Automobile endurance mileage prediction method, device, equipment and storage medium

Abstract

The application relates to a vehicle endurance mileage prediction method, device, equipment and storage medium, which comprises the following steps: collecting mileage prediction related data of a vehicle; processing the mileage prediction related data through a pre-trained first mileage prediction model to obtain a motor power sequence corresponding to a future time period; determining a basic endurance mileage according to the motor power sequence; obtaining a preset calibration factor, correcting the basic endurance mileage by using the preset calibration factor, and obtaining a target endurance mileage. It can be seen that the endurance mileage can be accurately determined.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a method, apparatus, device, and storage medium for predicting the driving range of an automobile. Background Technology

[0002] New energy vehicles (including pure electric vehicles and plug-in hybrid electric vehicles) are gradually becoming the mainstream direction of the automotive industry due to their environmental protection and energy-saving advantages. For users of new energy vehicles, driving range, which is the maximum distance a vehicle can travel continuously under certain driving conditions, is one of the most important core indicators. Therefore, accurately determining the driving range of new energy vehicles has become an urgent problem to be solved in the field of new energy vehicle technology. Summary of the Invention

[0003] This application provides a method, apparatus, device, and storage medium for predicting vehicle driving range, which can accurately determine the driving range.

[0004] In a first aspect, this application provides a method for predicting the driving range of a vehicle, the method comprising: Collect vehicle mileage prediction data; The mileage prediction data is processed by a pre-trained first mileage prediction model to obtain the motor power sequence corresponding to the future time period. The basic driving range is determined based on the motor power sequence. Obtain a preset calibration factor, and use the preset calibration factor to correct the base driving range to obtain the target driving range.

[0005] Optionally, the basic driving range is determined based on the motor power sequence, including: Based on the motor power sequence, the predicted total energy consumption is determined; Based on the vehicle's current speed and the said future time period, predict the energy recovery of regenerative braking; Subtracting the energy recovered by regenerative braking from the predicted total energy consumption yields the first total energy demand. The basic driving range is obtained by processing the currently available battery energy and the first total energy demand using a pre-trained second range prediction model.

[0006] Optionally, based on the motor power sequence, the predicted total energy consumption is determined, including: The predicted drive energy consumption is obtained by integrating the motor power sequence over time. Obtain the energy consumption characteristics of the attachments, and determine the predicted energy consumption of the attachments based on the energy consumption characteristics of the attachments; The predicted driving energy consumption and the predicted accessory energy consumption are added together to obtain the predicted total energy consumption.

[0007] Optionally, based on the vehicle's current speed and the said future time period, predicting regenerative braking energy recovery includes: Based on the vehicle's current speed, determine the total road segment that the vehicle will travel in the future time period; The total road segment is divided into multiple sub-segments, and the elevation change and regeneration participation coefficient of each sub-segment are obtained; The target energy to be recovered for each sub-segment is determined based on the historical average recovery efficiency, total vehicle mass, elevation change of each sub-segment, and regeneration participation coefficient. The target recovered energy of each sub-segment is added together to obtain the regenerative braking recovered energy.

[0008] Optionally, the method further includes: Based on the actual total energy consumption and predicted total energy consumption corresponding to each historical trip, the error ratio corresponding to each historical trip is determined, and the error ratio sequence is obtained; A preset calibration factor is determined based on the error ratio sequence.

[0009] Optionally, the method further includes: Based on the error ratio sequence, determine the target uncertainty coefficient; Based on the target uncertainty coefficient, determine the first coefficient and the second coefficient; The minimum driving range is determined based on the first coefficient and the target driving range, and the maximum driving range is determined based on the second coefficient and the target driving range. The driving range is determined based on the minimum and maximum driving range.

[0010] Optionally, determining the target uncertainty coefficient based on the error ratio sequence includes: Determine the mean and standard deviation corresponding to the error ratio sequence; The ratio of the mean to the standard deviation is determined as the reference uncertainty coefficient; When the reference uncertainty coefficient is greater than the preset maximum uncertainty coefficient, the maximum uncertainty coefficient is determined as the target uncertainty coefficient; When the reference uncertainty coefficient is not greater than the preset maximum uncertainty coefficient, the reference uncertainty coefficient is determined as the target uncertainty coefficient.

[0011] Optionally, the method further includes: The second total energy demand is determined based on the target distance from the vehicle's current location to the target location; Multiply the preset calibration factor by the second total energy requirement to obtain the third total energy requirement; Based on the currently available battery energy, the third total energy demand, and the total battery capacity, determine the estimated remaining percentage of battery power to reach the target location.

[0012] Optionally, the mileage prediction data includes a target driving aggression index, and the method further includes: The target duration for which the vehicle's acceleration exceeds a preset threshold within a preset time period is obtained, as well as the total driving time within the preset time period. A reference driving aggression index is determined based on the ratio between the target duration and the total driving time. The minimum value between the reference driving aggression index and the preset maximum driving aggression index is determined as the target driving aggression index.

[0013] Secondly, this application provides a vehicle range prediction device, the device comprising: The data acquisition unit is used to collect data related to vehicle mileage prediction. The processing unit is used to process the mileage prediction-related data through a pre-trained first mileage prediction model to obtain the motor power sequence corresponding to the future time period. The first determining unit is used to determine the basic driving range based on the motor power sequence; The correction unit is used to obtain a preset calibration factor and use the preset calibration factor to correct the basic driving range to obtain the target driving range.

[0014] Optionally, the first determining unit is used for: Based on the motor power sequence, the predicted total energy consumption is determined; Based on the vehicle's current speed and future time period, predict the energy recovery of regenerative braking; Subtracting the energy recovered by regenerative braking from the predicted total energy consumption yields the first total energy demand. The basic driving range is obtained by processing the currently available battery energy and the first total energy demand using a pre-trained second range prediction model.

[0015] Optionally, the first determining unit is used for: The predicted drive energy consumption is obtained by integrating the motor power sequence over time. Obtain the energy consumption characteristics of the attachments, and determine the predicted energy consumption of the attachments based on the energy consumption characteristics of the attachments; The predicted driving energy consumption and the predicted accessory energy consumption are added together to obtain the predicted total energy consumption.

[0016] Optionally, the first determining unit is used for: Based on the vehicle's current speed, determine the total road segment that the vehicle will travel in the future time period; The total road segment is divided into multiple sub-segments, and the elevation change and regeneration participation coefficient of each sub-segment are obtained; The target energy to be recovered for each sub-segment is determined based on the historical average recovery efficiency, total vehicle mass, elevation change of each sub-segment, and regeneration participation coefficient. The target recovered energy of each sub-segment is added together to obtain the regenerative braking recovered energy.

[0017] Optionally, the apparatus further includes a second determining unit, the second determining unit being configured to: Based on the actual total energy consumption and predicted total energy consumption corresponding to each historical trip, the error ratio corresponding to each historical trip is determined, and the error ratio sequence is obtained; A preset calibration factor is determined based on the error ratio sequence.

[0018] Optionally, the apparatus further includes a third determining unit, the third determining unit being configured to: Based on the error ratio sequence, determine the target uncertainty coefficient; Based on the target uncertainty coefficient, determine the first coefficient and the second coefficient; The minimum driving range is determined based on the first coefficient and the target driving range, and the maximum driving range is determined based on the second coefficient and the target driving range. The driving range is determined based on the minimum and maximum driving range.

[0019] Optionally, the third determining unit is used for: Determine the mean and standard deviation corresponding to the error ratio sequence; The ratio of the mean to the standard deviation is determined as the reference uncertainty coefficient; When the reference uncertainty coefficient is greater than the preset maximum uncertainty coefficient, the maximum uncertainty coefficient is determined as the target uncertainty coefficient; When the reference uncertainty coefficient is not greater than the preset maximum uncertainty coefficient, the reference uncertainty coefficient is determined as the target uncertainty coefficient.

[0020] Optionally, the apparatus further includes a fourth determining unit, the fourth determining unit being configured to: The second total energy demand is determined based on the target distance from the vehicle's current location to the target location; Multiply the preset calibration factor by the second total energy requirement to obtain the third total energy requirement; Based on the currently available battery energy, the third total energy demand, and the total battery capacity, determine the estimated remaining percentage of battery power to reach the target location.

[0021] Optionally, the mileage prediction data includes a target driving aggression index, and the device further includes a fifth determining unit, the fifth determining unit being used for: The target duration for which the vehicle's acceleration exceeds a preset threshold within a preset time period is obtained, as well as the total driving time within the preset time period. A reference driving aggression index is determined based on the ratio between the target duration and the total driving time. The minimum value between the reference driving aggression index and the preset maximum driving aggression index is determined as the target driving aggression index.

[0022] Thirdly, this application provides a vehicle range prediction device, comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; and at least one memory connected to the at least one bus, wherein the processor is configured to: Collect vehicle mileage prediction data; The mileage prediction data is processed by a pre-trained first mileage prediction model to obtain the motor power sequence corresponding to the future time period. The basic driving range is determined based on the motor power sequence. Obtain a preset calibration factor, and use the preset calibration factor to correct the base driving range to obtain the target driving range.

[0023] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method for predicting vehicle driving range.

[0024] Compared with the prior art, the technical solution provided in this application has the following advantages: In this application embodiment, vehicle mileage prediction-related data is collected; the mileage prediction-related data is processed by a pre-trained first mileage prediction model to obtain a motor power sequence corresponding to a future time period; a basic driving range is determined based on the motor power sequence; a preset calibration factor is obtained, and the basic driving range is corrected using the preset calibration factor to obtain the target driving range. It can be seen that this application predicts future motor power using a pre-trained mileage prediction model, calculates the basic driving range based on the prediction results, and then corrects the basic driving range using a calibration factor, thereby accurately determining the driving range. Attached Figure Description

[0025] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0026] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0028] Figure 1 A flowchart illustrating a method for predicting vehicle driving range provided in an embodiment of this application; Figure 2 A flowchart illustrating a method for determining basic driving range provided in an embodiment of this application; Figure 3 A flowchart illustrating a method for determining a preset calibration factor provided in an embodiment of this application; Figure 4 A flowchart illustrating a method for determining driving range provided in an embodiment of this application; Figure 5 A flowchart illustrating a method for determining the estimated remaining battery percentage provided in an embodiment of this application; Figure 6 A flowchart illustrating a method for determining a driving aggression index provided in an embodiment of this application; Figure 7 A schematic flowchart of a vehicle range prediction device provided in this application embodiment; Figure 8 This is a schematic diagram of a vehicle range prediction device provided in an embodiment of this application. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0030] The following disclosure provides numerous different embodiments or examples for implementing various structures of this application. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of this application. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0031] New energy vehicles (including pure electric vehicles and plug-in hybrid electric vehicles) are gradually becoming the mainstream direction of the automotive industry due to their environmental protection and energy-saving advantages. For users of new energy vehicles, driving range, which is the maximum distance a vehicle can travel continuously under certain driving conditions, is one of the most important core indicators. Therefore, accurately determining the driving range of new energy vehicles has become an urgent problem to be solved in the field of new energy vehicle technology.

[0032] To address the aforementioned problems, embodiments of this application provide a method for predicting vehicle driving range. This method can determine the driving range based on vehicle mileage prediction data, such as... Figure 1 As shown, the specific steps include: Step 101: Collect relevant data for vehicle mileage prediction.

[0033] The mileage prediction data includes real-time vehicle operating data, environmental data, and user settings data. Real-time operating data includes vehicle speed signals, motor power signals, battery voltage signals, battery current signals, battery temperature signals, and acceleration signals; environmental data includes temperature signals and gradient signals; user settings data includes air conditioning set temperature and driving modes (such as economy mode, standard mode, sport mode, etc.).

[0034] In this step, the various signals mentioned above on the vehicle's CAN bus are collected at a preset sampling frequency. The collected raw data can be stored in the vehicle's buffer and subjected to necessary data preprocessing, including: applying a moving average filter to voltage and current signals to remove measurement noise; removing outliers from vehicle speed and acceleration signals, such as removing abnormal data points that exceed reasonable physical ranges; and aligning signals from different sampling frequencies in time to ensure that signals collected at the same time are synchronized, facilitating subsequent feature extraction. The preprocessed data is used as mileage prediction data for subsequent steps.

[0035] Step 102: Process the mileage prediction data using the pre-trained first mileage prediction model to obtain the motor power sequence corresponding to the future time period.

[0036] The first mileage prediction model is a machine learning model, which can be a neural network model or other models, without limitation here. Specifically, the first mileage prediction model is a local-global dual-branch fusion hybrid model, including a multi-local-scale dilated convolution module and a Transformer module. The multi-local-scale dilated convolution module is used to capture local dynamic features and multi-scale temporal patterns of driving behavior, while the Transformer module is used to model long-term dependencies and global features. Furthermore, the training process of this model is similar to existing training processes, and will not be elaborated upon here.

[0037] A motor power sequence refers to a set of predicted motor power values ​​arranged at preset time intervals (e.g., one prediction point per minute) within a future time period (e.g., the next 30 minutes), i.e., motor power prediction values ​​containing multiple time steps.

[0038] In this step, the mileage prediction data collected in step 101 is first used to construct features, forming a multi-dimensional feature set. The feature construction process includes: Using 60 seconds, 300 seconds, and 900 seconds as sliding windows respectively, the average value, standard deviation, and maximum value of vehicle speed, acceleration, and motor power were calculated to form time series statistical characteristics; The cumulative driving distance and cumulative energy consumption are recorded. The energy consumption per 100 kilometers is recorded every 0.1 kilometers driven. The most recent 60 recording points are used to form a historical energy consumption sequence, which is then standardized. Calculate the aggressiveness index and the constant speed ratio as characteristics of driving style; Calculate the average battery voltage, average current, average temperature, and rate of temperature change as battery state characteristics; When navigation data is available, obtain the elevation information of future road segments, calculate the average and maximum slope, and use them as environmental path features; The power consumption of accessories is estimated based on the difference between the air conditioner's set temperature and the ambient temperature, serving as a characteristic of accessory energy consumption.

[0039] Then, the constructed multidimensional feature set is input into the pre-trained first mileage prediction model to obtain the motor power sequence corresponding to the future time period.

[0040] Step 103: Determine the basic driving range based on the motor power sequence.

[0041] The base driving range is an uncalibrated initial driving range estimate calculated based on the motor power sequence.

[0042] In this step, the basic driving range is calculated based on the motor power sequence obtained in step 102, combined with the accessory energy consumption, regenerative braking energy recovery, and currently available battery energy.

[0043] Step 104: Obtain the preset calibration factor, and use the preset calibration factor to correct the basic driving range to obtain the target driving range.

[0044] The preset calibration factor is a correction coefficient determined based on historical prediction errors, used to compensate for deviations in the first mileage prediction model during prediction. The preset calibration factor is a dimensionless value with an initial value of 1.0, dynamically updated during actual driving as historical data accumulates, typically ranging from 0.8 to 1.2. The target driving range is the final driving range value output to the user after correction by the calibration factor.

[0045] In this step, a preset calibration factor is obtained, and the preset calibration factor is multiplied by the base driving range to obtain the target driving range.

[0046] In this embodiment, vehicle mileage prediction data is collected; the mileage prediction data is processed using a pre-trained first mileage prediction model to obtain a motor power sequence corresponding to a future time period; a basic driving range is determined based on the motor power sequence; a preset calibration factor is obtained, and the basic driving range is corrected using the preset calibration factor to obtain the target driving range. It can be seen that this application accurately determines the driving range by predicting future motor power using a pre-trained mileage prediction model, calculating the basic driving range based on the prediction results, and then correcting the basic driving range using a calibration factor.

[0047] When determining the basic driving range based on the predicted motor power sequence, it is considered that the energy consumption during vehicle operation includes not only the energy consumed by the motor drive, but also the energy consumed by accessories such as air conditioning and heating. Furthermore, the vehicle can recover some energy through regenerative braking during downhill driving or braking. To more accurately reflect the actual energy demand of the vehicle during future driving, embodiments of this application provide a method for determining the basic driving range, such as... Figure 2 As shown, the specific steps include: Step 201: Determine the predicted total energy consumption based on the motor power sequence.

[0048] The predicted total energy consumption is the predicted value of all energy consumption required for the vehicle to operate within a preset future time period, which includes the energy consumed by the drive motor and the energy consumed by auxiliary equipment such as air conditioning and heating.

[0049] In this step, the motor power sequence is integrated over time to obtain the predicted drive energy consumption; the accessory energy consumption characteristics are obtained, and the predicted accessory energy consumption is determined based on the accessory energy consumption characteristics; the predicted drive energy consumption and the predicted accessory energy consumption are added together to obtain the predicted total energy consumption.

[0050] The term "accessory" refers to all auxiliary equipment on the vehicle that consumes electrical energy, excluding the drive motor. For example, the accessories include, but are not limited to, devices other than the motor, such as air conditioning systems, electric power steering systems, lighting systems, and infotainment systems. The accessory energy consumption characteristics are the energy-related features of the accessory. When the accessory is an air conditioner, the accessory energy consumption characteristics are the air conditioner's set temperature, the ambient temperature, and the user-set operating time.

[0051] In this step, the motor power sequence is integrated over time, that is, the motor power at each time step is multiplied by the duration of that time step and then summed to obtain the predicted drive energy consumption; then, based on the energy consumption characteristics of the accessories, the predicted accessory energy consumption is determined; the predicted drive energy consumption and the predicted accessory energy consumption are added together to obtain the predicted total energy consumption.

[0052] Based on the energy consumption characteristics of accessories, the specific steps for determining the predicted energy consumption of accessories are as follows: For each accessory, calculate the predicted accessory energy consumption according to its corresponding accessory energy consumption characteristics; then, add up the predicted accessory energy consumption of all accessories, and use the sum as the final predicted accessory energy consumption. For ease of understanding, the following explanation uses an air conditioning system as an example. When the accessory is an air conditioning system, its accessory energy consumption characteristics include: the air conditioning set temperature, the ambient temperature, and the user-set air conditioning operating time. The specific steps for determining the air conditioning system energy consumption based on the above accessory energy consumption characteristics are as follows: First, calculate the temperature difference between the air conditioning set temperature and the ambient temperature. Based on this temperature difference, and combined with the preset correspondence between temperature difference and air conditioning power (e.g., a temperature difference-power mapping table or a power characteristic curve), estimate the corresponding air conditioning power. Next, the user-defined air conditioner operating time is obtained and compared with the duration of a future time period: if the user-defined operating time is less than or equal to the duration of the future time period, the user-defined operating time is used as the effective operating time; if the user-defined operating time is greater than the duration of the future time period, the duration of the future time period is used as the effective operating time; that is, the smaller of the two values ​​is taken as the effective operating time. Finally, the estimated air conditioner power is multiplied by the effective operating time to obtain the predicted energy consumption of the air conditioning system. The predicted energy consumption of other types of accessories can be calculated separately using a similar method to that of the air conditioning system described above, and will not be elaborated here.

[0053] Step 202: Based on the vehicle's current speed and future time period, predict the energy recovery from regenerative braking.

[0054] Regenerative braking energy recovery refers to the predicted energy recovered by the vehicle through the regenerative braking system over a future period. When the vehicle decelerates or goes downhill, the drive motor acts as a generator, converting the vehicle's kinetic or potential energy into electrical energy and storing it back in the battery. This energy is the regenerative braking energy recovery.

[0055] In this step, the total road segment that the vehicle will travel in the future time period is determined based on the vehicle's current speed; the total road segment is divided into multiple sub-segments, and the elevation change and regeneration participation coefficient of each sub-segment are obtained; the target recovery energy of each sub-segment is determined based on the historical average recovery efficiency, the total mass of the vehicle, the elevation change and regeneration participation coefficient of each sub-segment; the target recovery energy of each sub-segment is added together to obtain the regenerative braking recovery energy.

[0056] The elevation change is the difference between the starting and ending elevations of each sub-segment. When the sub-segment is downhill, the elevation change is positive, indicating a decrease in vehicle potential energy, which is beneficial for regenerative braking to recover energy. When the sub-segment is uphill, the elevation change is negative, indicating an increase in vehicle potential energy, requiring additional energy to climb. Elevation changes can be obtained from road elevation data in the navigation system. The regenerative braking participation coefficient is the degree to which the regenerative braking system participates in energy recovery on each sub-segment, ranging from 0 to 1. This coefficient is determined based on the slope of the sub-segment. For example, on a gentle downhill slope, the driver may only need to lightly apply the brake pedal, with the regenerative braking system partially participating in recovery, resulting in a smaller regenerative braking participation coefficient (e.g., 0.3). On a steep downhill slope, the driver needs to brake more force, with the regenerative braking system fully participating, resulting in a larger regenerative braking participation coefficient (e.g., 0.9). On uphill or flat roads with constant speed, the vehicle does not need to brake, the regenerative braking system does not participate in recovery, and the regenerative braking participation coefficient is 0. Historical average recovery efficiency is the average efficiency by which a vehicle's regenerative braking system converts mechanical energy into electrical energy and stores it in the battery. Its value typically ranges from 0.6 to 0.9 (i.e., 60% to 90%). This efficiency can be dynamically updated by learning the ratio of actual recovery to theoretical recovery during the vehicle's historical driving process. Target recovery energy is the expected amount of electrical energy that can be recovered on each sub-segment.

[0057] In this step, the vehicle's current speed is multiplied by the duration of the future time period to obtain the estimated travel distance. This estimated distance is then combined with the navigation path or historical travel routes to determine the total road segment corresponding to this estimated travel distance. The total road segment is divided into multiple sub-segments (e.g., based on road slope change points or fixed distance intervals), and the elevation change (obtained from road elevation data in the navigation system) and regeneration participation coefficient (determined based on the sub-segment's slope, within a preset range of slopes and regeneration participation coefficients, or determined using other methods, which are not limited here) are obtained for each sub-segment. Then, based on the historical average recovery efficiency, the vehicle's total mass, the elevation change of each sub-segment, and the regeneration participation coefficient, the target recovery energy for each sub-segment is determined. Finally, the target recovery energies of each sub-segment are summed to obtain the regenerative braking recovery energy for the future time period.

[0058] The specific steps for determining the target recoverable energy are as follows: For each sub-segment, multiply its elevation change by the gravitational acceleration and the total mass of the vehicle to obtain the potential energy change of the sub-segment; multiply the potential energy change by the regeneration participation coefficient to obtain the mechanical energy participating in the recovery of the sub-segment; and then multiply the mechanical energy participating in the recovery by the historical average recovery efficiency to obtain the target recoverable energy of the sub-segment.

[0059] Step 203: Subtract the energy recovered by regenerative braking from the predicted total energy consumption to obtain the first total energy demand.

[0060] Step 204: The current available battery energy and the first total energy demand are processed by the pre-trained second mileage prediction model to obtain the basic driving range.

[0061] The second mileage prediction model is similar to the first mileage prediction model, and will not be described in detail here. The currently available battery energy is the remaining electrical energy in the power battery that can power the vehicle in its current state.

[0062] In this step, the first total energy demand obtained in step 203 and the current available battery energy obtained from the BMS are used as input data and fed into the pre-trained second range prediction model. The model calculates and outputs a value, which is the base driving range.

[0063] In this embodiment, after predicting the motor power sequence and calculating the basic driving range using a pre-trained first mileage prediction model, a calibration factor needs to be determined to correct the basic driving range in order to further eliminate the model's prediction bias. Therefore, this embodiment provides a method for determining a preset calibration factor, such as... Figure 3 As shown, the specific steps include: Step 301: Based on the actual total energy consumption and predicted total energy consumption corresponding to each historical trip, determine the error ratio corresponding to each historical trip to obtain the error ratio sequence.

[0064] The historical journey is the driving process corresponding to one prediction process. When the cumulative duration of continuous driving reaches the duration of a future preset time period and no power outage or engine shutdown occurs during this period, this continuous driving process is recorded as a complete historical journey.

[0065] In this step, for each historical trip, the actual total energy consumption and the predicted total energy consumption of that trip are obtained. Then, the actual total energy consumption is divided by the predicted total energy consumption to obtain the error ratio corresponding to that historical trip. For each completed historical trip, the corresponding error ratio is calculated in the above manner, and the error ratios are arranged in chronological order (the order in which the trips end) to form an error ratio sequence.

[0066] When the error ratio is equal to 1, it means that the predicted energy consumption is completely consistent with the actual energy consumption, and there is no prediction deviation. When the error ratio is greater than 1, it means that the actual energy consumption is higher than the predicted energy consumption, that is, the prediction model underestimates the actual energy consumption. When the error ratio is less than 1, it means that the actual energy consumption is lower than the predicted energy consumption, that is, the prediction model overestimates the actual energy consumption.

[0067] In the above process, the number of error ratios in the error ratio sequence increases continuously with the increase of vehicle mileage. When the length of the error ratio sequence reaches a preset queue length threshold (e.g., 50 times), a first-in-first-out (FIFO) approach is adopted for maintenance. That is, each time the latest error ratio is added, if the queue is full, the oldest error ratio is removed to ensure that the error ratio sequence always contains data from the most recent N historical trips, so that the calibration factor can quickly respond to changes in recent driving behavior.

[0068] Step 302: Determine the preset calibration factor based on the error ratio sequence.

[0069] In this step, when the number of error ratios in the error ratio sequence is less than a preset threshold, it indicates that the vehicle is in its initial usage phase or historical data is insufficient. In this case, the preset calibration factor is set to an initial value of 1.0, meaning no substantial correction is made to the base driving range. When the number of error ratios in the error ratio sequence is greater than or equal to the preset threshold, statistical calculations are performed on all error ratios in the sequence to determine the preset calibration factor. For example, the median of the error ratio sequence can be used as the preset calibration factor, or the arithmetic mean of the error ratio sequence can be used as the preset calibration factor, or a weighted average can be calculated for each error ratio in the sequence, and the weighted average result can be used as the preset calibration factor. In this calculation method, error ratios closer to the current time are given greater weight, allowing the calibration factor to respond more quickly to recent changes in driving style or vehicle status.

[0070] In this embodiment, considering the numerous uncertainties in actual driving (such as changes in road conditions, weather, and fluctuations in driving behavior), a single range value cannot fully reflect the reliability of the prediction, and users find it difficult to judge the accuracy and credibility of the value. If only a fixed range number is displayed to the user, any deviation between the actual range and the displayed value can easily lead to misjudgment, causing range anxiety or even breakdowns. Therefore, to provide users with more comprehensive and reliable range information, help them understand the uncertainty of the prediction, and make reasonable travel and charging decisions accordingly, this embodiment also provides a method for determining the range, such as... Figure 4 As shown, the specific steps include: Step 401: Determine the target uncertainty coefficient based on the error ratio sequence.

[0071] The uncertainty coefficient is a quantitative indicator used to measure the degree of uncertainty in the predicted driving range, and its value is greater than 0. The larger the uncertainty coefficient, the higher the uncertainty of the prediction result, and the greater the deviation of the actual driving range from the target value; conversely, the smaller the uncertainty coefficient, the more reliable the prediction result, and the closer the actual driving range is to the target driving range.

[0072] In this step, the mean and standard deviation corresponding to the error ratio sequence are determined; the ratio of the mean to the standard deviation is determined as the reference uncertainty coefficient; when the reference uncertainty coefficient is greater than the preset maximum uncertainty coefficient, the maximum uncertainty coefficient is determined as the target uncertainty coefficient; when the reference uncertainty coefficient is not greater than the preset maximum uncertainty coefficient, the reference uncertainty coefficient is determined as the target uncertainty coefficient.

[0073] The maximum uncertainty coefficient is a pre-set upper limit for uncertainty. For example, the maximum uncertainty coefficient is 0.3. This upper limit is set based on the following: when the uncertainty coefficient is 0.3, the corresponding driving range is a range centered on the target driving range, fluctuating by 30% above and below. This range, with current technology, can cover most driving range deviations in real-world scenarios. Simultaneously, psychological research shows that prediction deviations exceeding 30% significantly exacerbate users' range anxiety; setting an upper limit of 0.3 avoids presenting users with an overly wide driving range, thus preventing decision-making confusion. Therefore, limiting the uncertainty coefficient to within 0.3 objectively reflects the uncertainty of the prediction without losing its reference value due to an excessively wide range.

[0074] Specifically, the arithmetic mean and standard deviation of all error ratios in the error ratio sequence are calculated. The standard deviation is divided by the mean, and the resulting ratio is used as the reference uncertainty coefficient. Then, the reference uncertainty coefficient is compared with the preset maximum uncertainty coefficient. When the reference uncertainty coefficient is greater than the maximum uncertainty coefficient, the maximum uncertainty coefficient is used as the target uncertainty coefficient; when the reference uncertainty coefficient is less than or equal to the maximum uncertainty coefficient, the reference uncertainty coefficient is used as the target uncertainty coefficient.

[0075] It should be noted that the reference uncertainty coefficient calculated above is essentially the coefficient of variation (CV) of the error ratio sequence, used to measure the dispersion of each error ratio relative to its average value. When the values ​​of the error ratios in the error ratio sequence are relatively concentrated, the standard deviation is small, and the reference uncertainty coefficient is small, indicating that the prediction model output is stable and reliable. When the values ​​of the error ratios are relatively dispersed, the standard deviation is large, and the reference uncertainty coefficient is large, indicating that the performance of the prediction model varies greatly under different operating conditions, and the uncertainty of the prediction results is high.

[0076] Step 402: Determine the first coefficient and the second coefficient based on the target uncertainty coefficient.

[0077] The first coefficient is a multiplication factor used to calculate the minimum driving range, and the second coefficient is a multiplication factor used to calculate the maximum driving range. The first coefficient is less than 1, and the second coefficient is greater than 1.

[0078] In this step, subtract the target uncertainty coefficient from 1 to obtain the first coefficient; add the target uncertainty coefficient to 1 to obtain the second coefficient.

[0079] For example, when the uncertainty coefficient is 0.1, the first coefficient = 1 - 0.1 = 0.9, and the second coefficient = 1 + 0.1 = 1.1.

[0080] Step 403: Multiply the first coefficient by the target range to obtain the minimum range, and multiply the second coefficient by the target range to obtain the maximum range.

[0081] The minimum driving range is the lower limit of the driving range, representing the most conservative estimate of the actual driving range that the vehicle can travel; the maximum driving range is the upper limit of the driving range, representing the driving range that the vehicle may reach under optimistic estimation.

[0082] It should be noted that when the calculated minimum driving range is less than 0, the minimum driving range is set to 0, because the driving range cannot be negative.

[0083] Step 404: Determine the range based on the minimum and maximum range.

[0084] In this step, the minimum driving range is used as the lower limit of the driving range range, and the maximum driving range is used as the upper limit of the driving range range, thereby determining the driving range range.

[0085] In practice, the driving range range, along with the target driving range, can be displayed on the vehicle's instrument panel or central control screen. For example, the instrument panel can simultaneously display the following information: target driving range (e.g., "Typical range: 400km"), driving range range (e.g., "Driving range: 360km ~ 440km"), and the corresponding confidence level (e.g., "Confidence level: 90%)".

[0086] The confidence level can be understood as the probability estimate that the stated driving range range can cover the actual driving range. It is calculated as: Confidence Level = (1 - Target Uncertainty Coefficient) × 100%. For example, when the uncertainty coefficient is 0.1, the confidence level is 90%. That is, based on the statistical regularity of historical prediction errors, there is approximately a 90% probability that the actual driving range will fall within the displayed driving range range.

[0087] By simultaneously displaying typical range, range distance, and confidence level to users, users can gain a more comprehensive and intuitive understanding of the reliability of the prediction results. This helps users make more reasonable travel and charging decisions, effectively alleviates range anxiety, and avoids breakdowns on the road due to deviations in a single range value.

[0088] In this embodiment, based on the aforementioned range prediction method and preset calibration factor determination method, the energy consumption of the vehicle during future driving can be accurately predicted. After a user sets a navigation destination, the user not only needs to know the current range but also urgently wants to know whether the vehicle can successfully reach the destination and how much battery power will remain upon arrival, in order to decide whether charging is necessary. Therefore, to provide users with estimated battery power upon arrival in navigation scenarios, assisting them in trip planning and charging decisions, this embodiment also provides a method for determining the estimated remaining battery percentage, such as... Figure 5 As shown, the specific steps include: Step 501: Determine the second total energy requirement based on the target distance from the vehicle's current location to the target location.

[0089] The target location is the navigation destination set by the user through the in-vehicle navigation system or mobile map application. It can be a specific location name, a latitude and longitude coordinate, or a point of interest (such as "nearest charging station").

[0090] In this step, the vehicle's current location and target location are first obtained. The navigation system then plans the route and calculates the distance from the current location to the target location, which is taken as the target distance. This target distance can be determined based on the route planning results provided by the navigation system, which may include, but is not limited to, the shortest path, the fastest path, or a route that avoids congestion. The specific path can be determined according to the user's navigation settings.

[0091] Then, the vehicle's current speed is obtained, and the target distance is divided by the current speed to estimate the travel time required for the vehicle to travel from the current location to the target location. It should be noted that when the vehicle's current speed is 0 (i.e., the vehicle is stationary) or the speed is extremely low, the average speed predicted by the navigation system or the average speed under historical road conditions can be used instead of the current speed for calculation.

[0092] Secondly, the estimated travel time is used as the new prediction time period. Following the method described in step 102 above, the mileage prediction data (including real-time operating data, environmental data, and user setting data) collected in real time at the vehicle's current location is input into the pre-trained first mileage prediction model to predict the second motor power sequence corresponding to the new prediction time period. When the estimated travel time exceeds the maximum single prediction time of the first mileage prediction model (e.g., 30 minutes), the travel time is divided into multiple consecutive time windows. A rolling prediction method is used to predict the motor power sequence window by window. The first window uses the currently collected real-time data as input, and subsequent windows use the prediction result of the previous window and the corresponding environmental path features as input. Finally, the second motor power sequence covering the entire estimated travel time is obtained by splicing the data together.

[0093] Then, based on the second motor power sequence, the following is adopted: Figure 2 The second total energy demand is determined in a manner similar to the method for determining the basic driving range shown (i.e., steps 201 to 204).

[0094] Step 502: Multiply the preset calibration factor by the second total energy requirement to obtain the third total energy requirement.

[0095] In this step, the preset calibration factor is multiplied by the second total energy requirement to obtain the product, and this product is determined as the third total energy requirement.

[0096] Step 503: Determine the estimated remaining percentage of battery power to reach the target location based on the current available battery energy, the third total energy demand, and the total battery capacity.

[0097] The currently available battery energy refers to the remaining electrical energy in the vehicle's power battery that can be discharged at the current moment, calculated and provided in real time by the battery management system. The total battery capacity is the rated total capacity of the vehicle's power battery, i.e., the total electrical energy stored when the battery is fully charged, determined by the vehicle's factory parameters and stored in the vehicle system. The estimated remaining charge percentage is the percentage of the power battery's remaining charge relative to the total battery capacity after the vehicle has traveled from its current location to its destination, used to characterize the battery's remaining energy level upon arrival.

[0098] In this step, the current available battery energy is first obtained from the battery management system. Then, the current available battery energy is subtracted from the third total energy requirement to obtain the estimated remaining energy. Finally, this estimated remaining energy is divided by the total battery capacity and then multiplied by 100% to obtain the estimated percentage of remaining charge upon reaching the target location.

[0099] For example, when the currently available battery energy is 60kWh, the third total energy demand is 11.88kWh, and the total battery capacity is 75kWh, the estimated remaining energy = 60 - 11.88 = 48.12kWh, and the estimated remaining percentage of charge = 48.12 ÷ 75 × 100% = 64.16%, that is, according to the current prediction, the remaining battery charge after the vehicle arrives at its destination will be approximately 64.16%.

[0100] Additionally, when the estimated remaining battery percentage is less than a preset low battery threshold (e.g., 10%), it indicates that the battery level will be low upon arrival at the destination. In this case, a low battery warning is triggered, displaying a warning message on the navigation interface and recommending charging stations along the route to help the user plan charging locations and avoid the vehicle breaking down due to depleted battery. When the estimated remaining battery percentage is negative, it indicates that the current battery energy is insufficient to support the vehicle's journey to the target location. The system issues a warning message (e.g., "Current battery level cannot reach the destination") and automatically recommends charging stations or battery swapping stations within range of the current battery capacity as intermediate charging points.

[0101] In this embodiment, the mileage prediction data includes a target driving aggression index. The target driving aggression index characterizes the driver's aggressiveness during driving and is an important quantitative indicator reflecting driving style. Different drivers have significantly different driving styles; aggressive drivers tend to accelerate and decelerate rapidly, resulting in drastic fluctuations in motor power and higher energy consumption; while mild-mannered drivers accelerate smoothly and maintain a stable speed, resulting in relatively lower energy consumption. By introducing the driving aggression index, the mileage prediction model can more accurately capture the impact of driving behavior on energy consumption, thereby improving the accuracy of range prediction. Therefore, this embodiment provides a method for determining the driving aggression index, such as... Figure 6 As shown, the specific steps include: Step 601: Obtain the target duration for which the vehicle's acceleration exceeds a preset threshold within a preset time period, and the total driving time within the preset time period.

[0102] The preset threshold is a critical acceleration value used to determine whether a vehicle is undergoing "rapid acceleration." When the instantaneous acceleration of the vehicle exceeds this threshold, it indicates that the driver is performing rapid acceleration. For example, a typical value for the preset threshold is 2.0 m / s², which is a calibrated value and can be adaptively adjusted according to the power characteristics of different vehicle models. The preset time period is a fixed time window used to statistically analyze driving behavior. For example, the preset time period can be the most recent 5 minutes, the most recent 10 minutes, or the total driving time since the start of the current trip.

[0103] Step 602: Determine the reference driving aggression index based on the ratio between the target duration and the total driving time.

[0104] In this step, the ratio between the target duration and the total driving time is determined, and this ratio is multiplied by a scaling factor to obtain the reference driving aggression index. The scaling factor is the scaling factor that maps the acceleration frequency to the [0,1] interval, and is a calibration coefficient (typically 10).

[0105] Step 603: The minimum value between the reference driving aggression index and the preset maximum driving aggression index is determined as the target driving aggression index.

[0106] The maximum driving aggression index is a preset upper limit value for driving aggression. For example, the maximum driving aggression index is 1.0.

[0107] In this step, when the reference driving aggressive index is less than or equal to the maximum driving aggressive index, the reference driving aggressive index is directly used as the target driving aggressive index; when the reference driving aggressive index is greater than the maximum driving aggressive index, the maximum driving aggressive index is used as the target driving aggressive index.

[0108] like Figure 7 As shown, this application provides a vehicle range prediction device, which corresponds to the method embodiment, and specifically includes: The data acquisition unit 701 is used to collect data related to vehicle mileage prediction. The processing unit 702 is used to process the mileage prediction-related data through a pre-trained first mileage prediction model to obtain the motor power sequence corresponding to the future time period. The first determining unit 703 is used to determine the basic driving range based on the motor power sequence; The correction unit 704 is used to obtain a preset calibration factor and use the preset calibration factor to correct the basic driving range to obtain the target driving range.

[0109] Optionally, the first determining unit 703 is used for: Based on the motor power sequence, the predicted total energy consumption is determined; Based on the vehicle's current speed and future time period, predict the energy recovery of regenerative braking; Subtracting the energy recovered by regenerative braking from the predicted total energy consumption yields the first total energy demand. The base driving range is obtained by processing the currently available battery energy and the first total energy demand using a pre-trained second range prediction model.

[0110] Optionally, the first determining unit 703 is used for: The predicted drive energy consumption is obtained by integrating the motor power sequence over time. Obtain the energy consumption characteristics of the attachments, and determine the predicted energy consumption of the attachments based on the energy consumption characteristics of the attachments; The predicted driving energy consumption and the predicted accessory energy consumption are added together to obtain the predicted total energy consumption.

[0111] Optionally, the first determining unit 703 is used for: Based on the vehicle's current speed, determine the total road segment that the vehicle will travel in the future time period; The total road segment is divided into multiple sub-segments, and the elevation change and regeneration participation coefficient of each sub-segment are obtained; The target energy to be recovered for each sub-segment is determined based on the historical average recovery efficiency, total vehicle mass, elevation change of each sub-segment, and regeneration participation coefficient. The target recovered energy of each sub-segment is added together to obtain the regenerative braking recovered energy.

[0112] Optionally, the device further includes a second determining unit 705, the second determining unit 705 being configured to: Based on the actual total energy consumption and predicted total energy consumption corresponding to each historical trip, the error ratio corresponding to each historical trip is determined, and the error ratio sequence is obtained; A preset calibration factor is determined based on the error ratio sequence.

[0113] Optionally, the device further includes a third determining unit 706, the third determining unit 706 being configured to: Based on the error ratio sequence, determine the target uncertainty coefficient; Based on the target uncertainty coefficient, determine the first coefficient and the second coefficient; The minimum driving range is determined based on the first coefficient and the target driving range, and the maximum driving range is determined based on the second coefficient and the target driving range. The driving range is determined based on the minimum and maximum driving range.

[0114] Optionally, the third determining unit 706 is used for: Determine the mean and standard deviation corresponding to the error ratio sequence; The ratio of the mean to the standard deviation is determined as the reference uncertainty coefficient; When the reference uncertainty coefficient is greater than the preset maximum uncertainty coefficient, the maximum uncertainty coefficient is determined as the target uncertainty coefficient; When the reference uncertainty coefficient is not greater than the preset maximum uncertainty coefficient, the reference uncertainty coefficient is determined as the target uncertainty coefficient.

[0115] Optionally, the device further includes a fourth determining unit 707, the fourth determining unit 707 being configured to: The second total energy demand is determined based on the target distance from the vehicle's current location to the target location; Multiply the preset calibration factor by the second total energy requirement to obtain the third total energy requirement; Based on the currently available battery energy, the third total energy demand, and the total battery capacity, determine the estimated remaining percentage of battery power to reach the target location.

[0116] Optionally, the mileage prediction data includes a target driving aggression index, and the device further includes a fifth determining unit 708, which is used to: The target duration for which the vehicle's acceleration exceeds a preset threshold within a preset time period is obtained, as well as the total driving time within the preset time period. A reference driving aggression index is determined based on the ratio between the target duration and the total driving time. The minimum value between the reference driving aggression index and the preset maximum driving aggression index is determined as the target driving aggression index.

[0117] like Figure 8 As shown in the figure, this application provides a vehicle range prediction device, including a processor 801, a communication interface 802, a memory 803, and a communication bus 804. The processor 801, communication interface 802, and memory 803 communicate with each other via the communication bus 804. Memory 803 is used to store computer programs; In one embodiment of this application, when the processor 801 executes the program stored in the memory 803, it implements the vehicle range prediction method provided in any of the foregoing method embodiments, including: The data acquisition unit is used to collect data related to vehicle mileage prediction. The processing unit is used to process the mileage prediction-related data through a pre-trained first mileage prediction model to obtain the motor power sequence corresponding to the future time period. The first determining unit is used to determine the basic driving range based on the motor power sequence; The correction unit is used to obtain a preset calibration factor and use the preset calibration factor to correct the basic driving range to obtain the target driving range.

[0118] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, performs the steps of the vehicle range prediction method provided in any of the foregoing method embodiments.

[0119] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0120] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0121] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also include the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that additional or alternative steps may be used.

[0122] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for predicting the driving range of a vehicle, characterized in that, The method includes: Collect vehicle mileage prediction data; The mileage prediction data is processed by a pre-trained first mileage prediction model to obtain the motor power sequence corresponding to the future time period. The basic driving range is determined based on the motor power sequence. Obtain a preset calibration factor, and use the preset calibration factor to correct the base driving range to obtain the target driving range.

2. The method according to claim 1, characterized in that, Based on the motor power sequence, the basic driving range is determined, including: Based on the motor power sequence, the predicted total energy consumption is determined; Based on the vehicle's current speed and the said future time period, predict the energy recovery of regenerative braking; Subtracting the energy recovered by regenerative braking from the predicted total energy consumption yields the first total energy demand. The basic driving range is obtained by processing the currently available battery energy and the first total energy demand using a pre-trained second range prediction model.

3. The method according to claim 2, characterized in that, Based on the motor power sequence, the predicted total energy consumption is determined, including: The predicted drive energy consumption is obtained by integrating the motor power sequence over time. Obtain the energy consumption characteristics of the attachments, and determine the predicted energy consumption of the attachments based on the energy consumption characteristics of the attachments; The predicted driving energy consumption and the predicted accessory energy consumption are added together to obtain the predicted total energy consumption.

4. The method according to claim 2, characterized in that, Based on the vehicle's current speed and the said future time period, predict regenerative braking energy recovery, including: Based on the vehicle's current speed, determine the total road segment that the vehicle will travel in the future time period; The total road segment is divided into multiple sub-segments, and the elevation change and regeneration participation coefficient of each sub-segment are obtained; The target energy to be recovered for each sub-segment is determined based on the historical average recovery efficiency, total vehicle mass, elevation change of each sub-segment, and regeneration participation coefficient. The target recovered energy of each sub-segment is added together to obtain the regenerative braking recovered energy.

5. The method according to claim 3, characterized in that, The method further includes: Based on the actual total energy consumption and predicted total energy consumption corresponding to each historical trip, the error ratio corresponding to each historical trip is determined, and the error ratio sequence is obtained; A preset calibration factor is determined based on the error ratio sequence.

6. The method according to claim 5, characterized in that, The method further includes: Based on the error ratio sequence, determine the target uncertainty coefficient; Based on the target uncertainty coefficient, determine the first coefficient and the second coefficient; The minimum driving range is determined based on the first coefficient and the target driving range, and the maximum driving range is determined based on the second coefficient and the target driving range. The driving range is determined based on the minimum and maximum driving range.

7. The method according to claim 6, characterized in that, Determining the target uncertainty coefficient based on the error ratio sequence includes: Determine the mean and standard deviation corresponding to the error ratio sequence; The ratio of the mean to the standard deviation is determined as the reference uncertainty coefficient; When the reference uncertainty coefficient is greater than the preset maximum uncertainty coefficient, the maximum uncertainty coefficient is determined as the target uncertainty coefficient; When the reference uncertainty coefficient is not greater than the preset maximum uncertainty coefficient, the reference uncertainty coefficient is determined as the target uncertainty coefficient.

8. The method according to claim 1, characterized in that, The method further includes: The second total energy demand is determined based on the target distance from the vehicle's current location to the target location; Multiply the preset calibration factor by the second total energy requirement to obtain the third total energy requirement; Based on the currently available battery energy, the third total energy demand, and the total battery capacity, determine the estimated remaining percentage of battery power to reach the target location.

9. The method according to claim 1, characterized in that, The mileage prediction data includes a target driving aggression index, and the method further includes: The target duration for which the vehicle's acceleration exceeds a preset threshold within a preset time period is obtained, as well as the total driving time within the preset time period. A reference driving aggression index is determined based on the ratio between the target duration and the total driving time. The minimum value between the reference driving aggression index and the preset maximum driving aggression index is determined as the target driving aggression index.

10. A vehicle range prediction device, characterized in that, The device includes: The data acquisition unit is used to collect data related to vehicle mileage prediction. The processing unit is used to process the mileage prediction-related data through a pre-trained first mileage prediction model to obtain the motor power sequence corresponding to the future time period. The first determining unit is used to determine the basic driving range based on the motor power sequence; The correction unit is used to obtain a preset calibration factor and use the preset calibration factor to correct the basic driving range to obtain the target driving range.

11. A vehicle range prediction device, characterized in that, include: At least one communication interface; At least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; At least one memory connected to the at least one bus, wherein the processor is configured to: Collect vehicle mileage prediction data; The mileage prediction data is processed by a pre-trained first mileage prediction model to obtain the motor power sequence corresponding to the future time period. The basic driving range is determined based on the motor power sequence. Obtain a preset calibration factor, and use the preset calibration factor to correct the base driving range to obtain the target driving range.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the vehicle range prediction method according to any one of claims 1 to 9.

Images