle in the charging process, so that the initial charging remaining time is corrected, and the more accurate target charging remaining time is obtained. Moreover, the accurate target charging remaining time, namely the accurate charging remaining time prediction, can help the user to better arrange the charging plan time, reduce the waiting time, and can improve the charging management efficiency of the user.

Description

Technical Field

[0001] The present application relates to the field of battery charging technology, and in particular to a method and apparatus for determining the remaining charging time of a vehicle, a vehicle-side control device, a computer-readable storage medium, and a computer program product. Background Art

[0002] In the current use of new energy vehicles, users of new energy vehicles hope to charge the vehicles as much as possible within the planned time. Users usually plan the time based on the estimated remaining charging time displayed by the vehicle. However, during the actual charging process, the actual remaining charging time of the vehicle will change due to various factors and deviate from the estimated remaining charging time, resulting in the actual charging situation of the vehicle not meeting user expectations.

[0003] At present, the remaining charging time is mainly estimated by predicting the battery SOC (charge) state and current parameters. The prediction scheme is to fit the SOC and current parameters into a two-dimensional curve graph, and query the current remaining charging time according to the current SOC and current values ​​during real-time operation. However, in actual use, the above scheme has the problem of a large difference between the remaining charging time and the actual charging time. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, vehicle-side control device, computer-readable storage medium and computer program product for determining the remaining charging time of a vehicle, which can improve the accuracy of the remaining charging time, in order to address the above-mentioned technical problems.

[0005] In a first aspect, the present application provides a method for determining the remaining charging time of a vehicle, comprising:

[0006] Acquire the initial remaining charging time of the vehicle at the current charging moment during the charging process and the influencing characteristics of the remaining charging time of the vehicle during the charging process;

[0007] The initial remaining charging time is corrected using the remaining charging time influencing feature to obtain a target remaining charging time for the vehicle at the current charging time.

[0008] In one embodiment, the remaining charging time influencing feature includes a global degradation feature and a local fluctuation feature of the vehicle during the charging process; the global degradation feature is battery data associated with the attenuation of the battery charging and discharging performance of the vehicle battery at the current charging moment; the local fluctuation feature includes charging state data associated with the fluctuation of the remaining charging time during the charging process; the use of the remaining charging time influencing feature to correct the initial remaining charging time to obtain the target remaining charging time of the vehicle at the current charging moment includes:

[0009] The initial remaining charging time is corrected by using at least one of the global degradation feature and the local fluctuation feature to obtain a target remaining charging time for the vehicle at the current charging moment.

[0010] In one embodiment, the charging remaining time influencing feature includes a global degradation feature and a local fluctuation feature of the vehicle during the charging process; the global degradation feature is battery data associated with the attenuation of the battery charging and discharging performance of the vehicle battery at the current charging moment; the local fluctuation feature includes charging state data associated with the fluctuation of the charging remaining time during the charging process;

[0011] The using the remaining charging time influencing feature to correct the initial remaining charging time to obtain the target remaining charging time of the vehicle at the current charging time includes:

[0012] Performing a first correction on the initial remaining charging time according to the global degradation feature to obtain a corrected initial remaining charging time;

[0013] Obtaining a correction amount of the remaining charging time of the vehicle at the current charging time according to the local fluctuation characteristics;

[0014] The corrected initial remaining charging time is subjected to a second correction using the remaining charging time correction amount to obtain a target remaining charging time for the vehicle at the current charging time.

[0015] In one embodiment, performing a first correction on the initial remaining charging time according to the global degradation feature to obtain a corrected initial remaining charging time includes:

[0016] The global degradation feature is input into a time correction model, and a first correction is performed on the initial charging remaining time by using the time correction model and the charging state data at the current charging moment to obtain a corrected initial charging remaining time.

[0017] In one embodiment, obtaining the correction amount of the remaining charging time of the vehicle at the current charging time according to the local fluctuation characteristics includes:

[0018] The local fluctuation characteristic is input into a pre-constructed local fluctuation characteristic influence time function to obtain a correction amount of the remaining charging time corresponding to the local fluctuation characteristic; the local fluctuation characteristic influence time function is obtained based on the historical charging status data of the vehicle battery in the current life cycle and the historical remaining charging time corresponding to the historical charging status data.

[0019] In one embodiment, the step of acquiring the local fluctuation characteristic affecting the time function comprises:

[0020] Acquire historical charging status data of the vehicle battery in the current life cycle and historical charging remaining time corresponding to the historical charging status data;

[0021] The historical charging remaining time is sampled using a preset charging moment sampling interval to obtain a plurality of historical charging remaining time change values. When the historical charging remaining time change value is greater than a preset time change threshold, the charging state data corresponding to the historical charging remaining time change value is used as a local fluctuation feature, and each of the local fluctuation features is combined into a local fluctuation feature sequence;

[0022] The local fluctuation feature sequence is tracked and predicted by using a particle filter algorithm to obtain a predicted local fluctuation feature sequence, and the predicted local fluctuation feature sequence is fitted by using polynomial regression to obtain a local fluctuation feature influence time function.

[0023] In one embodiment, the method of tracking and predicting the local fluctuation feature sequence using a particle filter algorithm to obtain a predicted local fluctuation feature sequence, and fitting the predicted local fluctuation feature sequence using polynomial regression to obtain a local fluctuation feature influence time function includes:

[0024] Initialize using the initial probability density filter function to generate a particle swarm;

[0025] Update the weight of each particle and normalize it to get the weight of each particle;

[0026] Resample each particle to obtain a new particle set and weight;

[0027] The local fluctuation characteristic sequence is predicted by using the state equation to obtain a predicted local fluctuation characteristic sequence, and the predicted local fluctuation characteristic sequence is fitted by using polynomial regression to obtain a univariate polynomial regression function;

[0028] Solving the parameters of the univariate polynomial regression function using the least squares method to obtain a coefficient matrix;

[0029] According to the coefficient matrix and the univariate polynomial regression function, the local fluctuation characteristic influence time function is obtained.

[0030] In one embodiment, the step of acquiring the local fluctuation characteristics of the vehicle during the charging process includes:

[0031] Obtain the historical remaining charging time of the vehicle from the start of charging to the current charging time during the current charging process;

[0032] According to the historical remaining charging time and the preset charging time sampling interval, a plurality of historical remaining charging time change values ​​are obtained;

[0033] When the historical charging remaining time change value is greater than a preset time change threshold, the charging state data corresponding to the charging time interval associated with the historical charging remaining time change value is used as a local fluctuation feature.

[0034] In a second aspect, the present application also provides a device for determining the remaining charging time of a vehicle, comprising:

[0035] A feature extraction module, used to obtain the initial remaining charging time of the vehicle at the current charging moment during the charging process and the influencing features of the remaining charging time of the vehicle during the charging process;

[0036] The remaining time correction module is used to correct the initial remaining charging time by using the remaining charging time correction amount to obtain the target remaining charging time of the vehicle at the current charging time.

[0037] In a third aspect, the present application further provides a vehicle-side control device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method described in the first aspect when executing the computer program.

[0038] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method described in the first aspect.

[0039] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which implements the steps of the method described in the first aspect when executed by a processor.

[0040] The above-mentioned method, device, vehicle-side control device, computer-readable storage medium and computer program product for determining the remaining charging time of the vehicle first obtain the initial remaining charging time of the vehicle at the current charging moment during the charging process, and obtain the remaining charging time influencing characteristics of the vehicle during the charging process; then use the remaining charging time influencing characteristics to correct the initial remaining charging time, and finally obtain the target remaining charging time of the vehicle at the current charging moment. In the present application, by obtaining the remaining charging time influencing characteristics of the vehicle during the charging process, the changing factors in the charging process can be more accurately evaluated, thereby correcting the initial remaining charging time and obtaining a more accurate target remaining charging time. In addition, an accurate target remaining charging time, that is, an accurate remaining charging time prediction, can help users better arrange charging plan time, reduce waiting time, and improve the user's charging management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0042] FIG1 is a schematic flow chart of a method for determining the remaining charging time of a vehicle in one embodiment;

[0043] FIG2 is a schematic diagram of a process of correcting the initial remaining charging time by using the remaining charging time influencing feature to obtain the target remaining charging time of the vehicle at the current charging time in one embodiment;

[0044] FIG3 is a schematic flow chart of a step of obtaining the initial charging remaining time in one embodiment;

[0045] FIG4 is a flow chart of a MAP table update model training step in one embodiment;

[0046] FIG5 is a schematic flow chart of a step of acquiring local fluctuation characteristics in one embodiment;

[0047] FIG6 is a structural block diagram of a device for determining the remaining charging time of a vehicle in one embodiment;

[0048] FIG. 7 is a diagram showing the internal structure of a vehicle-side control device in one embodiment. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] The method for determining the remaining charging time of a vehicle provided in an embodiment of the present application can be applied to a vehicle battery management system (BMS). The vehicle battery management system obtains the initial remaining charging time of the vehicle at the current charging moment during the charging process and the influencing characteristics of the remaining charging time of the vehicle during the charging process from the data recorded in the vehicle management system; the vehicle battery management system uses the influencing characteristics of the remaining charging time to correct the initial remaining charging time to obtain the target remaining charging time of the vehicle at the current charging moment.

[0051] In an exemplary embodiment, as shown in FIG1 , a method for determining the remaining time of vehicle charging is provided, comprising the following steps S102 to S104. In which:

[0052] Step S102, obtaining the initial remaining charging time of the vehicle at the current charging moment during the charging process and the influencing characteristics of the remaining charging time of the vehicle during the charging process.

[0053] The initial remaining charging time may refer to the remaining time initially estimated to be required for the vehicle to be fully charged starting from the current moment during the charging process.

[0054] Specifically, during the vehicle charging process, the vehicle battery management system will first record the initial remaining charging time at the current moment. The initial remaining charging time refers to the remaining time expected to fully charge the vehicle from the current moment. This remaining time is usually the original estimated value of the remaining charging time calculated based on information such as the current charging state of the battery, the power of the charging pile, and the charging curve of the battery; during the vehicle charging process, the change of the remaining charging time may be affected by many factors. After the vehicle battery management system obtains these influencing factors and forms the remaining charging time influencing characteristics, it can correct the initial remaining charging time according to the remaining charging time influencing characteristics.

[0055] Step S104, using the remaining charging time influencing feature to correct the initial remaining charging time, to obtain the target remaining charging time of the vehicle at the current charging time.

[0056] Specifically, the vehicle battery management system utilizes the remaining charging time influencing characteristics and can use a preset algorithm to correct the initial remaining charging time. For example, the preset algorithm can be an empirical formula, a machine learning model, or other mathematical models, and then obtain the target remaining charging time of the vehicle at the current charging moment.

[0057] In the above-mentioned method for determining the remaining charging time of a vehicle, by obtaining the influencing characteristics of the remaining charging time of the vehicle during the charging process, the changing factors in the charging process can be more accurately evaluated, thereby correcting the initial remaining charging time and obtaining a more accurate target remaining charging time. In addition, the accurate target remaining charging time, i.e., the accurate remaining charging time prediction, can help users better arrange the charging plan time, reduce waiting time, and improve the user's charging management efficiency.

[0058] In an exemplary embodiment, the initial remaining charging time is corrected using the remaining charging time influencing feature to obtain the target remaining charging time of the vehicle at the current charging time, including:

[0059] At least one of the global degradation feature and the local fluctuation feature is used to correct the initial remaining charging time to obtain a target remaining charging time for the vehicle at the current charging moment.

[0060] Among them, the remaining charging time influencing characteristics include global degradation characteristics and local fluctuation characteristics of the vehicle during the charging process; the global degradation characteristics are battery data associated with the attenuation of the vehicle's battery charging and discharging performance at the current charging moment; the local fluctuation characteristics include charging status data associated with the fluctuation of the remaining charging time during the charging process.

[0061] Among them, as the vehicle battery is used, the battery's charging and discharging performance decays accordingly, that is, the battery will have a phenomenon corresponding to the global degradation characteristics, but the battery may not have a phenomenon corresponding to the local fluctuation characteristics during use. Therefore, the correction of the initial charging remaining time may include:

[0062] Example 1 only considers the global degradation characteristics of the battery; that is, the vehicle battery management system can use the global degradation characteristics to correct the initial remaining charging time to obtain the target remaining charging time of the vehicle at the current charging time.

[0063] Example 2 only considers the local fluctuation characteristics of the battery during use; the vehicle battery management system can use the local fluctuation characteristics to correct the initial remaining charging time to obtain the target remaining charging time of the vehicle at the current charging time.

[0064] Example 2: Considering the global degradation characteristics of the battery and the local fluctuation characteristics during use at the same time; the vehicle battery management system can use the global degradation characteristics and the local fluctuation characteristics to make two corrections to the initial remaining charging time to obtain the target remaining charging time of the vehicle at the current charging time.

[0065] In this embodiment, by utilizing at least one of the global degradation characteristics and the local fluctuation characteristics, the initial charging remaining time is corrected according to different situations to obtain the correction amount of the charging remaining time of the vehicle at the current charging moment. The initial charging remaining time can be corrected according to the global degradation characteristics and / or the local fluctuation characteristics. Different features can be selected according to different scenarios and then corrected, which can effectively improve the prediction accuracy of the charging remaining time.

[0066] In an exemplary embodiment, the remaining charging time influencing feature includes a global degradation feature and a local fluctuation feature of the vehicle during the charging process; the global degradation feature is battery data associated with the attenuation of the battery charging and discharging performance of the vehicle battery at the current charging moment; the local fluctuation feature includes charging state data associated with the fluctuation of the remaining charging time during the charging process; as shown in FIG. 2 , the above step S104 may specifically include:

[0067] Step S202: performing a first correction on the initial remaining charging time according to the global degradation characteristic to obtain a corrected initial remaining charging time.

[0068] Among them, the global degradation characteristics may refer to the attenuation characteristics of the overall battery performance, which can be evaluated through historical data and current battery status to reflect the health status of the battery.

[0069] Exemplarily, the vehicle battery management system may perform a first correction on the initial charging remaining time according to the global degradation characteristics to obtain a corrected initial charging remaining time.

[0070] Step S204, obtaining a correction amount of the remaining charging time of the vehicle at the current charging time according to the local fluctuation characteristics.

[0071] Among them, the local fluctuation characteristics include charging status data associated with the fluctuation of the remaining charging time; the charging status data may refer to data used to characterize the charging status of the battery, such as the battery's SOC, voltage, current, temperature and other data; specifically, the local fluctuation characteristics may refer to the changing characteristics of the charging status data during the charging process, such as changes in SOC, current, voltage, temperature and other changes, which may cause fluctuations in the remaining charging time.

[0072] Exemplarily, at time T1, the vehicle battery voltage is 400V, the current is 50A, the temperature is 25°C, and the SOC is 90%. The vehicle battery management system calculates the above parameters and obtains the initial remaining charging time of 20 minutes; the change in the remaining charging time during the charging process is obtained. If there is an abnormal fluctuation in the remaining charging time, the corresponding battery voltage, current, temperature and SOC charging status data when the abnormal fluctuation occurs is obtained, for example, the current jumps from 50A to 40A.

[0073] The remaining charging time correction amount may refer to a correction value of the initial remaining charging time calculated according to the local fluctuation characteristics, and is used to improve the accuracy of the initial remaining charging time estimation.

[0074] Exemplarily, the vehicle battery management system obtains the remaining charging time correction amount of the vehicle at the current charging time based on local fluctuation characteristics, such as the current jumping from current A to current B and the temperature changing from M to N, through current A, current B, temperature M and temperature N.

[0075] Step S206, performing a second correction on the corrected initial remaining charging time using the remaining charging time correction amount to obtain a target remaining charging time for the vehicle at the current charging time.

[0076] The target remaining charging time may refer to the corrected initial remaining charging time, which represents a more accurate time required from the current charging time to the completion of charging.

[0077] Exemplarily, the initial remaining charging time is A. Because the charging efficiency is reduced due to current fluctuations, the remaining charging time correction amount is -B. The vehicle battery management system uses the remaining charging time correction amount -B to make a second correction to the initial remaining charging time A to obtain the target remaining charging time AB for the vehicle at the current charging moment. The target remaining charging time AB can then be displayed in the vehicle system or on the user terminal application for user reference.

[0078] In this embodiment, the battery data associated with the battery charging and discharging performance attenuation of the vehicle battery at the charging moment, i.e., the global degradation feature, is used to first correct the initial remaining charging time to obtain the corrected initial remaining charging time. Then, the charging state data associated with the fluctuation of the remaining charging time, i.e., the local fluctuation feature, is used to obtain the correction amount of the remaining charging time of the vehicle at the current charging moment. Finally, the correction amount of the remaining charging time is used to correct the initial remaining charging time. On the basis of the initial remaining charging time that has been corrected by including the influence of the global degradation feature, combined with the correction amount of the remaining charging time obtained by including the influence of the local fluctuation feature, the target remaining charging time of the vehicle can be determined more accurately, thereby improving the accuracy of the remaining charging time prediction. In addition, displaying a more accurate target remaining charging time to the user can enable the user to plan time reasonably and reduce the waiting time of the user.

[0079] In an exemplary embodiment, the above step S102 may specifically include:

[0080] Step S6, inputting the global degradation characteristics into the time correction model, performing a first correction on the initial charging remaining time through the time correction model and the charging state data at the current charging moment, and obtaining a corrected initial charging remaining time.

[0081] The time correction model may be a model based on an empirical formula, a machine learning model or other mathematical models.

[0082] Specifically, the vehicle battery management system can input the global degradation characteristics into the time correction model, perform a first correction on the initial charging remaining time through the correction parameters output by the time correction model combined with the charging status data at the current charging moment, and obtain the corrected initial charging remaining time.

[0083] In this embodiment, the global degradation characteristics are converted into a direct impact on the remaining charging time through a time correction model, and the initial remaining charging time is first corrected in combination with the charging state data at the current charging moment, so as to improve the correction accuracy of the initial remaining charging time.

[0084] In an exemplary embodiment, the time correction model is a pre-trained MAP table update model, as shown in FIG3 , and the step S6 may specifically include:

[0085] Step S302: input the global degradation feature into a pre-trained MAP table update model to obtain a MAP table for interpolating and estimating the remaining charging time corresponding to the current charging moment.

[0086] Among them, the global degradation feature may refer to the global degradation feature corresponding to the vehicle battery in the entire current charging process. For example, if the current charging process is the Nth cycle charging, the battery data associated with the battery charge and discharge performance decay after the N-1th cycle charging may be obtained as the global degradation feature, or the battery data after the N-1th cycle discharging may be obtained as the global degradation feature. In another example, the battery data associated with the battery charge and discharge performance decay in the current charging process may also be used as the global degradation feature; the battery data associated with the battery charge and discharge performance decay in the current charging process may also be used as the global degradation feature and the battery data associated with the battery charge and discharge performance decay in the N-1 cycle charging process before the current charging process may also be combined as the global degradation feature.

[0087] Among them, a MAP (Multi-dimensional Array Map) table may refer to a multidimensional data structure for storing and querying the relationship between multiple variables. In this embodiment, a charging remaining time interpolation estimation MAP table may be used to represent the relationship between a battery state (such as SOC, voltage, current, temperature, etc.) and the charging remaining time. Through the charging remaining time interpolation estimation MAP table, the charging remaining time under a specific battery state may be quickly found; a pre-trained MAP table update model may refer to a machine learning model, which inputs battery data of battery charging and discharging performance such as the global degradation characteristics of the battery, such as the number of charging and discharging cycles, charging efficiency, internal resistance, and battery health, into the MAP table update model, and the corresponding charging remaining time interpolation estimation MAP table of the current charging moment may be updated according to the global degradation characteristics of the battery through the model output.

[0088] Exemplarily, after acquiring the global degradation characteristics, the vehicle battery management system inputs the global degradation characteristics into a pre-trained MAP table update model, and obtains a corresponding charging remaining time interpolation estimation MAP table for the current charging moment by updating the historical charging remaining time interpolation estimation MAP table.

[0089] Step S304, obtaining the remaining charging time that matches the charging state data at the current charging moment from the remaining charging time interpolation estimation MAP table as the initial remaining charging time.

[0090] Exemplarily, the vehicle battery management system obtains the charging status data at the current charging moment, and then obtains the charging remaining time that matches the charging status data at the current charging moment from the charging remaining time interpolation estimation MAP table, and uses the charging remaining time as the initial charging remaining time.

[0091] Exemplarily, the historical charging remaining time interpolation estimation MAP table is the first MAP table, and the global degradation feature is input into the pre-trained MAP table update model to obtain the corresponding charging remaining time interpolation estimation MAP table at the current charging moment, that is, the first MAP table is updated by the MAP table update model to obtain the corresponding charging remaining time interpolation estimation MAP table at the current charging moment, that is, the second MAP table, and the charging remaining time A matching the charging status data at the current charging moment is obtained from the second MAP table as the initial charging remaining time; if the charging remaining time B matching the charging status data at the current charging moment is obtained from the first MAP table, the charging remaining time A is not the same as the charging remaining time B, because the second MAP table includes the influence of the current global feature on the basis of the first MAP, and therefore, under the same charging status data, the charging remaining time obtained by different MAP tables is different.

[0092] In this embodiment, by inputting the global degradation characteristics into the pre-trained MAP table update model, the latest charging remaining time interpolation estimation MAP table that is changed due to the influence of the global degradation characteristics can be obtained, so that the charging remaining time that matches the charging status data at the current charging moment is obtained through the latest charging remaining time interpolation estimation MAP table, and is used as the initial charging remaining time. Therefore, the accuracy of the estimation of the initial charging remaining time corresponding to the current charging moment can be improved, that is, the vehicle battery management system can provide a more accurate initial charging remaining time estimate according to the current state of the battery, and then provide reliable basic data for the subsequent time correction process through the accurate initial charging remaining time.

[0093] In an exemplary embodiment, as shown in FIG4 , the training step of the MAP table update model includes:

[0094] Step S402, obtaining historical charging status data of the historical charging process in the current life cycle of the vehicle battery, the historical charging remaining time corresponding to the historical charging status data, the initial charging remaining time interpolation estimation MAP table and the number of charging cycles corresponding to the historical charging process.

[0095] Among them, the historical charging state data of the historical charging process during the current life cycle of the vehicle battery may refer to various status information about the battery charging process recorded by the vehicle during its current life cycle, such as current, voltage, temperature, SOC and other data. The historical charging remaining time may refer to the time prediction corresponding to the historical charging state data, indicating the charging remaining time expected to be required for the charging process at that time. The initial charging remaining time interpolation estimation MAP table may refer to a table established by an interpolation method using known charging state and charging remaining time data, which is used to estimate future charging conditions. The number of charging cycles may refer to the total number of times the battery undergoes a full cycle of charging and discharging.

[0096] Exemplarily, the vehicle battery management system obtains, from the recorded historical data, the historical charging status data of the historical charging process in the current life cycle of the vehicle battery, the historical charging remaining time corresponding to the historical charging status data, the initial charging remaining time interpolation estimation MAP table, and the number of charging cycles corresponding to the historical charging process.

[0097] Step S404, inputting historical charging remaining time, historical charging state data, initial charging remaining time interpolation estimation MAP table and charging cycle number into the MAP table update model to be trained, and obtaining the predicted charging remaining time interpolation estimation MAP table corresponding to the historical charging process.

[0098] Among them, the interpolation estimation MAP table of the remaining charging time and the MAP table update model can be deployed in the vehicle battery management system. The vehicle battery management system inputs the historical remaining charging time, the historical charging status data, the initial interpolation estimation MAP table of the remaining charging time and the number of charging cycles into the MAP table update model to be trained to obtain the predicted interpolation estimation MAP table of the remaining charging time corresponding to the historical charging process.

[0099] Step S406 , according to the historical remaining charging time and the historical charging state data, the charging state data characterized by local fluctuation characteristics are removed to obtain the target historical charging state data and the corresponding target historical remaining charging time.

[0100] Among them, the target historical charging status data and the corresponding target historical charging remaining time can refer to the historical charging remaining time and the historical charging status data. According to the historical charging status data and its corresponding historical charging remaining time after removing local fluctuation characteristics, the historical charging status data and its corresponding historical charging remaining time mainly containing global degradation characteristics can be obtained as the target historical charging status data and the corresponding target historical charging remaining time.

[0101] Step S408, obtaining a correlation curve between the target historical charging remaining time and the target historical charging status data, and obtaining a loss value based on the difference between the correlation curve and the predicted charging remaining time interpolation estimation MAP table corresponding relationship curve, and using the loss value to train the MAP table update model.

[0102] Exemplarily, the vehicle battery management system constructs a correlation curve by analyzing the relationship between the target historical charging status data and the target historical charging remaining time; at the same time, the correlation curve is compared with the corresponding relationship curve generated by the interpolation estimation MAP table of the predicted charging remaining time, and the loss value is obtained by calculating the difference between the above two relationship curves. The loss value is used to further train the model to optimize the model parameters of the MAP table update model, so that the generated predicted charging remaining time interpolation estimation MAP table is more accurate.

[0103] In this embodiment, the loss value is further obtained by removing the charging state data with local fluctuation characteristics, and the model is trained so that the model can more accurately capture the stable charging state trend, which helps to reduce the error caused by abnormal data noise, thereby improving the generation accuracy of the interpolation estimation MAP table for predicting the remaining charging time.

[0104] In an exemplary embodiment, as shown in FIG5 , the step of acquiring the local fluctuation characteristics of the vehicle during the charging process includes:

[0105] Step S502, obtaining the historical remaining charging time of the vehicle from the start of charging to the current charging time during the current charging process.

[0106] Among them, the historical remaining charging time from the start of charging to the current charging time in the current charging process may refer to the remaining charging time data of the battery from the current charging time to the start of charging during the charging process. The remaining charging time data is updated in real time as the charging time changes.

[0107] Step S504, obtaining a plurality of historical remaining charging time variation values ​​according to the historical remaining charging time and the preset charging time sampling interval.

[0108] The preset charging time sampling interval may refer to a time interval for selecting a specific time period for data sampling during the charging process. By regularly collecting data within the time interval, multiple historical charging remaining time change values ​​during the charging process may be obtained.

[0109] Exemplarily, the time interval can be a specific time interval of 1 minute, 3 minutes, 5 minutes, etc. This is only an example and is not specifically limited. It is set based on actual needs. Taking a time interval of 1 minute as an example, that is, from the moment when charging starts, the historical charging remaining time is sampled every minute to obtain the change value of the historical charging remaining time within each minute from the start of charging.

[0110] Step S506: When the historical charging remaining time change value is greater than the preset time change threshold, the charging state data corresponding to the charging time interval associated with the historical charging remaining time change value is used as a local fluctuation feature.

[0111] The preset time change threshold is used to determine whether the change value of the historical charging remaining time exceeds expectations.

[0112] Exemplarily, the preset time change threshold is threshold M, the preset charging time sampling interval is 3 minutes, and the multiple historical charging remaining time change values ​​obtained include: change value A, change value B, change value C, change value D, etc. Among them, change value A and change value C are greater than threshold M, so the charging state data corresponding to the 3-minute charging time interval associated with change value A and change value C are used as local fluctuation characteristics.

[0113] In this embodiment, by obtaining the change value of the historical remaining charging time through the preset charging moment sampling interval and the preset time change threshold, the local fluctuation characteristics in the charging process can be effectively identified and obtained, and associated with the charging status data, thereby providing important reference data for the subsequent correction of the remaining charging time.

[0114] In an exemplary embodiment, based on the local fluctuation characteristics, a charging remaining time correction amount of the vehicle at the current charging time is obtained, including: inputting the local fluctuation characteristics into a pre-constructed local fluctuation characteristic influence time function to obtain the charging remaining time correction amount corresponding to the local fluctuation characteristics.

[0115] The local fluctuation characteristic impact time function is obtained based on the historical charging state data of the vehicle battery in the current life cycle and the historical charging remaining time corresponding to the historical charging state data.

[0116] The pre-constructed local fluctuation characteristic impact time function can be used to output the time variation of the impact of the local fluctuation characteristic on the remaining charging time according to the input local fluctuation characteristic.

[0117] Exemplarily, the local fluctuation characteristics include characteristic A and characteristic B. The vehicle battery management system inputs characteristic A and characteristic B into a pre-constructed local fluctuation characteristic influence function, and calculates the remaining charging time correction amount corresponding to the local fluctuation characteristics through the local fluctuation characteristic influence function, that is, the corresponding characteristic A can output the time correction amount -a, and the corresponding characteristic B outputs the time correction amount b, and then correction can be made according to the time correction amount -a and the time correction amount b.

[0118] In this embodiment, through the local fluctuation characteristics and the local fluctuation characteristics affecting the time function, the remaining charging time correction amount is calculated according to the local fluctuation characteristics affecting the time function, which can be used to adjust the initial remaining charging time and more accurately predict the actual remaining charging time.

[0119] In an exemplary embodiment, the step of acquiring the local fluctuation characteristic influence time function includes:

[0120] Step S11, obtaining historical charging status data of the vehicle battery in the current life cycle and historical charging remaining time corresponding to the historical charging status data.

[0121] The historical charging status data of the vehicle battery in the current life cycle may refer to various data about the charging process recorded during the use of the vehicle battery up to now, such as SOC, voltage, current, temperature, charging time, etc. The historical charging remaining time corresponding to the historical charging status data may refer to the remaining time required for the vehicle to complete charging corresponding to each charging time in the historical charging status data.

[0122] Step S12, use the preset charging moment sampling interval to sample the historical charging remaining time to obtain multiple historical charging remaining time change values. When the historical charging remaining time change value is greater than the preset time change threshold, the charging state data corresponding to the historical charging remaining time change value is used as a local fluctuation feature, and the local fluctuation features are combined into a local fluctuation feature sequence.

[0123] The preset charging time sampling interval may refer to a time interval for data sampling in a specific time period during the charging process. By regularly collecting data within the time interval, multiple historical charging remaining time change values ​​during the charging process can be obtained. The preset time change threshold is used to determine whether the historical charging remaining time change value exceeds expectations. The local fluctuation feature sequence may refer to a sequence composed of multiple local fluctuation features.

[0124] Step S13, using a particle filter algorithm to track and predict the local fluctuation feature sequence to obtain a predicted local fluctuation feature sequence, and using polynomial regression to fit the predicted local fluctuation feature sequence to obtain a local fluctuation feature influence time function.

[0125] Among them, the particle filter algorithm is a recursive estimation method based on Bayesian theory. It estimates the state of the system by weighting and resampling a set of particles. It is suitable for systems with nonlinear and non-Gaussian noise. Polynomial regression is a regression analysis method that uses polynomial functions to fit data to capture nonlinear relationships in the data. The local fluctuation feature influence time function can be a function obtained by analyzing and modeling the local fluctuation feature, which is used to describe the influence of the local fluctuation feature on the remaining charging time.

[0126] Exemplarily, the vehicle management system uses a particle filter algorithm to track and predict the local fluctuation feature sequence to obtain a predicted local fluctuation feature sequence, performs polynomial regression fitting on the predicted local fluctuation feature sequence to obtain a local fluctuation feature influence time function.

[0127] In this embodiment, the particle filter algorithm is used to track and predict the local fluctuation feature sequence, and the predicted local fluctuation feature sequence is fitted using polynomial regression. This can more accurately extract the correlation between the local fluctuation characteristics and the remaining charging time, making the obtained local fluctuation feature affecting the time function more accurate.

[0128] In an exemplary embodiment, the above-mentioned step S13 may specifically include: initializing using an initial probability density filter function to generate a particle swarm; updating and normalizing the weight of each particle to obtain the weight of each particle; resampling each particle to obtain a new particle set and weight; predicting the local fluctuation feature sequence using a state equation to obtain a predicted local fluctuation feature sequence, fitting the predicted local fluctuation feature sequence using polynomial regression to obtain a univariate polynomial regression function; solving the parameters of the univariate polynomial regression function using the least squares method to obtain a coefficient matrix; and obtaining the local fluctuation feature influence time function based on the coefficient matrix and the univariate polynomial regression function.

[0129] Specifically, the above step S13 may include:

[0130] Step 1: Initialize using the initial probability density filter function to generate a particle swarm. Initialize model parameters x 0 =[ a 0 , b 0 , c 0 , d 0 , e 0 , f 0 ] , and then by the prior probability P( ) Generate particle set , N is the total number of particles, and the weights of all particles are .

[0131] Step 2: When the measured value is observed When It can be updated to the following equation:

[0132]

[0133] Step 3: Particles The calculation in the kth cycle is as follows:

[0134]

[0135] Step 4: Update and normalize the weight of each particle to obtain the weight of each particle; update the particle weight at time k and normalize it:

[0136]

[0137] In the formula is the weight of the i-th particle at time k, is the observed quantity at time k, is the i-th particle corresponding to time k, and then the mean square error estimate of the particle is solved by the following formula:

[0138]

[0139] Step 5: Use Taylor's formula for each state variable To expand, It can be used as the state value with a fluctuation time of 0. The Taylor expansion can be expressed by the following formula:

[0140]

[0141] because The formula can be optimized to obtain the following univariate polynomial regression function:

[0142] Step 6: Use the least squares method to solve the model parameters for the above univariate polynomial regression function. The formula is as follows:

[0143]

[0144] The formula after expanding the above formula is as follows:

[0145]

[0146] The expanded equation is decomposed into a matrix form, and the coefficient matrix is ​​obtained by Vandermonde decomposition. The obtained coefficient matrix is ​​substituted into the above-mentioned univariate polynomial regression function, and finally the local fluctuation characteristic influence time function is obtained. :

[0147]

[0148] In this embodiment, the particle filter can handle nonlinear and non-Gaussian noise. By generating and updating a particle swarm, the change of local fluctuation characteristics can be reflected in real time. This method performs well in dynamic systems and can provide more accurate state estimation. By performing polynomial regression on the predicted local fluctuation characteristic sequence, the nonlinear relationship in the data can be captured, further improving the accuracy of the prediction. The solution combining particle filtering and polynomial regression can maintain high computational efficiency while ensuring accuracy, and is suitable for real-time applications.

[0149] In a specific embodiment, a method for determining the remaining charging time of a vehicle is provided, which specifically includes:

[0150] The initial remaining charging time of the vehicle at the current charging moment and the local fluctuation characteristics of the vehicle during the charging process are obtained; the local fluctuation characteristics include the charging state data associated with the fluctuation of the remaining charging time; the initial remaining charging time is obtained based on the global degradation characteristics of the vehicle battery, and the global degradation characteristics are the battery data associated with the battery charging and discharging performance attenuation of the vehicle battery at the current charging moment. It should be noted that the extraction of global degradation characteristics is mainly aimed at the increase in battery usage time. When the number of charging and discharging cycles increases cumulatively, the battery performance will decay in a certain regularity, resulting in the corresponding time-following change of the interpolation estimation MAP table of the remaining charging time. In general, the battery SOH state will only be updated according to the number of cycles, and the overall battery performance attenuation is not directly increased according to the number of cycles to compensate for the remaining charging time. Therefore, we need to collect data of global degradation characteristics as well. The global degradation characteristic phenomenon is a certain situation, while the local abnormal fluctuation characteristics are not an inevitable event. Therefore, the global degradation characteristic phenomenon is a phenomenon that is bound to exist throughout the entire life cycle. Therefore, the estimation of the remaining charging time should include it as one of the compensation conditions.

[0151] Among them, the step of obtaining the initial remaining charging time of the vehicle at the current charging moment during the charging process includes: inputting the global degradation characteristics into a pre-trained MAP table update model to obtain the corresponding remaining charging time interpolation estimation MAP table at the current charging moment; obtaining the remaining charging time that matches the charging status data at the current charging moment from the remaining charging time interpolation estimation MAP table as the initial remaining charging time.

[0152] Among them, the training steps of the MAP table update model include: obtaining historical charging status data of the historical charging process within the current life cycle of the vehicle battery, the historical charging remaining time corresponding to the historical charging status data, the initial charging remaining time interpolation estimation MAP table, and the number of charging cycles corresponding to the historical charging process; inputting the historical charging remaining time, the historical charging status data, the initial charging remaining time interpolation estimation MAP table, and the number of charging cycles into the MAP table update model to be trained to obtain the predicted charging remaining time interpolation estimation MAP table corresponding to the historical charging process; according to the historical charging remaining time and the historical charging status data, removing the charging status data characterized by local fluctuation characteristics, and obtaining the target historical charging status data and the corresponding target historical charging remaining time; obtaining the correlation relationship curve between the target historical charging remaining time and the target historical charging status data, and obtaining the loss value according to the difference between the correlation relationship curve and the corresponding relationship curve of the predicted charging remaining time interpolation estimation MAP table, and using the loss value to train the MAP table update model.

[0153] Among them, the step of obtaining the local fluctuation characteristics of the vehicle during the charging process includes: obtaining the historical remaining charging time of the vehicle from the start of charging to the current charging time during the current charging process; obtaining multiple historical remaining charging time change values ​​according to the historical remaining charging time and a preset charging time sampling interval; when the historical remaining charging time change value is greater than a preset time change threshold, the charging status data corresponding to the charging time interval associated with the historical remaining charging time change value is used as the local fluctuation characteristic.

[0154] The local fluctuation feature is input into the pre-constructed local fluctuation feature influence time function to obtain the charge remaining time correction corresponding to the local fluctuation feature; the local fluctuation feature influence time function is obtained based on the historical charging state data of the vehicle battery in the current life cycle and the historical charge remaining time corresponding to the historical charging state data. Among them, the step of obtaining the local fluctuation feature influence time function includes: obtaining the historical charging state data of the vehicle battery in the current life cycle and the historical charge remaining time corresponding to the historical charging state data; sampling the historical charge remaining time using the preset charging time sampling interval to obtain multiple historical charge remaining time change values, and when the historical charge remaining time change value is greater than the preset time change threshold, the charge state data corresponding to the historical charge remaining time change value is used as the local fluctuation feature, and each local fluctuation feature is composed into a local fluctuation feature sequence.

[0155] Among them, the local fluctuation feature refers to the instantaneous time change caused by other factors. The extraction of local fluctuation features can be to extract each charge as a sampling sample and extract the more abnormal fluctuations, such as a period of time. The local features that deviate from the remaining charging time by more than M (preset time change threshold, the threshold range can be determined by experiment) minutes within the (preset charging time sampling interval) are extracted, and a total of N samples of local abnormal fluctuations are taken. Each time a local feature abnormal change occurs, there must be corresponding factors, such as voltage mutation, temperature change, SOC jump, and abnormal current fluctuation, which will cause a large change in the current remaining charging time estimation. Therefore, the functional relationship equation of each local abnormal fluctuation and current, temperature, SOC, and voltage is established, and each local feature is composed of a corresponding array sequence. The formula is as follows:

[0156]

[0157] Initialize with the initial probability density filter function to generate a particle swarm; update and normalize the weight of each particle to obtain the weight of each particle; resample each particle to obtain a new particle set and weight; use the state equation to predict the local fluctuation feature sequence to obtain the predicted local fluctuation feature sequence, and use polynomial regression to fit the predicted local fluctuation feature sequence to obtain a univariate polynomial regression function; use the least squares method to solve the parameters of the univariate polynomial regression function to obtain the coefficient matrix; according to the coefficient matrix and the univariate polynomial regression function, obtain the local fluctuation feature influence time function.

[0158] Among them, step 1: use the initial probability density filter function to initialize and generate a particle swarm. Initialize model parameters x 0 =[ a 0 , b 0 , c 0 , d 0 , e 0 , f 0 ] , and then by the prior probability P( ) Generate particle set , N is the total number of particles, and the weights of all particles are .

[0159] Step 2: When the measured value is observed When It can be updated to the following equation:

[0160]

[0161] Step 3: Particles The calculation in the kth cycle is as follows:

[0162]

[0163] Step 4: Update and normalize the weight of each particle to obtain the weight of each particle; update the particle weight at time k and normalize it:

[0164]

[0165] In the formula is the weight of the i-th particle at time k, is the observed quantity at time k, is the i-th particle corresponding to time k, and then the mean square error estimate of the particle is solved by the following formula:

[0166]

[0167] Step 5: Use Taylor's formula for each state variable To expand, It can be used as the state value with a fluctuation time of 0. The Taylor expansion can be expressed by the following formula:

[0168]

[0169] because The formula can be optimized to obtain the following univariate polynomial regression function:

[0170] Step 6: Use the least squares method to solve the model parameters for the above univariate polynomial regression function. The formula is as follows:

[0171]

[0172] The formula after expanding the above formula is as follows:

[0173]

[0174] The expanded equation is decomposed into a matrix form, and the coefficient matrix is ​​obtained by Vandermonde decomposition. The obtained coefficient matrix is ​​substituted into the above-mentioned univariate polynomial regression function, and finally the local fluctuation characteristic influence time function is obtained. :

[0175]

[0176] The initial remaining charging time is corrected using the remaining charging time correction amount to obtain the target remaining charging time of the vehicle at the current charging time. Specifically, it can be: target remaining charging time The initial remaining charging time obtained by the BMS through interpolation minus the time change caused by characteristic fluctuations can be simplified to the following equation:

[0177]

[0178] Among them, i represents current, v represents voltage, and T represents temperature.

[0179] In this embodiment, it can help to achieve accurate estimation of the remaining charging time and improve the estimation accuracy of the remaining time; it can help the entire vehicle and battery components to more accurately understand the service life and safety level; it can help to standardize the functions of industry algorithm software and make it easier to upgrade and iterate.

[0180] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0181] Based on the same inventive concept, the embodiment of the present application also provides a vehicle charging remaining time determination device for implementing the vehicle charging remaining time determination method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more vehicle charging remaining time determination device embodiments provided below can refer to the above limitations on the vehicle charging remaining time determination method, and will not be repeated here.

[0182] In an exemplary embodiment, as shown in FIG6 , a vehicle charging remaining time determination device 600 is provided, comprising: a feature extraction module 601 and a remaining time correction module 602, wherein:

[0183] The feature extraction module 601 is used to obtain the initial remaining charging time of the vehicle at the current charging moment during the charging process and the influencing features of the remaining charging time of the vehicle during the charging process.

[0184] The remaining time correction module 602 is used to correct the initial remaining charging time by using the remaining charging time influencing feature to obtain the target remaining charging time of the vehicle at the current charging time.

[0185] In an exemplary embodiment, the characteristics affecting the remaining charging time include global degradation characteristics and local fluctuation characteristics of the vehicle during the charging process; the global degradation characteristics are battery data associated with the attenuation of the battery charging and discharging performance of the vehicle battery at the current charging moment; the local fluctuation characteristics include charging state data associated with the fluctuation of the remaining charging time during the charging process; the above-mentioned remaining time correction module 602 is also used to use at least one of the global degradation characteristics and the local fluctuation characteristics to correct the initial remaining charging time to obtain the target remaining charging time of the vehicle at the current charging moment.

[0186] In an exemplary embodiment, the charging remaining time influencing characteristics include global degradation characteristics and local fluctuation characteristics of the vehicle during the charging process; the global degradation characteristics are battery data associated with the attenuation of the battery charging and discharging performance of the vehicle battery at the current charging moment; the local fluctuation characteristics include charging state data associated with the fluctuation of the charging remaining time during the charging process; the above-mentioned remaining time correction module 602 is also used to perform a first correction on the initial charging remaining time according to the global degradation characteristics to obtain the corrected initial charging remaining time; obtain the charging remaining time correction amount of the vehicle at the current charging moment according to the local fluctuation characteristics; and perform a second correction on the corrected initial charging remaining time using the charging remaining time correction amount to obtain the target charging remaining time of the vehicle at the current charging moment.

[0187] In an exemplary embodiment, the remaining time correction module 602 is further used to input the global degradation characteristics into the time correction model, perform a first correction on the initial charging remaining time through the time correction model and the charging status data at the current charging moment, and obtain the corrected initial charging remaining time.

[0188] In an exemplary embodiment, the time correction model is a pre-trained MAP table update model; the remaining time correction module 602 is also used to input the global degradation characteristics into the pre-trained MAP table update model to obtain the corresponding charging remaining time interpolation estimation MAP table at the current charging moment; and obtain the charging remaining time that matches the charging status data at the current charging moment from the charging remaining time interpolation estimation MAP table as the initial charging remaining time.

[0189] In an exemplary embodiment, the remaining time correction module 602 is also used to obtain historical charging status data, historical charging remaining time corresponding to the historical charging status data, an initial charging remaining time interpolation estimation MAP table, and the number of charging cycles corresponding to the historical charging process during the current life cycle of the vehicle battery; the historical charging remaining time, the historical charging status data, the initial charging remaining time interpolation estimation MAP table, and the number of charging cycles are input into the MAP table update model to be trained to obtain a predicted charging remaining time interpolation estimation MAP table corresponding to the historical charging process; according to the historical charging remaining time and the historical charging status data, the charging status data characterized by local fluctuation characteristics are removed to obtain the target historical charging status data and the corresponding target historical charging remaining time; the correlation relationship curve between the target historical charging remaining time and the target historical charging status data is obtained, and the loss value is obtained according to the difference between the correlation relationship curve and the corresponding relationship curve of the predicted charging remaining time interpolation estimation MAP table, and the loss value is used to train the MAP table update model.

[0190] In an exemplary embodiment, the remaining time correction module 602 is also used to input the local fluctuation characteristics into a pre-constructed local fluctuation characteristic influence time function to obtain a charging remaining time correction amount corresponding to the local fluctuation characteristics; the local fluctuation characteristic influence time function is obtained based on the historical charging status data of the vehicle battery in the current life cycle and the historical charging remaining time corresponding to the historical charging status data.

[0191] In an exemplary embodiment, the remaining time correction module 602 is also used to obtain historical charging status data of the vehicle battery in the current life cycle and the historical charging remaining time corresponding to the historical charging status data; the historical charging remaining time is sampled using a preset charging time sampling interval to obtain multiple historical charging remaining time change values, and when the historical charging remaining time change value is greater than a preset time change threshold, the charging status data corresponding to the historical charging remaining time change value is used as a local fluctuation feature, and each local fluctuation feature is combined into a local fluctuation feature sequence; the local fluctuation feature sequence is tracked and predicted using a particle filter algorithm to obtain a predicted local fluctuation feature sequence, and the predicted local fluctuation feature sequence is fitted using polynomial regression to obtain a local fluctuation feature influence time function.

[0192] In an exemplary embodiment, the above-mentioned remaining time correction module 602 is also used to initialize using an initial probability density filter function to generate a particle swarm; update the weight of each particle and normalize it to obtain the weight of each particle; resample each particle to obtain a new particle set and weight; use the state equation to predict the local fluctuation feature sequence to obtain a predicted local fluctuation feature sequence, use polynomial regression to fit the predicted local fluctuation feature sequence to obtain a univariate polynomial regression function; use the least squares method to solve the parameters of the univariate polynomial regression function to obtain a coefficient matrix; according to the coefficient matrix and the univariate polynomial regression function, obtain the local fluctuation feature influence time function.

[0193] In an exemplary embodiment, the feature extraction module 601 is also used to obtain the historical remaining charging time of the vehicle from the start of charging to the current charging time during the current charging process; based on the historical remaining charging time and the preset charging time sampling interval, multiple historical remaining charging time change values ​​are obtained; when the historical remaining charging time change value is greater than the preset time change threshold, the charging status data corresponding to the charging time interval associated with the historical remaining charging time change value is used as a local fluctuation feature.

[0194] Each module in the above-mentioned vehicle charging remaining time determination device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0195] In one embodiment, a vehicle-side control device is also provided, whose internal structure diagram can be shown in Figure 7, including a memory and a processor, the memory stores a computer program, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0196] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0197] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0198] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0199] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0200] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for determining the remaining time of vehicle charging, characterized in that: The method comprises: Acquire the initial remaining charging time of the vehicle at the current charging moment during the charging process and the influencing characteristics of the remaining charging time of the vehicle during the charging process; The initial remaining charging time is corrected using the remaining charging time influencing feature to obtain a target remaining charging time for the vehicle at the current charging time.

2. The method according to claim 1, characterized in that The remaining charging time influencing feature includes a global degradation feature and a local fluctuation feature of the vehicle during the charging process; the global degradation feature is battery data associated with the attenuation of the battery charging and discharging performance of the vehicle battery at the current charging moment; the local fluctuation feature includes charging state data associated with the fluctuation of the remaining charging time during the charging process; The using the remaining charging time influencing feature to correct the initial remaining charging time to obtain the target remaining charging time of the vehicle at the current charging time includes: The initial remaining charging time is corrected by using at least one of the global degradation feature and the local fluctuation feature to obtain a target remaining charging time for the vehicle at the current charging moment.

3. The method according to claim 1, characterized in that The remaining charging time influencing feature includes a global degradation feature and a local fluctuation feature of the vehicle during the charging process; the global degradation feature is battery data associated with the attenuation of the battery charging and discharging performance of the vehicle battery at the current charging moment; the local fluctuation feature includes charging state data associated with the fluctuation of the remaining charging time during the charging process; The using the remaining charging time influencing feature to correct the initial remaining charging time to obtain the target remaining charging time of the vehicle at the current charging time includes: Performing a first correction on the initial remaining charging time according to the global degradation feature to obtain a corrected initial remaining charging time; Obtaining a correction amount of the remaining charging time of the vehicle at the current charging time according to the local fluctuation characteristics; The corrected initial remaining charging time is subjected to a second correction using the remaining charging time correction amount to obtain a target remaining charging time for the vehicle at the current charging time.

4. The method according to claim 3, characterized in that: The first correction of the initial remaining charging time according to the global degradation characteristic to obtain the corrected initial remaining charging time includes: The global degradation feature is input into a time correction model, and a first correction is performed on the initial charging remaining time by using the time correction model and the charging state data at the current charging moment to obtain a corrected initial charging remaining time.

5. The method according to claim 3, characterized in that: The obtaining, according to the local fluctuation characteristics, a correction amount of the remaining charging time of the vehicle at the current charging time includes: The local fluctuation characteristic is input into a pre-constructed local fluctuation characteristic influence time function to obtain a correction amount of the remaining charging time corresponding to the local fluctuation characteristic; the local fluctuation characteristic influence time function is obtained based on the historical charging status data of the vehicle battery in the current life cycle and the historical remaining charging time corresponding to the historical charging status data.

6. The method according to claim 5, characterized in that The step of obtaining the local fluctuation characteristic affecting the time function comprises: Acquire historical charging status data of the vehicle battery in the current life cycle and historical charging remaining time corresponding to the historical charging status data; The historical charging remaining time is sampled using a preset charging moment sampling interval to obtain a plurality of historical charging remaining time change values. When the historical charging remaining time change value is greater than a preset time change threshold, the charging state data corresponding to the historical charging remaining time change value is used as a local fluctuation feature, and each of the local fluctuation features is combined into a local fluctuation feature sequence; The local fluctuation feature sequence is tracked and predicted by using a particle filter algorithm to obtain a predicted local fluctuation feature sequence, and the predicted local fluctuation feature sequence is fitted by using polynomial regression to obtain a local fluctuation feature influence time function.

7. The method according to claim 6, characterized in that The method of tracking and predicting the local fluctuation feature sequence by using a particle filter algorithm to obtain a predicted local fluctuation feature sequence, and fitting the predicted local fluctuation feature sequence by using polynomial regression to obtain a local fluctuation feature influence time function includes: Initialize using the initial probability density filter function to generate a particle swarm; Update the weight of each particle and normalize it to get the weight of each particle; Resample each particle to obtain a new particle set and weight; The local fluctuation characteristic sequence is predicted by using the state equation to obtain a predicted local fluctuation characteristic sequence, and the predicted local fluctuation characteristic sequence is fitted by using polynomial regression to obtain a univariate polynomial regression function; Solving the parameters of the univariate polynomial regression function using the least squares method to obtain a coefficient matrix; According to the coefficient matrix and the univariate polynomial regression function, the local fluctuation characteristic influence time function is obtained.

8. The method according to claim 3, characterized in that The step of acquiring the local fluctuation characteristics of the vehicle during the charging process includes: Obtain the historical remaining charging time of the vehicle from the start of charging to the current charging time during the current charging process; According to the historical remaining charging time and the preset charging time sampling interval, a plurality of historical remaining charging time change values ​​are obtained; When the historical charging remaining time change value is greater than a preset time change threshold, the charging state data corresponding to the charging time interval associated with the historical charging remaining time change value is used as a local fluctuation feature.

9. A device for determining the remaining time of vehicle charging, characterized in that: The device comprises: A feature extraction module, used to obtain the initial remaining charging time of the vehicle at the current charging moment during the charging process and the influencing features of the remaining charging time of the vehicle during the charging process; The remaining time correction module is used to correct the initial remaining charging time by using the remaining charging time correction amount to obtain the target remaining charging time of the vehicle at the current charging time.

10. A vehicle-side control device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images