Endurance mileage prediction method, device, vehicle, computer device and storage medium

Abstract

The present application relates to a method, apparatus, vehicle, computer device, and storage medium for predicting driving range. During the operation of a target vehicle, nominal physical parameters of the target vehicle, as well as mileage parameters, energy consumption parameters, and state of charge parameters, are acquired, and secondary analysis and calculation are performed in combination with the mileage parameters, energy consumption parameters, and state of charge parameters to obtain the current driving range and current energy consumption per unit mileage of the target vehicle in the current state. Finally, in combination with the nominal physical parameters, current driving range, current energy consumption per unit mileage, and mileage parameters, the driving range of the target vehicle at any driving node within a preset future time period is predicted. Through this solution, the prediction of the driving range at a future moment can be achieved by combining the current driving range, current energy consumption per unit mileage, mileage parameters corresponding to the actual operating state of the target vehicle, and the nominal physical parameters inherent to the target vehicle itself.

Description

Technical Field

[0001] This application relates to the technical field of vehicles, and particularly to a method, device, vehicle, computer device, storage medium, and computer program product for predicting driving range. Background Art

[0002] With the development of new energy technologies, vehicles powered by batteries are becoming increasingly widely used in daily life, bringing great convenience to people's transportation. The electric energy stored in the vehicle's battery is limited, and it is usually necessary to recharge at a charging station to meet the driving range requirements. Therefore, estimating the driving range of a vehicle is of great significance for users' travel planning, driving safety, etc.

[0003] However, in related technologies, vehicles cannot predict the driving range at future times. Summary of the Invention

[0004] Based on this, it is necessary to propose a method, device, vehicle, computer device, storage medium, and computer program product for predicting driving range to achieve the prediction of the driving range of a vehicle at any moment within a certain future time period.

[0005] This application provides a method for predicting driving range, including: obtaining the operation data and nominal physical parameters of a target vehicle; the operation data includes mileage parameters, energy consumption parameters, and state of charge parameters; determining the current driving range and the current energy consumption per unit mileage according to the mileage parameters, the energy consumption parameters, and the state of charge parameters; predicting the driving range of the target vehicle at any driving node within a preset future time period according to the nominal physical parameters, the current driving range, the current energy consumption per unit mileage, and the mileage parameters.

[0006] In the above method for predicting driving range, during the operation of the target vehicle, the nominal physical parameters of the target vehicle, as well as the mileage parameters, energy consumption parameters, and state of charge parameters, are obtained, and secondary analysis and calculation are performed in combination with the mileage parameters, energy consumption parameters, and state of charge parameters to obtain the current driving range and the current energy consumption per unit mileage of the target vehicle in the current state. Finally, in combination with the nominal physical parameters, the current driving range, the current energy consumption per unit mileage, and the mileage parameters, the driving range of the target vehicle at any driving node within a preset future time period is predicted. Through this solution, the prediction of the driving range at future times can be achieved by combining the current driving range, the current energy consumption per unit mileage, the mileage parameters corresponding to the actual operation state of the target vehicle, and the nominal physical parameters inherent to the target vehicle.

[0007] In some embodiments, predicting the cruising range of the target vehicle at any driving node within a preset time period in the future based on the nominal physical parameters, the current cruising range, the current energy consumption per unit mileage and the mileage parameters includes: obtaining vehicle model information of the target vehicle; inputting the vehicle model information, the nominal physical parameters, the current cruising range, the current energy consumption per unit mileage and the mileage parameters into a preset cruising range attenuation model for prediction, so as to obtain the cruising range of the target vehicle at any driving node within the preset time period in the future.

[0008] The above solution, combined with a pre-trained range attenuation model for range prediction, has a high prediction efficiency.

[0009] In some embodiments, the predicting of the cruising range of the target vehicle at any driving node within a preset time period in the future includes: determining the cruising range of the target vehicle at the future time node or the future mileage node in combination with the future time node or future mileage node to be predicted.

[0010] The above scheme can predict the cruising range from two dimensions: mileage and time, and has a high prediction convenience.

[0011] In some embodiments, the method for determining the range attenuation model includes: obtaining the nominal physical parameters of the sample vehicle, and the historical operating data under each charging condition within a preset historical period; the historical operating data includes historical mileage parameters, historical energy consumption parameters and historical state of charge parameters, and the vehicle type of the sample vehicle is the same as the vehicle type of the target vehicle; analyzing and processing the historical mileage parameters, the historical energy consumption parameters and the historical state of charge parameters to determine the range data set and the unit mileage energy consumption data set; jointly determining the sample data corresponding to the sample vehicle by the historical mileage parameters, the nominal physical parameters, the range data set and the unit mileage energy consumption data set; obtaining a sample data set based on the sample data of multiple sample vehicles; and performing model training in combination with the sample data set and a preset training model to determine the range attenuation model.

[0012] The above scheme, for the same type of sample vehicles, combines the historical operation data to obtain the range data set and unit mileage energy consumption data set through secondary calculation, completes the construction of the range attenuation model, and improves the accuracy of the range attenuation model.

[0013] In some embodiments, analyzing and processing according to the historical mileage parameter, the historical energy consumption parameter, and the historical state of charge parameter to determine a cruising range data set and a unit mileage energy consumption data set includes: calculating according to the historical mileage parameter and the historical state of charge parameter to determine the cruising range data set; calculating according to the historical mileage parameter, the historical state of charge parameter, and the historical energy consumption parameter to determine the unit mileage energy consumption data set.

[0014] In the above solution, the cruising range data set and the unit mileage energy consumption data set are established through different historical operation data respectively, which improves the accuracy of the cruising range data set and the unit mileage energy consumption data set.

[0015] In some embodiments, calculating according to the historical mileage parameter and the historical state of charge parameter to determine the cruising range data set includes: calculating, according to the historical mileage parameter, the mileage difference between each charging condition and the previous charging condition; calculating, according to the historical state of charge parameter, the state of charge consumption value between each charging condition and the previous charging condition; analyzing and calculating according to the mileage difference and the state of charge consumption value to determine the cruising range data set.

[0016] In the above solution, each charging is taken as a working condition point respectively, and combined with the mileage change and the battery state of charge change of each working condition point, a highly reliable cruising range data set is established.

[0017] In some embodiments, the method further includes: determining the time difference between each charging condition and the previous charging condition; judging data jump and loss for each charging condition according to the time difference and the state of charge consumption value; and executing the step of analyzing and calculating according to the mileage difference and the state of charge consumption value to determine the cruising range data set when the data jump and loss judgment passes.

[0018] In the above solution, combining the time difference and the state of charge consumption value to perform data jump and loss judgment correction processing on each working condition point, that is, performing noise reduction processing on the data obtained at each working condition point, to improve the data accuracy of each working condition point.

[0019] In some embodiments, analyzing and calculating according to the mileage difference and the state of charge consumption value to determine the cruising range data set includes: analyzing and calculating according to the mileage difference and the state of charge consumption value to determine the original cruising range data set; and correcting the original cruising range data set to obtain the cruising range data set.

[0020] After determining the original endurance dataset by combining the driving range difference and the state of charge consumption value, the above solution will correct the original endurance dataset, and use the corrected original endurance dataset as the endurance dataset to further improve the accuracy of the endurance dataset.

[0021] In some embodiments, the correcting the original endurance dataset to obtain an endurance dataset includes: correcting the original endurance dataset according to the nominal physical parameters to obtain an endurance dataset.

[0022] The above solution combines the nominal physical parameters of the sample vehicle and eliminates the data in the original endurance dataset that does not meet the nominal physical parameters, which has high correction reliability.

[0023] In some embodiments, the correcting the original endurance dataset to obtain an endurance dataset includes: performing filtering and convergence correction on the original endurance dataset to obtain an endurance dataset.

[0024] The above solution corrects the original endurance dataset in a filtering and convergence manner, which has high correction efficiency.

[0025] In some embodiments, the calculating according to the historical mileage parameter, the historical state of charge parameter, and the historical energy consumption parameter to determine the unit mileage energy consumption dataset includes: calculating the driving range difference between each charging condition and the previous charging condition according to the historical mileage parameter; calculating the state of charge consumption value between each charging condition and the previous charging condition according to the historical state of charge parameter; analyzing and calculating according to the historical energy consumption parameter corresponding to each charging condition, the driving range difference, and the state of charge consumption value to determine the unit mileage energy consumption dataset.

[0026] The above solution combines the driving range change, the battery state of charge change at each working condition point, and the historical energy consumption parameters at each working condition point to establish a unit mileage energy consumption dataset, which improves the accuracy of the unit mileage energy consumption dataset.

[0027] In some embodiments, the method further includes: when the driving range difference is greater than or equal to a preset mileage threshold and the state of charge consumption value is greater than or equal to a preset state of charge threshold, determining the endurance dataset or the unit mileage energy consumption dataset based on the driving range difference and the state of charge consumption value; when the driving range difference is less than the preset mileage threshold and / or the state of charge consumption value is less than the preset state of charge threshold, splicing the driving range difference and / or the state of charge consumption value, and determining the endurance dataset or the unit mileage energy consumption dataset based on the splicing result.

[0028] According to the actual situation, the above solution performs slicing fusion on the consumed charge amount and / or the driving range, so that smaller driving range differences and / or smaller state of charge consumption values all have the opportunity to participate in the construction of the data set, further improving the accuracy of each data set.

[0029] In some embodiments, the historical operation data further includes historical environmental temperature parameters; the simultaneous solution of the historical mileage parameters, the nominal physical parameters, the endurance data set, and the unit mileage energy consumption data set to determine the sample data corresponding to the sample vehicle includes: configuring the corresponding historical environmental temperature parameters for each working condition point in the endurance data set, and configuring the corresponding historical environmental temperature parameters for each working condition point in the unit mileage energy consumption data set; and performing a simultaneous solution based on the historical mileage parameters, the nominal physical parameters, and the endurance data set and the unit mileage energy consumption data set after configuring the historical environmental temperature parameters to determine the sample data corresponding to the sample vehicle.

[0030] The above solution introduces historical environmental temperature parameters to construct the sample data set, making the endurance degradation model more matched to the actual operation environment and improving the accuracy of the endurance degradation model.

[0031] In some embodiments, the historical operation data further includes behavior working condition parameters; the simultaneous solution of the historical mileage parameters, the nominal physical parameters, the endurance data set, and the unit mileage energy consumption data set to determine the sample data corresponding to the sample vehicle includes: performing a simultaneous solution on the historical mileage parameters, the nominal physical parameters, the endurance data set, the unit mileage energy consumption data set, and the behavior working condition parameters to determine the sample data corresponding to the sample vehicle.

[0032] The above solution introduces behavior working condition parameters to construct the sample data set, making the sample data set more matched to the user's behavior habits and further improving the accuracy of the sample data set.

[0033] In some embodiments, the simultaneous solution of the historical mileage parameters, the nominal physical parameters, the endurance data set, and the unit mileage energy consumption data set to determine the sample data corresponding to the sample vehicle includes: merging the historical mileage parameters, the nominal physical parameters, the endurance data set, and the unit mileage energy consumption data set according to the historical mileage parameters and / or historical time points to obtain the sample data corresponding to the sample vehicle.

[0034] The above solution combines historical mileage parameters and / or historical time points to perform a simultaneous solution on the endurance data set and the unit mileage energy consumption data set, making the sample data set change with the mileage parameters or time points and improving the accuracy of the endurance degradation model.

[0035] The present application also provides an endurance mileage prediction device, including: a parameter acquisition module, configured to obtain the operating data and nominal physical parameters of a target vehicle; the operating data includes mileage parameters, energy consumption parameters, and state of charge parameters; a parameter calculation module, configured to determine the current endurance mileage and the current energy consumption per unit mileage according to the mileage parameters, the energy consumption parameters, and the state of charge parameters; an endurance prediction module, configured to predict the endurance mileage of any driving node of the target vehicle within a preset time period in the future according to the nominal physical parameters, the current endurance mileage, the current energy consumption per unit mileage, and the mileage parameters.

[0036] The present application also provides a vehicle, including a battery management system, a battery, a drive system, and a vehicle controller. The battery management system is disposed on the battery, and the battery management system and the drive system are respectively connected to the vehicle controller, and the vehicle controller is configured to execute the steps of the above-mentioned endurance mileage prediction method.

[0037] The present application also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned endurance mileage prediction method are implemented.

[0038] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned endurance mileage prediction method are implemented.

[0039] The present application also provides a computer program product, including a computer program. When the computer program is executed by a processor, the steps of the above-mentioned endurance mileage prediction method are implemented. Description of the Drawings

[0040] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present application. Moreover, in all the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0041] Figure 1 It is a schematic flowchart of the endurance mileage prediction method in some embodiments of the present application;

[0042] Figure 2 It is a schematic flowchart of the endurance mileage prediction method in some other embodiments of the present application;

[0043] Figure 3 It is a schematic flowchart of the endurance decay model training process in some embodiments of the present application;

[0044] Figure 4 It is a schematic flowchart of the sample data set establishment process in some embodiments of the present application;

[0045] Figure 5 Schematic diagram of the establishment process of the endurance data set in some embodiments of the present application;

[0046] Figure 6 Schematic diagram of the establishment process of the endurance data set in some other embodiments of the present application;

[0047] Figure 7 Schematic diagram of the establishment process of the endurance data set in some other embodiments of the present application;

[0048] Figure 8 Schematic diagram of the endurance data set in some embodiments of the present application;

[0049] Figure 9 Schematic diagram of the establishment process of the endurance data set in some other embodiments of the present application;

[0050] Figure 10 Schematic diagram of the establishment process of the energy consumption data set per unit mileage in some embodiments of the present application;

[0051] Figure 11 Schematic diagram of the establishment process of the sample data set in some other embodiments of the present application;

[0052] Figure 12 Schematic diagram of the training process of the endurance attenuation model in some other embodiments of the present application;

[0053] Figure 13 Schematic diagram of the training process of the endurance attenuation model in some other embodiments of the present application;

[0054] Figure 14 Schematic diagram of the structure of the endurance mileage prediction device in some embodiments of the present application;

[0055] Figure 15 Schematic diagram of the structure of the endurance mileage prediction device in some other embodiments of the present application;

[0056] Figure 16 Schematic diagram of the internal structure of the computer device in some embodiments of the present application. Detailed implementation manners

[0057] Next, embodiments of the technical solution of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to illustrate the technical solution of the present application more clearly, so they are only examples and cannot be used to limit the protection scope of the present application.

[0058] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs; the terms used herein are for the purpose of describing specific embodiments only and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the description of the specification, claims and above drawings of this application are intended to cover non-exclusive inclusion.

[0059] In the description of the embodiments of this application, technical terms such as "first" and "second" are only used to distinguish different objects and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity, specific order or primary-secondary relationship of the indicated technical features. In the description of the embodiments of this application, the meaning of "a plurality of" is more than two, unless otherwise specifically defined.

[0060] Referring to "embodiment" herein means that a specific feature, structure or characteristic described in connection with the embodiment may be included in at least one embodiment of this application. The phrase appearing in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0061] In the description of the embodiments of this application, the term "and / or" is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " herein generally represents an "or" relationship between the associated objects before and after.

[0062] In the description of the embodiments of this application, the term "a plurality of" means more than two (including two). Similarly, "a plurality of groups" means more than two groups (including two groups), and "a plurality of pieces" means more than two pieces (including two pieces).

[0063] In the description of the embodiments of this application, unless otherwise clearly specified and limited, technical terms such as "installation", "connection", "connection", "fixation" and the like should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or integrated; it may also be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and may be the communication inside two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of this application can be understood according to specific circumstances.

[0064] At present, from the perspective of the development of the market situation, battery-powered electric vehicles are becoming more and more widely used, and the cruising range has always been one of the main concerns of electric vehicles. However, different energy consumption, power, driving environment, and user driving behaviors will all affect the single available cruising range of the vehicle. Therefore, it is particularly important to predict the cruising range of the vehicle.

[0065] At present, the common cruising range standards include NEDC (New European Driving Cycle), CLTC (China Light-duty Vehicle Test Cycle), WLTC (World Light Vehicle Test Cycle), or the cruising range test standard formulated by the Environmental Protection Agency of the United States. However, the actual cruising range and the predicted results of these cruising range standards often differ greatly, and usually can only predict the cruising range of the vehicle in the current state, and fail to reflect the cruising range of the vehicle at future moments.

[0066] After in-depth research, it is found that most of the current cruising range prediction methods directly combine the collected vehicle operation data and vehicle models for cruising range prediction. They can often only predict the remaining cruising range of the vehicle in the current state, and it is easy to fail to truly reflect the current cruising range level of the vehicle due to reasons such as data fluctuations. At the same time, they do not have the ability to predict future cruising ranges.

[0067] To alleviate the above phenomena, it is possible to consider performing secondary calculations by combining the operation data of the vehicle to obtain parameters that can better represent the actual operation state of the vehicle. Using these parameters for cruising range prediction can not only improve the prediction accuracy of the cruising range but also achieve the prediction of the cruising range at any node within a certain future time period.

[0068] Based on the above considerations, this application provides a method for predicting the cruising range. During the operation of the target vehicle, the nominal physical parameters, mileage parameters, energy consumption parameters, and state of charge parameters of the target vehicle are obtained, and secondary analysis and calculation are performed by combining the mileage parameters, energy consumption parameters, and state of charge parameters to obtain the current cruising range and the current energy consumption per unit mileage of the target vehicle in the current state. Finally, by combining the nominal physical parameters, the current cruising range, the current energy consumption per unit mileage, and the mileage parameters, the cruising range of the target vehicle at any node within a preset future time period is predicted.

[0069] Through the above solution, it is possible to combine the current cruising range, the current energy consumption per unit mileage, the mileage parameters corresponding to the actual operation state of the target vehicle, and the nominal physical parameters inherent in the vehicle to achieve the prediction of the cruising range at future moments.

[0070] The driving range prediction method provided by this application is applied to electric transportation vehicles, which can be electric vehicles such as electric cars and electric motorcycles, and no specific limitation is made. More specifically, in one embodiment, the driving range prediction method is applied to a pure electric vehicle, that is, an electric car powered only by a battery, which can be a passenger car or a commercial vehicle, and no specific limitation is made.

[0071] Please refer to Figure 1 , this application provides a driving range prediction method, including step 102, step 104, and step 106.

[0072] Step 102, obtain the operation data and nominal physical parameters of the target vehicle.

[0073] Specifically, the operation data includes mileage parameters, energy consumption parameters, and state of charge parameters. The nominal physical parameters refer to the parameters calibrated when the vehicle leaves the factory, which are used to characterize the physical properties of the vehicle such as power, driving ability, and charging efficiency. The nominal physical parameters usually do not change with the use of the vehicle, and their types are not unique, and no specific limitation is made. For example, in one embodiment, the nominal physical parameters include at least one of nominal battery capacity, nominal driving range, and energy consumption per 100 kilometers.

[0074] The target vehicle is the vehicle that currently has a driving range prediction requirement; the operation data is the data related to the operation state generated during the actual operation of the target vehicle. The mileage parameters are the parameters related to the driving mileage of the target vehicle, and their types are not unique, and can include at least one of cumulative mileage, average daily driving mileage, average monthly driving mileage, and average annual driving mileage, and no specific limitation is made. The energy consumption parameters are the parameters related to the consumed power when the target vehicle is running, and their specific types are not unique, and can be cumulative operation energy consumption, single operation energy consumption, etc., and no specific limitation is made. The state of charge parameter is the state of charge parameter (SOC, State of Charge) of the battery of the target vehicle, and can also be understood as the remaining power of the battery.

[0075] During the operation of the target vehicle, the operation data can be collected in real time through devices such as an energy consumption data collector, a battery management system, an odometer, or a milometer, and the collected operation data is sent to the vehicle controller, and the vehicle controller performs relevant operations for driving range prediction. The operation of the target vehicle refers to the target vehicle being in a discharging state, including but not limited to the target vehicle being in a driving state, the target vehicle being powered on and parked (such as waiting for a traffic light), etc., and no specific limitation is made.

[0076] Step 104, determine the current driving range and current energy consumption per unit mileage according to the mileage parameters, energy consumption parameters, and state of charge parameters.

[0077] Specifically, the current cruising range refers to the mileage that the target vehicle actually cruises between the current charging condition and the previous charging condition. The current energy consumption per unit mileage refers to the energy consumption of the vehicle per unit mileage between the current charging condition and the previous charging condition.

[0078] It should be noted that the specific size of the unit mileage is not unique and can be selected according to actual needs. In one embodiment, 100 kilometers can be used as a unit mileage; in other embodiments, 10 kilometers, 1 kilometer, etc. can also be used as a unit mileage, and there is no specific limitation. For the sake of understanding, 100 kilometers can be used as a unit mileage in the following embodiments. Correspondingly, the current energy consumption per unit mileage refers to the energy consumption per 100 kilometers.

[0079] In the solution of this embodiment, each charging of the vehicle is used as a working condition point, and the cruising range is predicted based on each working condition point. After receiving the operation data, the vehicle controller will analyze and calculate based on this to obtain the current cruising range and the current energy consumption per unit mileage.

[0080] It can be understood that the calculation methods of the current cruising range and the current energy consumption per unit mileage are not unique. In one embodiment, the current cruising range can be calculated based on the mileage parameter and the state of charge parameter, and the current energy consumption per unit mileage can be calculated by combining the mileage parameter, the state of charge parameter, and the energy consumption parameter.

[0081] Furthermore, in one embodiment, for each working condition point (except the first working condition point), the current cruising range can be calculated by combining the running mileage difference between the current charging condition and the previous charging condition, and the state of charge consumption value between the current charging condition and the previous charging condition. More specifically, in one embodiment, the ratio of the running mileage difference to the state of charge consumption value can be used as the current cruising range.

[0082] For example, the working condition points include adjacent working condition point 1, working condition point 2, and working condition point 3, and their corresponding cumulative mileages are a, b, and c respectively. The state of charge parameters at the start of charging are m0, n0, and p0 respectively, and the state of charge parameters at the end of charging are m1, n1, and p1 respectively. Then, the running mileage difference of working condition point 2 is b - a, the state of charge consumption value corresponding to working condition point 2 is m1 - n0, and the cruising range of working condition point 2 can be expressed as (b - a) / (m1 - n0); the running mileage difference of working condition point 3 is c - b, the state of charge consumption value corresponding to working condition point 3 is n1 - p0; the cruising range of working condition point 3 can be expressed as (c - b) / (n1 - p0).

[0083] In one embodiment, for each operating condition point, the current energy consumption per unit mileage can be calculated by combining the driving mileage difference between the current charging condition and the previous charging condition, the state of charge consumption value between the current charging condition and the previous charging condition, and the energy consumption parameter corresponding to the current charging condition. The calculation methods of the driving mileage difference and the state of charge consumption value for each operating condition point are the same as those in the current driving range and will not be elaborated here.

[0084] More specifically, in one embodiment, the current driving range can be first calculated by combining the driving mileage difference and the state of charge consumption value, and then the current energy consumption per unit mileage can be calculated based on the current driving range and the energy consumption parameter. Taking the energy consumption per 100 kilometers as an example, it can be obtained by dividing the energy consumption parameter by the current driving range and then multiplying by 100.

[0085] Step 106: Predict the driving range of the target vehicle at any driving node within a preset future time period according to the nominal physical parameters, the current driving range, the current energy consumption per unit mileage, and the mileage parameters.

[0086] Specifically, the driving node also changes with the driving of the target vehicle and is a parameter used to characterize the cumulative driving state of the target vehicle. The cumulative driving states of the target vehicle are different at different driving nodes. And the cumulative driving state is not unique and can be the cumulative driving time or the cumulative mileage. Correspondingly, the driving node can include a time node or a mileage node. After calculating the current driving range and the current energy consumption per unit mileage, the vehicle control unit will combine the collected nominal physical parameters and mileage parameters, as well as the secondarily calculated current driving range and current energy consumption per unit mileage for prediction, and finally obtain the driving range at any node within the preset future time period, that is, the remaining available driving range of the target vehicle at any node.

[0087] It can be understood that the size of the preset time period is not unique and can be one year, one quarter, one month, etc., without specific limitation, and it can be specifically set according to the actual scenario.

[0088] The above-mentioned driving range prediction method obtains the nominal physical parameters of the target vehicle, as well as the mileage parameters, energy consumption parameters, and state of charge parameters during the operation of the target vehicle, and performs secondary analysis and calculation in combination with the mileage parameters, energy consumption parameters, and state of charge parameters to obtain the current driving range and current energy consumption per unit mileage of the target vehicle in the current state. Finally, in combination with the nominal physical parameters, current driving range, current energy consumption per unit mileage, and mileage parameters, the driving range of the target vehicle at any node within a preset future time period is predicted. Through this solution, the driving range prediction at future moments can be realized by combining the current driving range, current energy consumption per unit mileage, mileage parameters corresponding to the actual operating state of the target vehicle, and the nominal physical parameters inherent to the target vehicle itself.

[0089] Please refer to Figure 2 , in some embodiments, step 106 includes step 202 and step 204.

[0090] Step 202, obtain the vehicle type information of the target vehicle.

[0091] Step 204, input the vehicle type information, nominal physical parameters, current driving range, current energy consumption per unit mileage, and mileage parameters into a preset driving range attenuation model for prediction to obtain the driving range of the target vehicle at any driving node within a preset future time period.

[0092] Specifically, the vehicle type information is also the information related to the type of the target vehicle, which may include the model of the target vehicle; in other embodiments, the vehicle type information may also include information such as the capacity of the target vehicle's battery, the manufacturer, and the battery type, without specific limitation. The driving range attenuation model is a prediction model used to predict the driving range of the target vehicle at any time node based on the nominal physical parameters, current driving range, current energy consumption per unit mileage, and mileage parameters of the target vehicle, and it can be trained through the historical operation data of the target vehicle within a historical time period, without specific limitation. It can be understood that for each type of vehicle, it can be trained separately according to its historical operation data, etc., and the training result is stored in the driving range attenuation model, that is, the driving range attenuation model can realize the driving range prediction of multiple different vehicle types.

[0093] In the solution of this embodiment, the vehicle control unit pre-stores a driving range attenuation model. For each type of vehicle, it can combine the vehicle type information, as well as the nominal physical parameters, current driving range, current energy consumption per unit mileage, and mileage parameters, and perform prediction analysis in the driving range attenuation model to obtain the driving range at any node within the subsequent preset time period.

[0094] It should be noted that, in one embodiment, the future preset time period can be determined according to the time span of the historical operation data used when training the endurance attenuation model. For example, in one embodiment, the historical operation data is historical operation data within one year, and the future preset time period can be configured as the next year.

[0095] The above solution, combined with a pre-trained range attenuation model for range prediction, has a high prediction efficiency.

[0096] In some embodiments, predicting the range of a target vehicle at any driving node within a preset time period in the future includes: determining the range of the target vehicle at a future time node or a future mileage node in combination with the future time nodes or future mileage nodes to be predicted.

[0097] Specifically, in actual operation scenarios, the accumulated mileage of a vehicle will increase with time. Therefore, the mileage can be predicted based on the mileage node, or based on the time node, without specific limitation. The future time node is the time point within the future preset time period; the future mileage node is the accumulated mileage that reaches the time within the future preset time period.

[0098] The above scheme can predict the cruising range from two dimensions: mileage and time, and has a high prediction convenience.

[0099] See also Figure 3 In some embodiments, the method for determining the endurance attenuation model includes: step 302 , step 304 , step 306 , step 308 and step 310 .

[0100] Step 302, obtaining nominal physical parameters of the sample vehicle and historical operating data under various charging conditions within a preset historical period.

[0101] Step 304 , analyzing and processing the historical mileage parameters, the historical energy consumption parameters, and the historical state of charge parameters to determine a cruising range data set and a unit mileage energy consumption data set.

[0102] Step 306 , the historical mileage parameters, the nominal physical parameters, the endurance data set, and the unit mileage energy consumption data set are combined to determine the sample data corresponding to the sample vehicle.

[0103] Step 308 , obtaining a sample data set based on the sample data of the plurality of sample vehicles.

[0104] Step 310, perform model training in combination with the sample data set and the preset training model to determine the endurance attenuation model.

[0105] Specifically, the historical operation data includes historical mileage parameters, historical energy consumption parameters, and historical state of charge parameters, and the vehicle type of the sample vehicle is the same as that of the target vehicle. The historical mileage parameters are a series of parameters related to the mileage of the sample vehicle within a historical time period, which may include cumulative mileage at different working condition points or different times, or may include daily average mileage, monthly average mileage, or annual average mileage, etc., without specific limitation. The historical energy consumption parameters are parameters related to the energy consumption of the sample vehicle at different working condition points or different time points within a historical time period. The state of charge parameters are the battery state of charge parameters of the sample vehicle at different working condition points or different time points within a historical time period. The endurance data set is a set of endurance data corresponding to each charging condition of the sample vehicle within a preset historical period. The unit mileage energy consumption data set refers to the electric energy consumed by the sample vehicle when running a unit mileage (such as 100 kilometers) under each charging condition of the sample vehicle within a preset historical period.

[0106] The time span within the preset historical period is not unique and can be two years, one year, one quarter, etc., without specific limitation. For the convenience of understanding the technical solution of this application, it can be understood that the preset historical period is the most recent year in the following embodiments.

[0107] The training of the endurance decay model can be carried out on the vehicle control unit of the sample vehicle. At this time, the vehicle control unit of the sample vehicle can cluster the historical operation data and nominal physical parameters of other sample vehicles of the same type, so as to realize the training of the endurance decay model corresponding to this type of vehicle. In another embodiment, the training of the endurance decay model can also be carried out through a host computer or a background server. At this time, the historical operation data and nominal physical parameters of sample vehicles of the same type are clustered through the host computer or the background server, so as to realize the training of the endurance decay model corresponding to this type of vehicle.

[0108] For the convenience of understanding the technical solution of this application, it can be understood in the following embodiments that the training of the endurance decay model is carried out through the background server, and after the training is completed, the endurance decay model is sent to the target vehicle for application.

[0109] Similar to predicting the driving range by combining the operating data of the target vehicle described above and the nominal physical parameters, after obtaining the historical operating data, secondary calculations will be performed by combining the historical mileage parameters, historical energy consumption parameters, and historical state of charge parameters in the historical operating data to obtain the historical driving range parameters and historical energy consumption per unit mileage parameters corresponding to different operating conditions within a preset historical period. The set of historical driving range parameters for all operating conditions is used as the driving range data set, and the set of historical energy consumption per unit mileage parameters for all operating conditions is used as the energy consumption per unit mileage data set. Then, the nominal physical parameters, the historical mileage parameters of each operating condition, and the combined driving range data set and energy consumption per unit mileage data set obtained from the secondary calculation are merged to obtain the sample data set. Finally, part of the data in the sample data set is used as the training set and part as the test set, and model training is performed by combining a preset training model to obtain the driving range attenuation model.

[0110] It should be noted that during the actual training process, the historical driving range parameters corresponding to the driving range data set in the sample data set are used as labels to represent the actual output or expected output driving range of the training samples. For different data groups (i.e., data corresponding to different operating conditions or time points), the historical mileage parameters, nominal physical parameters, and data corresponding to the energy consumption per unit mileage data set are input into the preset training model for model training, and supervised learning is performed by combining the historical driving range parameters corresponding to the driving range data set in this data group, and each parameter in the preset training model is continuously corrected until the training is finally completed.

[0111] It can be understood that the type of the preset training model is not unique, and any model of the type that predicts one dependent variable with multiple independent variables can be used, without specific limitation. For example, a regression model, a neural network model, etc. can be used. For the convenience of understanding the technical solution of this application, the following embodiments will be explained by taking a multiple regression model as an example.

[0112] In the above solution, for vehicles of the same type, the driving range data set and the energy consumption per unit mileage data set obtained by secondary calculation by combining the historical operating data are used to complete the construction of the driving range attenuation model, improving the accuracy of the driving range attenuation model.

[0113] Please refer to Figure 4 , in some embodiments, step 304 includes step 402 and step 404.

[0114] Step 402, calculate according to the historical mileage parameters and the historical state of charge parameters to determine the driving range data set.

[0115] Step 404, calculate according to the historical mileage parameters, the historical state of charge parameters, and the historical energy consumption parameters to determine the energy consumption per unit mileage data set.

[0116] Specifically, in this embodiment, the endurance dataset and the energy consumption dataset per unit mileage are calculated separately. The endurance dataset can be analyzed and calculated in combination with the historical mileage parameters and the historical state of charge parameters. Specifically, by combining the cumulative mileage parameters corresponding to each historical charging condition in the historical mileage parameters and their corresponding state of charge parameters for analysis, the endurance data for each historical charging condition are calculated separately. Finally, these endurance data are stored according to time points, cumulative mileage nodes, or working condition points to obtain the endurance dataset. The energy consumption dataset per unit mileage is analyzed and calculated in combination with the historical mileage parameters, the historical state of charge parameters, and the historical energy consumption parameters. Specifically, by combining the cumulative mileage parameters corresponding to each historical charging condition in the historical mileage parameters and their corresponding state of charge parameters and energy consumption parameters for analysis, the energy consumption data per unit mileage for each historical charging condition are calculated separately. Finally, these energy consumption data per unit mileage are stored according to time points, cumulative mileage nodes, or working condition points to obtain the energy consumption dataset per unit mileage.

[0117] In the above solution, the endurance dataset and the energy consumption dataset per unit mileage are established through different historical operation data respectively, which improves the accuracy of the endurance dataset and the energy consumption dataset per unit mileage.

[0118] Please refer to Figure 5 , in some embodiments, step 402 includes step 502, step 504, and step 506.

[0119] Step 502, according to the historical mileage parameters, calculate the running mileage difference between each charging condition and the previous charging condition.

[0120] Step 504, according to the historical state of charge parameters, calculate the state of charge consumption value between each charging condition and the previous charging condition.

[0121] Step 506, analyze and calculate based on the running mileage difference and the state of charge consumption value to determine the endurance dataset.

[0122] Specifically, the running mileage difference is also the difference in the cumulative running mileage of the sample vehicle between the previous charge and the current charge, and its essence represents the actual running mileage of the sample vehicle. The state of charge consumption value is also the actual consumption of the state of charge of the sample vehicle from the completion of the previous charge to the current charge. In the process of establishing the actual dataset, it is possible to analyze and calculate the running mileage difference of the sample vehicle between any two adjacent charging conditions by combining the collected historical operation data, that is, by subtracting the cumulative mileage of the previous charging condition (which can be the start or end of charging, and the mileage does not change during charging) from the cumulative mileage of the current working condition point to obtain the running mileage difference.

[0123] By taking the difference between the historical state of charge parameter at the start of the current charging condition and the historical state of charge parameter at the end of the previous charging, the state of charge consumption value between the two charging conditions can be obtained. When this state of charge consumption value can be equivalent to the battery power consumed when the sample vehicle's driving mileage difference occurs, then, by analyzing in combination with the driving mileage difference and the state of charge consumption value, the historical cruising range corresponding to the current charging condition can be obtained. Using a similar method, each operating condition point is analyzed and calculated respectively. Finally, the set of historical cruising ranges of each operating condition point is used as the cruising data set.

[0124] It can be understood that the method for determining the cruising data set based on the driving mileage difference and the state of charge consumption value is not unique. In one embodiment, the ratio of the two can be used as the historical cruising range, that is: , represents the historical cruising range, represents the driving mileage difference, represents the state of charge consumption value. Correspondingly, if the historical cruising ranges corresponding to each charging condition within a preset historical period are placed in the same data set, then there is:

[0125]

[0126] where the subscripts 1, 2, 3... n respectively represent the numbers of each charging condition.

[0127] In the above solution, each charging is used as an operating condition point respectively. By combining the driving mileage changes and the battery state of charge changes at each operating condition point, a highly reliable cruising data set is established.

[0128] In some embodiments, the method further includes: determining the time difference between each charging condition and the previous charging condition; performing data jump and loss determination on each charging condition according to the time difference and the state of charge consumption value; and when the data jump and loss determination passes, performing the step of analyzing and calculating according to the driving mileage difference and the state of charge consumption value to determine the cruising data set.

[0129] Specifically, the time difference is the time interval between the previous charging and the current charging. In the process of constructing the sample data set by combining the historical mileage parameters, in order to improve the accuracy and authenticity of the sample data, it is necessary to perform data jump and loss determination, filter out the data with loss or jump, and retain the data without jump and loss.

[0130] Specifically, if the time difference between two adjacent charging conditions is too large, it indicates that there may be data jumps and losses in the sample vehicle, that is, there may be charging conditions between these two chargings, but these data have not been recorded. If the power state consumption value between two adjacent charging conditions is abnormal, for example, the state of charge parameter at the start of the current charging condition is greater than the state of charge parameter at the end of the previous charging, it is also considered that there are data jumps and losses in the sample vehicle at this time.

[0131] The determination of data jump and loss passing means that the time difference between two adjacent charging conditions is within the set time range, and the state of charge consumption value between two adjacent charging conditions is within the normal difference range. If the time difference is not within the set time range and / or the state of charge consumption value is not within the normal difference range, it is considered that the determination of data jump and loss fails. At this time, the data corresponding to the current condition will be discarded, and the data under other conditions will be used to establish the sample data set.

[0132] The above solution combines the time difference and the state of charge consumption value to perform data jump and loss determination and correction processing on each working condition point, that is, perform noise reduction processing on the data obtained at each working condition point to improve the data accuracy of each working condition point.

[0133] Please refer to Figure 6 , in some embodiments, step 506 includes step 602 and step 604.

[0134] Step 602, analyze and calculate according to the running mileage difference and the state of charge consumption value to determine the original endurance data set.

[0135] Step 604, correct the original endurance data set to obtain the endurance data set.

[0136] Specifically, when establishing the endurance data set, first establish the original endurance data set, and then correct the original endurance data set to obtain a high-precision endurance data set.

[0137] It should be noted that in other embodiments, to increase the sample size, the original endurance data set can also be directly used as the endurance data set to participate in the subsequent establishment of the sample data set, and the specific method is not limited.

[0138] The above solution, after determining the original endurance data set by combining the running mileage difference and the state of charge consumption value, will correct the original endurance data set, and use the corrected original endurance data set as the endurance data set to further improve the accuracy of the endurance data set.

[0139] Please refer to Figure 7 , in some embodiments, step 604 includes step 702.

[0140] Step 702: Correct the original endurance dataset according to the nominal physical parameters to obtain the endurance dataset.

[0141] Specifically, when the endurance data is reasonable, the parameters it represents should be within the allowable range of the nominal physical parameters. If it exceeds the allowable range of the nominal physical parameters, the data is considered incorrect. Therefore, in the solution of this embodiment, the nominal physical parameters can be used to correct the original endurance dataset, eliminating some unreasonable data and improving the accuracy of the endurance dataset.

[0142] It can be understood that the type of the nominal dataset is not unique. In one embodiment, it can be the nominal endurance or the nominal energy consumption. The data at each working condition point in the original endurance dataset can be compared and corrected with the nominal endurance or the nominal energy consumption. For the sake of easy understanding, taking the nominal endurance as an example, the endurance data in the original endurance dataset can be respectively compared and analyzed with the nominal endurance in the nominal physical parameters, and the endurance data that is significantly greater than the nominal endurance can be eliminated to obtain an accurate endurance dataset.

[0143] For example, in one embodiment, after converting the original endurance dataset into a one-dimensional n-row array, as Figure 8 shown, the abscissa represents the cumulative mileage, and the ordinate represents the endurance mileage, with the unit being kilometers or kilometers, and the specific unit is not limited. For a certain vehicle model, its nominal endurance is 600 kilometers. There is some data in the figure whose endurance mileage is significantly greater than 600 kilometers, not meeting the requirements of the nominal endurance. At this time, this part of the data in the original endurance dataset can be eliminated.

[0144] The above solution, combined with the nominal physical parameters of the sample vehicle, eliminates the data in the original endurance dataset that does not meet the nominal physical parameters, and has high correction reliability.

[0145] Please refer to Figure 9 , in some embodiments, step 604 includes step 902.

[0146] Step 902: Filter, converge, and correct the original endurance dataset to obtain the endurance dataset.

[0147] Specifically, in the solution of this embodiment, the original endurance dataset is directly filtered, converged, and corrected by a filtering algorithm, and the discrete data is converged and corrected into highly convergent data.

[0148] It should be noted that when performing the filtering, convergence, and correction, the filtering method used is not unique. In one embodiment, the IQR (Interquartile Range) filtering method can be used for correction. In other embodiments, other methods can also be used for filtering and correction, such as the median filtering method, etc., and the specific method is not limited.

[0149] The above solution corrects the original endurance dataset in a filtering and convergence manner, with high correction efficiency.

[0150] Please refer to Figure 10 , in some embodiments, step 404 includes step 1002, step 1004, and step 1006.

[0151] Step 1002, according to the historical mileage parameter, calculate the running mileage difference between each charging condition and the previous charging condition.

[0152] Step 1004, according to the historical state of charge parameter, calculate the state of charge consumption value between each charging condition and the previous charging condition.

[0153] Step 1006, based on the historical energy consumption parameter corresponding to each charging condition, as well as the running mileage difference and the state of charge consumption value, calculate and determine the unit mileage energy consumption dataset.

[0154] Specifically, similar to the establishment of the endurance dataset in the above embodiments, in this embodiment, each charging condition is also used as a node, and the unit mileage energy consumption corresponding to each charging condition is calculated respectively. Then, the set of each unit mileage energy consumption is used as the unit mileage energy consumption dataset.

[0155] To facilitate understanding of the technical solution of the present application, in the following embodiments, the unit mileage energy consumption dataset is taken as an example of the energy consumption per 100 kilometers dataset for explanation. For each charging condition point, the endurance mileage can be calculated in a similar manner as above, by combining the running mileage difference and the state of charge consumption value. Then, by dividing the energy consumption parameter by the current endurance mileage and multiplying by 100, the energy consumption per 100 kilometers is obtained. Finally, the set of the energy consumption per 100 kilometers for each charging condition is used as the energy consumption per 100 kilometers dataset.

[0156] The above solution combines the running mileage changes, battery state of charge changes at each working condition point, and the historical energy consumption parameters at each working condition point to establish the unit mileage energy consumption dataset, improving the accuracy of the unit mileage energy consumption dataset.

[0157] In some embodiments, the method further includes: when the running mileage difference is greater than or equal to the preset mileage threshold and the state of charge consumption value is greater than or equal to the preset state of charge threshold, determining the endurance dataset or the unit mileage energy consumption dataset based on the running mileage difference and the state of charge consumption value; when the running mileage difference is less than the preset mileage threshold and / or the state of charge consumption value is less than the preset state of charge threshold, splicing the running mileage difference and / or the state of charge consumption value, and determining the endurance dataset or the unit mileage energy consumption dataset based on the splicing result.

[0158] Specifically, the scheme of this embodiment uses the state of charge consumption value greater than or equal to the preset charge threshold as the long SOC, and the state of charge consumption value less than the preset charge threshold as the short SOC; the running mileage difference greater than or equal to the preset mileage threshold is used as the long mileage, and the running mileage difference less than the preset mileage threshold is used as the short mileage. For long mileage and long SOC, they can directly participate in the calculation of the endurance data set or the unit mileage energy consumption data set; and for short mileage and / or short SOC, they can be spliced ​​and then participate in the calculation of the endurance data set or the unit mileage energy consumption data set.

[0159] Among them, splicing means taking the sum of multiple short mileages as a running mileage difference, and the sum of the SOCs corresponding to multiple short mileages (which can be long SOCs or short SOCs) as a state of charge consumption value, and calculating a range data. Or taking the sum of multiple short SOCs as a state of charge consumption value, and the sum of the mileages corresponding to multiple short SOCs (which can be short mileages or long mileages) as a running mileage difference, and calculating a range data.

[0160] The above scheme slices and fuses the consumed charge and / or mileage according to the actual situation, so that smaller mileage differences and / or smaller state of charge consumption values ​​have the opportunity to participate in the data set construction, further improving the accuracy of each data set.

[0161] See also Figure 11 In some embodiments, the historical operating data also includes historical ambient temperature parameters; step 306 includes step 112 and step 114 .

[0162] Step 112, respectively configure the corresponding historical ambient temperature parameters for each operating point in the endurance data set, and respectively configure the corresponding historical ambient temperature parameters for each operating point in the unit mileage energy consumption data set.

[0163] Step 114 , based on the historical mileage parameters, the nominal physical parameters, and the endurance data set and the unit mileage energy consumption data set after configuring the historical ambient temperature parameters, the sample data corresponding to the sample vehicle are determined.

[0164] Specifically, the historical ambient temperature parameter refers to the ambient temperature corresponding to each charging condition within a preset historical period. In actual scenarios, changes in ambient temperature will also have a certain impact on the operating conditions of the sample vehicles. Therefore, the solution of this embodiment, for each operating point, comprehensively considers the impact of the user's ambient temperature on the battery life, introduces the ambient condition as a scene label, and determines the sample data and sample data set. In this way, in the subsequent training process, the attenuation coefficient can be corrected in combination with the ambient temperature to reflect the proportion of the attenuation coefficient affected by the ambient temperature in different seasons or different regions, and dynamically adjusts the attenuation coefficient of the preset training model according to the actual season or usage area.

[0165] The above solution introduces historical ambient temperature parameters to construct a sample data set, so that the endurance attenuation model better matches the actual operating environment and improves the accuracy of the endurance attenuation model.

[0166] See also Figure 12 In some embodiments, the historical operating data further includes behavioral operating condition parameters, and step 306 includes step 122 .

[0167] Step 122 , historical mileage parameters, nominal physical parameters, endurance data set, unit mileage energy consumption data set, and behavior condition parameters are combined to determine sample data corresponding to the sample vehicle.

[0168] Specifically, the behavioral operating condition parameters are parameters that characterize different operating conditions of the sample vehicles caused by user behavior. It can be understood that the types of behavioral operating condition parameters are not unique. In one embodiment, the behavioral operating condition parameters may include the power-on and power-off intervals of the sample vehicles. In other embodiments, the behavioral operating condition parameters may also include the ambient temperature when the sample vehicles are in use (different users prefer to use the vehicles in different environments), the energy consumption of the sample vehicles (different users use other energy-consuming products in the car differently, which will result in different energy consumption, for example, some users like to turn on the air conditioner, car player, etc.), without specific limitation.

[0169] Therefore, the solution of this embodiment introduces some behavioral condition parameters caused by user behavior habits, combines historical mileage parameters, nominal physical parameters, endurance data set, and unit mileage energy consumption data set to obtain a sample data set for model training.

[0170] The above scheme introduces behavioral condition parameters to construct a sample data set, so that the sample data set better matches the user's behavioral habits, further improving the accuracy of the sample data set.

[0171] See also Figure 13 , in some embodiments, step 306 includes step 132 .

[0172] Step 132 , based on the historical mileage parameters and / or historical time points, the historical mileage parameters, the nominal physical parameters, the endurance data set, and the unit mileage energy consumption data set are combined to determine the sample data corresponding to the sample vehicle.

[0173] Specifically, within a preset historical period, the mileage of the sample vehicle will increase with the increase in usage time. In order to facilitate the distinction between different groups of data and to facilitate subsequent mileage prediction from the mileage dimension and / or time dimension, mileage labels or time labels can be assigned to different groups of data to obtain sample data and sample data sets containing time labels and / or mileage labels.

[0174] It is understandable that whether to assign mileage labels or time labels can be selected according to actual needs. If predictions need to be made from the mileage dimension in the future, mileage labels can be assigned to the sample data in the sample data set, that is, the historical mileage parameters, nominal physical parameters, endurance data sets and unit mileage energy consumption data sets under the same historical mileage parameters can be combined as a set of sample data.

[0175] If you need to make predictions from the time dimension later, you can give time labels to the sample data in the sample data set, that is, combine the historical mileage parameters, nominal physical parameters, endurance data set, and unit mileage energy consumption data set at the same historical time as a set of sample data. If you need to make predictions in both mileage and time dimensions, you can give both time and mileage labels to the same set of sample data.

[0176] The above scheme combines historical mileage parameters and / or historical time points to jointly integrate the endurance data set and the unit mileage energy consumption data set, so that the sample data set changes with the mileage parameters or time points, thereby improving the accuracy of the endurance attenuation model.

[0177] In order to facilitate understanding of the technical solution of the present application, the present application is explained below in conjunction with detailed embodiments.

[0178] Model training phase:

[0179] The vehicle controller or backend server can be used to cluster the historical mileage parameters (including cumulative mileage, average daily mileage and average annual mileage), historical energy consumption parameters and historical state of charge parameters of sample vehicles of the same type (including vehicle model, battery manufacturer, battery capacity, etc.) in the past year, as well as the nominal physical parameters of the sample vehicles of this type (including nominal power, nominal cruising range, and energy consumption per 100 kilometers).

[0180] Then, for each charging condition point, the running mileage difference between the previous charging condition is calculated according to the historical mileage parameters, and the state of charge consumption value between the previous charging condition is calculated according to the historical state of charge parameters. Combined with the time difference and the state of charge consumption value between two adjacent charging conditions, data jump and loss judgment is performed. After the data jump and loss judgment is passed, for each operating point, the ratio of the running mileage difference and the state of charge consumption value can be used to calculate the historical cruising range, and the set of historical cruising ranges of each operating point is used as the original cruising range data set. Then, the physical nominal parameters are introduced to correct the original data set, and the original cruising range data set is converged and corrected by combining IQR filtering to finally obtain the cruising range data set.

[0181] Similarly, for each operating point, the energy consumption per 100 kilometers is calculated by combining the mileage difference, charge state consumption value and energy consumption parameters, and the collection of energy consumption per 100 kilometers at each operating point is used as the energy consumption data set per 100 kilometers.

[0182] After that, according to the time point or cumulative mileage parameters, the historical mileage parameters, nominal physical parameters, endurance data set and unit mileage energy consumption data set are combined to obtain a set of data at each time point or cumulative mileage parameter. For each set of sample data, the behavioral operating parameters are introduced, namely the ambient temperature, power-on and power-off intervals, energy consumption parameters, etc., and finally the collection of each set of data is used as the sample data. The sample data is substituted into the multivariate regression prediction model and divided into training sets and test sets for model training, and finally the endurance attenuation model corresponding to the sample vehicle is obtained.

[0183] Finally, a similar method to the above is used to cluster the historical mileage parameters, historical energy consumption parameters, historical state of charge parameters and nominal physical parameters of different vehicle models for training and analysis, and a range attenuation model covering a variety of different vehicle models is obtained.

[0184] Model application phase:

[0185] The target vehicle analyzes and calculates the current cruising range and current energy consumption per 100 kilometers (i.e., current energy consumption per unit mileage) based on mileage parameters, energy consumption parameters, state of charge parameters, and nominal physical parameters. Then, the vehicle model, nominal physical parameters (including nominal cruising range, energy consumption per 100 kilometers, and nominal power), mileage parameters (including cumulative mileage, daily average mileage, and annual average mileage), current cruising range, current energy consumption per unit mileage, and behavioral operating parameters (including ambient temperature, power-on and power-off intervals, etc.) are substituted into the trained cruising range attenuation model for prediction, and the cruising range of the target vehicle at any node in the next year can be obtained. Specifically, the corresponding cruising range can be output based on the future time node or future mileage node that needs to be predicted.

[0186] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of the steps or stages in other steps or other steps.

[0187] Based on the same inventive concept, an embodiment of the present application also provides a driving range prediction device for implementing the driving range prediction method described above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the driving range prediction device provided below can refer to the limitations on the driving range prediction method in the above text, and will not be repeated here.

[0188] Please refer to Figure 14 , the present application also provides a driving range prediction device, including a parameter acquisition module 142, a parameter calculation module 144, and a driving range prediction module 146.

[0189] The parameter acquisition module 142 is used to obtain the running data and nominal physical parameters of the target vehicle; the parameter calculation module 144 is used to determine the current driving range and the current energy consumption per unit mileage according to the mileage parameter, energy consumption parameter, and state of charge parameter; the driving range prediction module 146 is used to predict the driving range of the target vehicle at any driving node within a preset future time period according to the nominal physical parameters, the current driving range, the current energy consumption per unit mileage, and the mileage parameter.

[0190] In some embodiments, the driving range prediction module 146 is further used to obtain the vehicle type information of the target vehicle; input the vehicle type information, nominal physical parameters, current driving range, current energy consumption per unit mileage, and mileage parameter into a preset driving range attenuation model for prediction, so as to obtain the driving range of the target vehicle at any driving node within a preset future time period.

[0191] In some embodiments, the driving range prediction module 146 is further used to combine the future time node or future mileage node to be predicted to determine the driving range of the target vehicle at the future time node or the driving range at the future mileage node.

[0192] Please refer to Figure 15In some embodiments, the cruising range prediction device also includes a model training module 152 .

[0193] The model training module 152 is used to obtain the nominal physical parameters of the sample vehicle, as well as the historical operating data under each charging condition within a preset historical period; to analyze and process the historical mileage parameters, historical energy consumption parameters and historical state of charge parameters to determine the endurance data set and the unit mileage energy consumption data set; to combine the historical mileage parameters, the nominal physical parameters, the endurance data set and the unit mileage energy consumption data set to determine the sample data corresponding to the sample vehicle; to obtain a sample data set based on the sample data of multiple sample vehicles; to perform model training in combination with the sample data set and the preset training model to determine the endurance attenuation model.

[0194] In some embodiments, the model training module 152 is also used to calculate based on historical mileage parameters and historical state of charge parameters to determine the endurance data set; calculate based on historical mileage parameters, historical state of charge parameters and historical energy consumption parameters to determine the unit mileage energy consumption data set.

[0195] In some embodiments, the model training module 152 is also used to calculate the mileage difference between each charging condition and the previous charging condition based on historical mileage parameters; calculate the state of charge consumption value between each charging condition and the previous charging condition based on historical state of charge parameters; and perform analysis and calculation based on the mileage difference and the state of charge consumption value to determine the endurance data set.

[0196] In some embodiments, the model training module 152 is also used to determine the time difference between each charging condition and the previous charging condition; based on the time difference and the state of charge consumption value, data jump and loss judgment is performed on each charging condition; when the data jump and loss judgment is passed, analysis and calculation are performed based on the running mileage difference and the state of charge consumption value to determine the operation of the endurance data set.

[0197] In some embodiments, the model training module 152 is further used to perform analysis and calculation based on the running mileage difference and the state of charge consumption value to determine an original endurance data set; and to correct the original endurance data set to obtain an endurance data set.

[0198] In some embodiments, the model training module 152 is further used to modify the original endurance data set according to the nominal physical parameters to obtain the endurance data set.

[0199] In some embodiments, the model training module 152 is further used to perform filtering and convergence correction on the original endurance data set to obtain the endurance data set.

[0200] In some embodiments, the model training module 152 is also used to calculate the running mileage difference between each charging condition and the previous charging condition based on historical mileage parameters; calculate the charge state consumption value between each charging condition and the previous charging condition based on historical charge state parameters; and determine the unit mileage energy consumption data set based on the historical energy consumption parameters corresponding to each charging condition, as well as the running mileage difference and the charge state consumption value.

[0201] In some embodiments, the model training module 152 is also used to configure corresponding historical ambient temperature parameters for each operating point in the endurance data set, and to configure corresponding historical ambient temperature parameters for each operating point in the unit mileage energy consumption data set; based on the historical mileage parameters, nominal physical parameters, and the endurance data set and the unit mileage energy consumption data set after the historical ambient temperature parameters are configured, the sample data corresponding to the sample vehicle is determined.

[0202] In some embodiments, the model training module 152 is also used to combine historical mileage parameters, nominal physical parameters, endurance data sets, unit mileage energy consumption data sets, and behavioral operating condition parameters to determine sample data corresponding to the sample vehicle.

[0203] In some embodiments, the range prediction module 146 is also used to combine historical mileage parameters, nominal physical parameters, range data sets and unit mileage energy consumption data sets according to historical mileage parameters and / or historical time points to determine sample data corresponding to the sample vehicle.

[0204] Each module in the above-mentioned cruising range prediction device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0205] The above-mentioned cruising range prediction device obtains the nominal physical parameters of the target vehicle, as well as the mileage parameters, energy consumption parameters, and state of charge parameters during the operation of the target vehicle, and performs secondary analysis and calculation in combination with the mileage parameters, energy consumption parameters, and state of charge parameters to obtain the current cruising range and current unit mileage energy consumption of the target vehicle in the current state. Finally, the nominal physical parameters, current cruising range, current unit mileage energy consumption, and mileage parameters are combined to predict the cruising range of the target vehicle at any driving node in the future preset time period. Through this solution, the current cruising range, current unit mileage energy consumption, mileage parameters corresponding to the actual operating state of the target vehicle, and the nominal physical parameters inherent to the target vehicle itself can be combined to achieve the prediction of the cruising range at a future moment.

[0206] The present application also provides a vehicle, including a battery management system, a battery, a drive system, and a vehicle controller. The battery management system is disposed on the battery. The battery management system and the drive system are respectively connected to the vehicle controller, and the vehicle controller is configured to execute the steps of the above-mentioned driving range prediction method.

[0207] Specifically, the driving range prediction method is as shown in the above-mentioned various embodiments and the accompanying drawings, and will not be elaborated here. During the operation of the target vehicle, the nominal physical parameters of the target vehicle, as well as the mileage parameter, the energy consumption parameter, and the state of charge parameter, are obtained, and a secondary analysis and calculation are performed in combination with the mileage parameter, the energy consumption parameter, and the state of charge parameter to obtain the current driving range and the current energy consumption per unit mileage of the target vehicle in the current state. Finally, in combination with the nominal physical parameters, the current driving range, the current energy consumption per unit mileage, and the mileage parameter, the driving range of the target vehicle at any driving node within a preset time period in the future is predicted. Through this solution, the current driving range, the current energy consumption per unit mileage, the mileage parameter corresponding to the actual operating state of the target vehicle, and the nominal physical parameters inherent to the target vehicle itself can be combined to achieve the prediction of the driving range at a future moment.

[0208] In some embodiments, the present application provides a computer device, which may be a server, and its internal structure diagram may be as Figure 16 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store vehicle operation data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a driving range prediction method.

[0209] Those skilled in the art can understand that Figure 16 the structure shown in

[0210] The present application also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the following driving range prediction method are implemented: obtaining the operation data and nominal physical parameters of a target vehicle; determining the current driving range and the current energy consumption per unit mileage according to the mileage parameter, the energy consumption parameter, and the state of charge parameter; predicting the driving range of the target vehicle at any driving node within a preset future time period according to the nominal physical parameters, the current driving range, the current energy consumption per unit mileage, and the mileage parameter.

[0211] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the following driving range prediction method are implemented: obtaining the operation data and nominal physical parameters of a target vehicle; determining the current driving range and the current energy consumption per unit mileage according to the mileage parameter, the energy consumption parameter, and the state of charge parameter; predicting the driving range of the target vehicle at any driving node within a preset future time period according to the nominal physical parameters, the current driving range, the current energy consumption per unit mileage, and the mileage parameter.

[0212] The present application also provides a computer program product, including a computer program. When the computer program is executed by a processor, the steps of the following driving range prediction method are implemented: obtaining the operation data and nominal physical parameters of a target vehicle; determining the current driving range and the current energy consumption per unit mileage according to the mileage parameter, the energy consumption parameter, and the state of charge parameter; predicting the driving range of the target vehicle at any driving node within a preset future time period according to the nominal physical parameters, the current driving range, the current energy consumption per unit mileage, and the mileage parameter.

[0213] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. 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 methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. 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), magnetoresistive 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. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., and are not limited thereto.

[0214] During the operation of the target vehicle, the above computer device, storage medium, and computer program product acquire the nominal physical parameters of the target vehicle, as well as mileage parameters, energy consumption parameters, and state of charge parameters, and perform secondary analysis and calculation in combination with the mileage parameters, energy consumption parameters, and state of charge parameters to obtain the current cruising range and current energy consumption per unit mileage of the target vehicle in the current state. Finally, in combination with the nominal physical parameters, current cruising range, current energy consumption per unit mileage, and mileage parameters, the cruising range of the target vehicle at any driving node within a preset future time period is predicted. Through this solution, the prediction of the cruising range at a future moment can be realized by combining the current cruising range, current energy consumption per unit mileage, mileage parameters corresponding to the actual operating state of the target vehicle, and the nominal physical parameters inherent to the target vehicle itself.

[0215] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present application, and they should all be covered within the scope of the claims and the description of the present application. In particular, as long as there is no structural conflict, the technical features mentioned in each embodiment can be combined in any way. The present application is not limited to the specific embodiments disclosed in the text, but includes all technical solutions that fall within the scope of the claims.

Claims

1. A method for predicting a cruising range, characterized in that: include: When the target vehicle is running, obtaining vehicle model information, operating data, and nominal physical parameters of the target vehicle; The operating data includes mileage parameters, energy consumption parameters and state of charge parameters; Determine the current cruising range and the current energy consumption per unit mileage according to the mileage parameter, the energy consumption parameter and the state of charge parameter; The vehicle model information, the nominal physical parameters, the current cruising range, the current energy consumption per unit mileage and the mileage parameters are input into a preset cruising range attenuation model for prediction, so as to obtain the cruising range of any driving node of the target vehicle within a preset time period in the future; The range attenuation model is obtained by model training based on historical mileage parameters, nominal physical parameters, a range data set and a unit mileage energy consumption data set under each charging condition. The range data set is obtained based on the mileage difference between each charging condition and the previous charging condition and the state of charge consumption value.

2. The method for predicting the cruising range according to claim 1, characterized in that: The predicting of the cruising range of the target vehicle at any driving node within a preset time period in the future includes: In combination with the future time node or future mileage node to be predicted, the cruising range of the target vehicle at the future time node or the cruising range at the future mileage node is determined.

3. The method for predicting the cruising range according to claim 1, characterized in that: The method for determining the endurance attenuation model includes: Obtaining nominal physical parameters of the sample vehicle and historical operating data under various charging conditions within a preset historical period; the historical operating data includes historical mileage parameters, historical energy consumption parameters, and historical state of charge parameters, and the vehicle type of the sample vehicle is the same as the vehicle type of the target vehicle; Analyze and process the historical mileage parameter, the historical energy consumption parameter, and the historical state of charge parameter to determine a cruising range data set and a unit mileage energy consumption data set; The historical mileage parameter, the nominal physical parameter, the endurance data set and the unit mileage energy consumption data set are combined to determine sample data corresponding to the sample vehicle; Obtaining a sample data set according to the sample data of the plurality of sample vehicles; Model training is performed in combination with the sample data set and a preset training model to determine a range attenuation model.

4. The method for predicting the cruising range according to claim 3, characterized in that: The analyzing and processing according to the historical mileage parameter, the historical energy consumption parameter and the historical state of charge parameter to determine the endurance data set and the unit mileage energy consumption data set includes: Calculate according to the historical mileage parameter and the historical state of charge parameter to determine the endurance data set; A unit mileage energy consumption data set is determined by performing calculations based on the historical mileage parameter, the historical state of charge parameter, and the historical energy consumption parameter.

5. The method for predicting the cruising range according to claim 4, characterized in that: The calculating according to the historical mileage parameter and the historical state of charge parameter to determine the endurance data set includes: Calculate the running mileage difference between each charging condition and the last charging condition according to the historical mileage parameter; Calculating the state of charge consumption value between each charging condition and the previous charging condition according to the historical state of charge parameters; An analysis and calculation is performed based on the running mileage difference and the state of charge consumption value to determine a cruising range data set.

6. The method for predicting the cruising range according to claim 5, characterized in that: The method further comprises: Determine the time difference between each charging condition and the previous charging condition; According to the time difference and the state of charge consumption value, data jump and loss determination is performed for each charging condition; In the case where the data jump and loss determination is passed, the step of analyzing and calculating according to the running mileage difference and the state of charge consumption value to determine the endurance data set is executed.

7. The method for predicting the cruising range according to claim 5, characterized in that: The analyzing and calculating according to the running mileage difference and the state of charge consumption value to determine the endurance data set includes: Analyze and calculate the running mileage difference and the state of charge consumption value to determine an original endurance data set; The original endurance data set is corrected to obtain an endurance data set.

8. The method for predicting the cruising range according to claim 7, characterized in that: The correcting the original endurance data set to obtain the endurance data set includes: The original endurance data set is corrected according to the nominal physical parameters to obtain an endurance data set.

9. The method for predicting the cruising range according to claim 7, characterized in that: The correcting the original endurance data set to obtain the endurance data set includes: The original endurance data set is filtered and converged to obtain an endurance data set.

10. The method for predicting the cruising range according to claim 4, characterized in that: The calculating according to the historical mileage parameter, the historical state of charge parameter and the historical energy consumption parameter to determine the unit mileage energy consumption data set includes: Calculate the running mileage difference between each charging condition and the last charging condition according to the historical mileage parameter; Calculating the state of charge consumption value between each charging condition and the previous charging condition according to the historical state of charge parameters; The unit mileage energy consumption data set is determined by analyzing and calculating the historical energy consumption parameters corresponding to each charging condition, the running mileage difference, and the state of charge consumption value.

11. The method for predicting the cruising range according to claim 5 or 10, characterized in that: The method further comprises: When the running mileage difference is greater than or equal to the preset mileage threshold, and the state of charge consumption value is greater than or equal to the preset charge threshold, determining the endurance data set or the unit mileage energy consumption data set by using the running mileage difference and the state of charge consumption value; When the running mileage difference is less than the preset mileage threshold, and / or the state of charge consumption value is less than the preset charge threshold, the running mileage difference and / or the state of charge consumption value are spliced ​​to determine the endurance data set or the unit mileage energy consumption data set based on the splicing result.

12. The method for predicting the range of a vehicle according to any one of claims 3 to 10, characterized in that: The historical operation data also includes historical ambient temperature parameters; the historical mileage parameters, the nominal physical parameters, the endurance data set, and the unit mileage energy consumption data set are combined to determine the sample data corresponding to the sample vehicle, including: respectively configuring the corresponding historical ambient temperature parameters for each operating point in the endurance data set, and respectively configuring the corresponding historical ambient temperature parameters for each operating point in the unit mileage energy consumption data set; The sample data corresponding to the sample vehicle is determined by combining the historical mileage parameters, the nominal physical parameters, and the endurance data set and the unit mileage energy consumption data set after configuring the historical ambient temperature parameters.

13. The method for predicting the range of a vehicle according to any one of claims 3 to 10, characterized in that: The historical operation data also includes behavior condition parameters, and the historical mileage parameters, the nominal physical parameters, the endurance data set, and the unit mileage energy consumption data set are combined to determine the sample data corresponding to the sample vehicle, including: The historical mileage parameters, the nominal physical parameters, the endurance data set, the unit mileage energy consumption data set, and the behavior condition parameters are combined to determine sample data corresponding to the sample vehicle.

14. The method for predicting the range of a vehicle according to any one of claims 3 to 10, characterized in that: The combining of the historical mileage parameter, the nominal physical parameter, the endurance data set, and the unit mileage energy consumption data set to determine the sample data corresponding to the sample vehicle includes: According to the historical mileage parameters and / or historical time points, the historical mileage parameters, the nominal physical parameters, the endurance data set and the unit mileage energy consumption data set are combined to obtain sample data corresponding to the sample vehicle.

15. A cruising range prediction device, characterized in that: include: A parameter acquisition module, used to obtain the model information, operation data and nominal physical parameters of the target vehicle when the target vehicle is running; The operating data includes mileage parameters, energy consumption parameters and state of charge parameters; A parameter calculation module, used to determine the current cruising range and the current energy consumption per unit mileage according to the mileage parameter, the energy consumption parameter and the state of charge parameter; A cruising range prediction module is used to input the vehicle model information, the nominal physical parameters, the current cruising range, the current unit mileage energy consumption and the mileage parameters into a preset cruising range attenuation model for prediction, so as to obtain the cruising range of any driving node of the target vehicle within a preset time period in the future; The range attenuation model is obtained by model training based on historical mileage parameters, nominal physical parameters, a range data set and a unit mileage energy consumption data set under each charging condition. The range data set is obtained based on the mileage difference between each charging condition and the previous charging condition and the state of charge consumption value.

16. A vehicle, characterized in that: It includes a battery management system, a battery, a drive system and a vehicle controller, wherein the battery management system is arranged on the battery, the battery management system and the drive system are respectively connected to the vehicle controller, and the vehicle controller is used to execute the steps of the cruising range prediction method according to any one of claims 1 to 14.

17. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the cruising range prediction method described in any one of claims 1 to 14 are implemented.

18. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the cruising range prediction method described in any one of claims 1 to 14 are implemented.

19. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the range prediction method described in any one of claims 1 to 14 are implemented.

Images