New energy endurance mileage prediction method

By collecting various real scenario data on new energy vehicles and building neural network models for range prediction, the problem of inaccurate range prediction in the existing technology is solved, and the accuracy of prediction and user trust is improved.

CN118928048APending Publication Date: 2024-11-12CHANGCHUN AUTOMOTIVE TEST CENT +1
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411043035.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-31
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The existing range prediction methods for new energy vehicles cannot accurately reflect the mileage in real driving scenarios, resulting in a decrease in user trust and an increase in anxiety.

Method used

By laying sensors on new energy vehicles to collect environmental data, driving conditions and battery conditions, building a neural network model for range prediction, considering the influence of factors in a variety of real scenarios, including road type, tire wear, bump vibration and wind resistance, wait.

Benefits of technology

It improves the accuracy of range prediction of new energy vehicles, can more accurately reflect the range changes in real scenarios, and enhances users' trust in range.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118928048A_ABST
    Figure CN118928048A_ABST
Patent Text Reader

Abstract

The invention provides a new energy endurance mileage prediction method, and relates to the technical field of automobile endurance prediction.The new energy endurance mileage prediction method comprises the steps that environmental data of a surrounding environment during endurance mileage testing in a real scene are collected through sensor equipment arranged on a target new energy automobile, the environmental data are analyzed, and an analysis result is obtained; the method comprises the following steps: acquiring a target new energy automobile, acquiring a driving condition and a battery condition of the target new energy automobile, counting total mileage information when the target new energy automobile runs out of energy, and constructing a training data set according to an analysis result, the driving condition, the battery condition and the total mileage information which are obtained when endurance mileage tests are performed in various real scenes for many times; the neural network model is pre-trained through the training data set to obtain the endurance mileage prediction model, the endurance mileage prediction model constructed by the method considers the endurance mileage change when the new energy vehicle is influenced by various factors in a real scene, and the endurance mileage of the new energy vehicle can be predicted more accurately.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of automobile cruising range prediction, and in particular to a new energy cruising range prediction method. Background Art

[0002] In recent years, with the gradual increase in the market share of new energy vehicles, the driving range of electric vehicles has become the main energy consumption indicator that consumers are concerned about. At present, the nominal driving range of products sold by various new energy vehicle companies mostly adopts GB / T18386.1-2021 "Test Method for Energy Consumption and Driving Range of Electric Vehicles Part 1: Light Vehicles", which is the normal temperature test result under CLTC (China Light Vehicle Test Cycle) conditions. It lacks driving range under harsh conditions such as low temperature, high speed, and real driving, and cannot reflect the comprehensive energy consumption level of electric vehicles. This will further lead to inaccurate prediction results when predicting the cruising range of new energy vehicles, which will cause users to distrust the displayed cruising range of new energy vehicles and make users anxious about the cruising range. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide a new energy range prediction method, by testing the actual range of new energy vehicles under various conditions in real scenarios, constructing a range prediction model, and improving the accuracy of range prediction.

[0004] In order to achieve the above-mentioned object of the invention, the present invention provides a new energy cruising range prediction method, the method comprising:

[0005] S101. When the target new energy vehicle starts a cruising range test in a real scenario, collect environmental data of the surrounding environment of the target new energy vehicle during the cruising range test through a sensor device arranged on the target new energy vehicle;

[0006] S102, analyzing all environmental data collected during the cruising range test to obtain analysis results, wherein the analysis results include changes in ambient temperature and road surface;

[0007] S103, obtaining the driving condition and battery condition of the target new energy vehicle during the cruising range test, wherein the driving condition includes a driving speed curve, a load condition, and an air conditioning operation condition, and the battery condition includes a battery capacity and a battery health status;

[0008] S104. When the target new energy vehicle runs out of energy, the total mileage information of the target new energy vehicle in this cruising range test is counted;

[0009] S105, constructing a training data set by using the analysis results, driving conditions, battery conditions, and total mileage information obtained when performing mileage tests in multiple real scenarios, and pre-training a neural network model by using the training data set to obtain a mileage prediction model;

[0010] S106: Use the cruising range prediction model to predict the cruising range of new energy vehicles.

[0011] Furthermore, the environmental data includes multiple road surface locations, and all environmental data collected during the cruising range test are analyzed to obtain road surface changes, including:

[0012] S201, for each road surface position, determining the corresponding road surface type, and calculating the friction force generated by the corresponding road surface type on the target new energy vehicle;

[0013] S202. Obtaining road surface changes based on the road surface types and friction forces corresponding to all road surface positions that the target new energy vehicle passes through when energy is exhausted during the cruising range test.

[0014] Furthermore, the method further comprises:

[0015] S301, for each road surface position, determining the tire wear degree and tire pressure of the target new energy vehicle at the road surface position;

[0016] S302, for each road surface position, determining the contact area between the tire and the road surface of the target new energy vehicle at the road surface position;

[0017] S303. Analyze the contact area between the tire and the road surface of the target new energy vehicle at each road surface position to obtain the change in contact area between the tire and the road surface during the cruising range test. Input the change in contact area between the tire and the road surface, the road surface change, and the friction force into a pre-trained tire energy consumption analysis model for analysis to obtain the change in tire energy consumption corresponding to all road surface positions that the target new energy vehicle passes through when the energy is exhausted during the cruising range test, and update the energy consumption change to the driving condition.

[0018] Furthermore, the method further comprises:

[0019] S401, collecting bump vibration data of the target new energy vehicle at each road surface position through a sensor device arranged on the target new energy vehicle, and determining suspension system information adopted by the target new energy vehicle;

[0020] S402. Analyze the bump and vibration data of the target new energy vehicle at each road position to obtain the bump and vibration changes of the target new energy vehicle during the cruising range test, input the bump and vibration changes and suspension system information into a pre-trained vibration energy consumption analysis model for analysis, obtain the vibration energy consumption changes corresponding to all road positions that the target new energy vehicle passes through when the energy is exhausted during the cruising range test, and update the vibration energy consumption changes to the driving condition.

[0021] Furthermore, the method further comprises:

[0022] S501, collecting wind direction and wind speed data of the target new energy vehicle at each road position through a sensor device arranged on the target new energy vehicle, and determining a drag coefficient of the target new energy vehicle;

[0023] S502. Analyze the wind direction and wind speed data of the target new energy vehicle at each road position to obtain the change of wind direction and wind speed during the cruising range test, input the change of wind direction and wind speed and the wind resistance coefficient of the target new energy vehicle into the pre-trained wind resistance energy consumption analysis model for analysis, obtain the change of wind resistance energy consumption corresponding to all road positions that the target new energy vehicle passes through when the energy is exhausted during the cruising range test, and update the change of wind resistance energy consumption to the driving condition.

[0024] Furthermore, the cruising range prediction model is used to predict the cruising range of new energy vehicles, including:

[0025] S601, inputting the real-time analysis results, driving conditions, and battery conditions of the target new energy vehicle into a cruising range prediction model to obtain a cruising range prediction result of the target new energy vehicle;

[0026] S602, determining whether the predicted cruising range of the target new energy vehicle is less than a preset standard cruising range under the same driving scenario;

[0027] S603. If the predicted range of the target new energy vehicle is less than the preset standard range under the same driving scenario, the range difference between the predicted range and the preset standard range is calculated, and based on the range difference, driving condition, battery condition, and analysis result, the first vehicle setting recommended for adjustment to enable the target new energy vehicle to reach the preset standard range under the same driving scenario is analyzed, wherein the first vehicle setting includes at least one of driving speed, tire type, battery type, body drag coefficient, and body load.

[0028] Furthermore, the method further comprises:

[0029] S701, when the predicted cruising range of the target new energy vehicle is not less than the preset standard cruising range under the same driving scenario, obtaining vehicle information of the target new energy vehicle, the vehicle information including wind resistance coefficient, tire type, battery type, and vehicle body load;

[0030] S702, searching for other new energy vehicles whose vehicle information matches the vehicle information of the target new energy vehicle among all other new energy vehicles that have been tested for cruising range, and further obtaining test results of the other new energy vehicles found;

[0031] S703. Further search for other new energy vehicles with abnormal mileage in the test conditions according to the obtained test conditions of other new energy vehicles;

[0032] S704. For other new energy vehicles with abnormal cruising range found, determine whether the abnormal cruising range is caused by vehicle settings. If so, obtain the specific abnormal cause of the cruising range, and generate a second vehicle setting that the target new energy vehicle is recommended to avoid based on the obtained specific abnormal cause. The second vehicle setting includes at least one of the driving speed, tire type, battery type, body drag coefficient, and body load.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] The present invention provides a new energy cruising range prediction method, which collects environmental data of the surrounding environment of the target new energy vehicle when the cruising range test is performed in a real scene through a sensor device arranged on the target new energy vehicle, analyzes the environmental data to obtain an analysis result, and obtains the driving condition and battery condition of the target new energy vehicle during this cruising range test. When the energy of the target new energy vehicle is exhausted, the total mileage information is counted, and a training data set is constructed through the analysis results, driving conditions, battery conditions and total mileage information obtained when the cruising range test is performed in multiple real scenes for multiple times. A neural network model is pre-trained through the training data set to obtain a cruising range prediction model that can be applied to the cruising range prediction of the new energy vehicle. The cruising range prediction model constructed by the present invention takes into account the cruising range changes of the new energy vehicle when it is affected by multiple factors in the real scene, and can more accurately predict the cruising range of the new energy vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only preferred embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0036] Figure 1 It is a schematic diagram of the overall process of a new energy range prediction method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The principles and features of the present invention are described below in conjunction with the accompanying drawings. The enumerated embodiments are only used to explain the present invention and are not used to limit the scope of the present invention.

[0038] Reference Figure 1 This embodiment provides a new energy range prediction method, the method comprising:

[0039] S101. When a target new energy vehicle starts a range test in a real scenario, environmental data of the surrounding environment of the target new energy vehicle during the range test is collected through sensor equipment arranged on the target new energy vehicle.

[0040] In this embodiment, the target new energy vehicle is a new energy vehicle for which a new energy cruising range prediction is required. The target new energy vehicle is equipped with a variety of different types of sensor devices, such as temperature sensors, vibration sensors, etc., which are not specifically limited in this embodiment.

[0041] S102, analyzing all environmental data collected during the cruising range test to obtain analysis results, wherein the analysis results include changes in environmental temperature and road surface.

[0042] In this embodiment, the environmental data includes multiple road locations in the area between the starting position of the target new energy vehicle at the start of the cruising range test and the stop position when the energy is exhausted. All environmental data collected during the cruising range test are analyzed to obtain road surface changes, including:

[0043] S201. For each road surface position, determine the corresponding road surface type, and calculate the friction force generated by the corresponding road surface type on the target new energy vehicle.

[0044] Different road types generate different friction when the vehicle is driving, and have different effects on the endurance of new energy vehicles. In this embodiment, the road type may include paved road, unpaved road, or more specifically asphalt road, gravel road, muddy road, etc., which are not specifically limited in this embodiment.

[0045] S202. Obtaining road surface changes based on the road surface types and friction forces corresponding to all road surface positions that the target new energy vehicle passes through when energy is exhausted during the cruising range test.

[0046] It can be seen that this embodiment also analyzes the road surface type and friction at multiple road surface positions in the driving area to obtain road surface changes such as road surface type and friction corresponding to all road surface positions passed by the target new energy vehicle when the energy is exhausted during the cruising range test, thereby improving the accuracy of the environmental data analysis results.

[0047] S103, obtaining the driving condition and battery condition of the target new energy vehicle during the endurance test, wherein the driving condition includes a driving speed curve, a load condition, and an air conditioning operation condition, and the battery condition includes a battery capacity and a battery health status.

[0048] In this embodiment, the driving speed curve is used to characterize the corresponding driving speed of the new energy vehicle at different time nodes during the cruising range test. The load conditions include the fixed load of the new energy vehicle, such as battery weight, body weight, etc., and the non-fixed load, such as passengers. The air conditioning operation condition is used to characterize the operation of the refrigeration, air conditioning and heating equipment in the target new energy vehicle during the cruising range test, such as the operating temperature, operating time, etc.

[0049] S104. When the target new energy vehicle runs out of energy, the total mileage information of the target new energy vehicle in this endurance test is counted.

[0050] S105. Construct a training data set by obtaining the analysis results, driving conditions, battery conditions and total mileage information obtained by performing range tests in multiple different real scenarios, such as real driving, low temperature, high-speed driving, etc., and pre-train the neural network model through the training data set to obtain a range prediction model.

[0051] S106: Use the cruising range prediction model to predict the cruising range of new energy vehicles.

[0052] The cruising range prediction model constructed in this embodiment takes into account the changes in the cruising range of new energy vehicles when they are affected by various factors in real scenarios, and can predict the cruising range of new energy vehicles more accurately.

[0053] As an optional embodiment, the method may further include the following steps:

[0054] S301. For each road surface position, determine the tire wear degree and tire pressure of the target new energy vehicle at the road surface position.

[0055] S302: For each tire wear degree and tire pressure at each road surface position, determine the contact area between the tire and the road surface when the target new energy vehicle is at the road surface position.

[0056] S303. Analyze the contact area between the tire and the road surface of the target new energy vehicle at each road surface position to obtain the change in contact area between the tire and the road surface during the cruising range test. Input the change in contact area between the tire and the road surface, the road surface change, and the friction force into a pre-trained tire energy consumption analysis model for analysis to obtain the change in tire energy consumption corresponding to all road surface positions that the target new energy vehicle passes through when the energy is exhausted during the cruising range test, and update the energy consumption change to the driving condition.

[0057] In this optional embodiment, the tire energy consumption analysis model is obtained by pre-training a neural network model based on sample data such as sample contact area change, sample road surface change, sample friction and sample energy consumption change data.

[0058] Tires are one of the key components that connect vehicles to the road, and the state of tires directly affects the vehicle's driving performance and energy consumption. When tires are worn, the tire pattern gradually disappears, which causes the contact area between the tire and the road to change. Generally speaking, tire wear causes the tread to become flatter, and the area in contact with the ground actually increases. The increase in contact area will lead to increased rolling resistance, thereby increasing the energy consumption of new energy vehicles when driving. This optional embodiment analyzes the energy consumption changes caused by tires when the target new energy vehicle passes through different road positions by combining data such as the change in tire contact area, road surface changes, and friction force of the target new energy vehicle at different road positions, thereby improving the accuracy of the analysis of the driving conditions of the target new energy vehicle, thereby improving the training effect of the subsequent model.

[0059] As another optional embodiment, the method may further include the following steps:

[0060] S401. Collect the bump and vibration data of the target new energy vehicle at each road surface position through the sensor equipment arranged on the target new energy vehicle, and determine the suspension system information adopted by the target new energy vehicle.

[0061] S402. Analyze the bump and vibration data of the target new energy vehicle at each road position to obtain the bump and vibration changes of the target new energy vehicle during the cruising range test, input the bump and vibration changes and suspension system information into a pre-trained vibration energy consumption analysis model for analysis, obtain the vibration energy consumption changes corresponding to all road positions that the target new energy vehicle passes through when the energy is exhausted during the cruising range test, and update the vibration energy consumption changes to the driving condition.

[0062] In this optional embodiment, the vibration energy consumption analysis model is obtained by pre-training a neural network model based on sample data such as sample bump vibration changes, sample suspension system information, and sample vibration energy consumption changes.

[0063] When a new energy vehicle is driving on the road, the bumps and vibrations caused by different road conditions will increase the energy consumption of the vehicle during driving, which is more obvious on vehicles that lack a good shock absorption system. This optional embodiment analyzes the energy consumption changes caused by bumps and vibrations of the target new energy vehicle when passing through different road positions by combining the bump and vibration data of the target new energy vehicle at different road positions, suspension system information and other data, thereby improving the accuracy of the analysis of the driving conditions of the target new energy vehicle, and further improving the training effect of the subsequent model.

[0064] As another optional embodiment, the method may further include the following steps:

[0065] S501. Collect wind direction and wind speed data of the target new energy vehicle at each road position through sensor equipment arranged on the target new energy vehicle, and determine the drag coefficient of the target new energy vehicle.

[0066] S502. Analyze the wind direction and wind speed data of the target new energy vehicle at each road position to obtain the change of wind direction and wind speed during the cruising range test, input the change of wind direction and wind speed and the wind resistance coefficient of the target new energy vehicle into the pre-trained wind resistance energy consumption analysis model for analysis, obtain the change of wind resistance energy consumption corresponding to all road positions that the target new energy vehicle passes through when the energy is exhausted during the cruising range test, and update the change of wind resistance energy consumption to the driving condition.

[0067] In this optional embodiment, the wind resistance energy consumption analysis model is obtained by pre-training a neural network model based on sample data such as sample wind direction and wind speed changes, sample drag coefficients, and sample wind resistance energy consumption changes.

[0068] This optional embodiment analyzes the changes in energy consumption of the target new energy vehicle due to wind resistance when it passes through different road locations by combining data such as the wind direction and wind speed changes and the drag coefficient of the target new energy vehicle at different road locations, thereby improving the accuracy of the analysis of the driving conditions of the target new energy vehicle, and further improving the training effect of the subsequent model.

[0069] As another optional embodiment, the cruising range prediction model is used to predict the cruising range of new energy vehicles, including:

[0070] S601. Input the real-time analysis results, driving conditions, and battery conditions of the target new energy vehicle into a cruising range prediction model to obtain a cruising range prediction result of the target new energy vehicle.

[0071] S602: Determine whether the predicted cruising range of the target new energy vehicle is less than a preset standard cruising range under the same driving scenario.

[0072] S603. If the predicted range of the target new energy vehicle is less than the preset standard range under the same driving scenario, the range difference between the predicted range and the preset standard range is calculated, and based on the range difference, driving condition, battery condition, and analysis result, the first vehicle setting recommended for adjustment to enable the target new energy vehicle to reach the preset standard range under the same driving scenario is analyzed, wherein the first vehicle setting includes at least one of driving speed, tire type, battery type, body drag coefficient, and body load.

[0073] In this optional embodiment, the range difference, driving condition, battery condition, and analysis result are input into a pre-trained setting analysis model for analysis, and the first vehicle setting that is recommended to be adjusted so that the target new energy vehicle can reach the preset standard range under the same driving scenario is obtained. The setting analysis model is pre-trained based on sample data such as sample range difference, sample driving condition, sample battery condition, sample analysis result, and sample vehicle setting.

[0074] After predicting the range of the target new energy vehicle, this optional embodiment calculates the range difference between the predicted range result and the preset standard range if it is determined that the range of the target new energy vehicle is less than the preset standard range under the same driving scenario, and analyzes the first vehicle setting that is recommended to be adjusted so that the target new energy vehicle can reach the preset standard range under the same driving scenario based on the range difference, driving conditions, battery conditions, and analysis results, so as to adjust the vehicle setting of the target new energy vehicle and improve the actual range of the target new energy vehicle.

[0075] As another optional embodiment, the method may further include:

[0076] S701, when the predicted cruising range of the target new energy vehicle is not less than the preset standard cruising range under the same driving scenario, obtaining vehicle information of the target new energy vehicle, the vehicle information including wind resistance coefficient, tire type, battery type, and vehicle body load;

[0077] S702, searching for other new energy vehicles whose vehicle information matches the vehicle information of the target new energy vehicle among all other new energy vehicles that have been tested for cruising range, and further obtaining test results of the other new energy vehicles found;

[0078] S703. Further search for other new energy vehicles with abnormal mileage in the test conditions according to the obtained test conditions of other new energy vehicles;

[0079] S704. For other new energy vehicles with abnormal cruising range found, determine whether the abnormal cruising range is caused by vehicle settings. If so, obtain the specific abnormal cause of the cruising range, and generate a second vehicle setting that the target new energy vehicle is recommended to avoid based on the obtained specific abnormal cause. The second vehicle setting includes at least one of the driving speed, tire type, battery type, body drag coefficient, and body load.

[0080] When the estimated cruising range of the target new energy vehicle is normal, this optional embodiment further generates a second vehicle setting that is recommended to be avoided based on the cause of the abnormal cruising range of other new energy vehicles whose vehicle information matches the target new energy vehicle among other new energy vehicles that have undergone cruising range tests, so as to avoid the target new energy vehicle from being adjusted in a direction that is not conducive to increasing the cruising range in subsequent adjustments, so as to ensure the accuracy of the estimated cruising range of the target new energy vehicle.

[0081] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A new energy mileage prediction method, characterized in that: The method comprises: S101. When the target new energy vehicle starts a cruising range test in a real scenario, collect environmental data of the surrounding environment of the target new energy vehicle during the cruising range test through a sensor device arranged on the target new energy vehicle; S102, analyzing all environmental data collected during the cruising range test to obtain analysis results, wherein the analysis results include changes in ambient temperature and road surface; S103, obtaining the driving condition and battery condition of the target new energy vehicle during the cruising range test, wherein the driving condition includes a driving speed curve, a load condition, and an air conditioning operation condition, and the battery condition includes a battery capacity and a battery health status; S104. When the target new energy vehicle runs out of energy, the total mileage information of the target new energy vehicle in this cruising range test is counted; S105, constructing a training data set by using the analysis results, driving conditions, battery conditions, and total mileage information obtained when performing mileage tests in multiple real scenarios, and pre-training a neural network model by using the training data set to obtain a mileage prediction model; S106: Use the cruising range prediction model to predict the cruising range of new energy vehicles.

2. A new energy range prediction method according to claim 1, characterized in that: The environmental data includes multiple road locations. All environmental data collected during the cruising range test are analyzed to obtain road surface changes, including: S201, for each road surface position, determining the corresponding road surface type, and calculating the friction force generated by the corresponding road surface type on the target new energy vehicle; S202. Obtaining road surface changes based on the road surface types and friction forces corresponding to all road surface positions that the target new energy vehicle passes through when energy is exhausted during the cruising range test.

3. A new energy mileage prediction method according to claim 2, characterized in that: The method further comprises: S301, for each road surface position, determining the tire wear degree and tire pressure of the target new energy vehicle at the road surface position; S302, for each road surface position, determining the contact area between the tire and the road surface of the target new energy vehicle at the road surface position; S303. Analyze the contact area between the tire and the road surface of the target new energy vehicle at each road surface position to obtain the change in contact area between the tire and the road surface during the cruising range test. Input the change in contact area between the tire and the road surface, the road surface change, and the friction force into a pre-trained tire energy consumption analysis model for analysis to obtain the change in tire energy consumption corresponding to all road surface positions that the target new energy vehicle passes through when the energy is exhausted during the cruising range test, and update the energy consumption change to the driving condition.

4. A new energy mileage prediction method according to claim 2, characterized in that: The method further comprises: S401, collecting bump vibration data of the target new energy vehicle at each road surface position through a sensor device arranged on the target new energy vehicle, and determining suspension system information adopted by the target new energy vehicle; S402. Analyze the bump and vibration data of the target new energy vehicle at each road position to obtain the bump and vibration changes of the target new energy vehicle during the cruising range test, input the bump and vibration changes and suspension system information into a pre-trained vibration energy consumption analysis model for analysis, obtain the vibration energy consumption changes corresponding to all road positions that the target new energy vehicle passes through when the energy is exhausted during the cruising range test, and update the vibration energy consumption changes to the driving condition.

5. The method for predicting the range of new energy vehicles according to claim 2, characterized in that: The method further comprises: S501, collecting wind direction and wind speed data of the target new energy vehicle at each road position through a sensor device arranged on the target new energy vehicle, and determining a drag coefficient of the target new energy vehicle; S502. Analyze the wind direction and wind speed data of the target new energy vehicle at each road position to obtain the change of wind direction and wind speed during the cruising range test, input the change of wind direction and wind speed and the wind resistance coefficient of the target new energy vehicle into the pre-trained wind resistance energy consumption analysis model for analysis, obtain the change of wind resistance energy consumption corresponding to all road positions that the target new energy vehicle passes through when the energy is exhausted during the cruising range test, and update the change of wind resistance energy consumption to the driving condition.

6. A new energy range prediction method according to any one of claims 1 to 5, characterized in that: The range prediction model is used to predict the range of new energy vehicles, including: S601, inputting the real-time analysis results, driving conditions, and battery conditions of the target new energy vehicle into a cruising range prediction model to obtain a cruising range prediction result of the target new energy vehicle; S602, determining whether the predicted cruising range of the target new energy vehicle is less than a preset standard cruising range under the same driving scenario; S603. If the predicted range of the target new energy vehicle is less than the preset standard range under the same driving scenario, the range difference between the predicted range and the preset standard range is calculated, and based on the range difference, driving condition, battery condition, and analysis result, the first vehicle setting recommended for adjustment to enable the target new energy vehicle to reach the preset standard range under the same driving scenario is analyzed, wherein the first vehicle setting includes at least one of driving speed, tire type, battery type, body drag coefficient, and body load.

7. A new energy mileage prediction method according to claim 6, characterized in that: The method further comprises: S701, when the predicted cruising range of the target new energy vehicle is not less than the preset standard cruising range under the same driving scenario, obtaining vehicle information of the target new energy vehicle, the vehicle information including wind resistance coefficient, tire type, battery type, and vehicle body load; S702, searching for other new energy vehicles whose vehicle information matches the vehicle information of the target new energy vehicle among all other new energy vehicles that have been tested for cruising range, and further obtaining test results of the other new energy vehicles found; S703. Further search for other new energy vehicles with abnormal mileage in the test conditions according to the obtained test conditions of other new energy vehicles; S704. For other new energy vehicles with abnormal cruising range found, determine whether the abnormal cruising range is caused by vehicle settings. If so, obtain the specific abnormal cause of the cruising range, and generate a second vehicle setting that the target new energy vehicle is recommended to avoid based on the obtained specific abnormal cause. The second vehicle setting includes at least one of the driving speed, tire type, battery type, body drag coefficient, and body load.

Citation Information

Cited By

  • Method and equipment for testing endurance mileage of multi-rotor unmanned aerial vehicle

    CN122570896A

  • A multi-rotor unmanned aerial vehicle endurance test method and device

    CN122570896B