Vehicle travel energy consumption prediction method, device, equipment, medium and program product

Abstract

The invention relates to the technical field of vehicle energy consumption prediction, in particular to a vehicle travel energy consumption prediction method, device and equipment, a medium and a program product, and the method comprises the steps: obtaining real-time road data and real-time environment data of a current vehicle; generating a vehicle speed curve of the current vehicle according to the real-time road data and the real-time environment data, and calculating an intensity factor corresponding to the vehicle speed curve; and inputting the intensity factor corresponding to the vehicle speed curve into a preset energy consumption prediction benchmark decision model to obtain a target energy consumption prediction benchmark, and obtaining the final predicted energy consumption of the current vehicle according to the target energy consumption prediction benchmark. Therefore, by integrating the real-time road data, the environment data and the machine learning algorithm, the problem that energy consumption prediction of the electric vehicle under different driving conditions is inaccurate is solved, the precision and the real-time performance of energy consumption prediction are improved, a user is helped to better plan the journey, a scientific basis is provided for a charging station operator, and healthy development of the electric vehicle industry is promoted.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle energy consumption prediction, and in particular to a method, device, equipment, medium and program product for predicting vehicle travel energy consumption. Background Art

[0002] With the increasing global awareness of environmental protection and the development of renewable energy technology, electric vehicles, as one of the effective tools to reduce urban air pollution and greenhouse gas emissions, have received widespread attention and development. The popularization of electric vehicles faces many challenges, among which range anxiety is the main factor restricting its development; in order to improve the efficiency of electric vehicles and reduce users' range anxiety, accurate travel energy consumption prediction technology is particularly important.

[0003] In the related technologies, most of the energy consumption prediction methods for electric vehicles are based on static data, such as vehicle type, battery capacity, etc. Some use historical data to calculate the predicted energy consumption and predict subsequent vehicle speed changes based on probability statistics.

[0004] However, the electric vehicle energy consumption prediction method in the related technology fails to fully consider the impact of driving conditions (such as road conditions, driving habits, weather, etc.) on energy consumption; at the same time, the prediction method that uses historical data to predict energy consumption calculations often has a huge amount of calculations, and it is difficult to ensure the real-time requirements of the vehicle's energy consumption prediction calculations or the computing power requirements are too high, resulting in difficulties in vehicle terminal implementation, and there is a large deviation between energy consumption and the predicted value, which affects the user experience and the accuracy of vehicle management decisions, and needs to be solved urgently. Summary of the invention

[0005] The present application provides a vehicle travel energy consumption prediction method, device, equipment, medium and program product to solve the problem of inaccurate energy consumption prediction of electric vehicles under different driving conditions, improve the accuracy and real-time performance of energy consumption prediction, help users better plan their trips, provide a scientific basis for charging station operators, and promote the healthy development of the electric vehicle industry.

[0006] The first embodiment of the present application provides a method for predicting vehicle travel energy consumption, comprising the following steps:

[0007] Obtain real-time road data and real-time environmental data of the current vehicle;

[0008] generating a vehicle speed curve of the current vehicle according to the real-time road data and the real-time environment data, and calculating an intensity factor corresponding to the vehicle speed curve;

[0009] The intensity factor corresponding to the vehicle speed curve is input into a preset energy consumption prediction benchmark decision model to obtain a target energy consumption prediction benchmark, and the final predicted energy consumption of the current vehicle is obtained based on the target energy consumption prediction benchmark.

[0010] Optionally, before inputting the intensity factor corresponding to the vehicle speed curve into a preset energy consumption prediction benchmark decision model to obtain the target energy consumption prediction benchmark, the following steps are further included:

[0011] Obtain the non-idle driving energy consumption data of the vehicle under multiple different working conditions under at least one energy consumption prediction benchmark, and calculate the actual energy consumption of the current vehicle under each energy consumption prediction benchmark in each working condition based on the non-idle driving energy consumption data of the vehicle under multiple different working conditions under each energy consumption prediction benchmark;

[0012] Calculate the predicted energy consumption of each energy consumption prediction benchmark in each working condition, and obtain the error of each energy consumption prediction benchmark in each working condition based on the predicted energy consumption of each energy consumption prediction benchmark in each working condition and the actual energy consumption of each energy consumption prediction benchmark in each working condition;

[0013] Based on the error of each energy consumption prediction benchmark in each working condition, determine the energy consumption prediction benchmark with the smallest error in each working condition, and perform machine learning training based on a binary tree classifier with the intensity factors of all working conditions as input and the energy consumption prediction benchmark with the smallest error in each working condition as the response to obtain the preset energy consumption prediction benchmark decision model.

[0014] Optionally, the calculation of the predicted energy consumption of each energy consumption prediction benchmark in each working condition includes:

[0015] Based on a preset energy consumption calculation formula, calculate the predicted energy consumption of each energy consumption prediction benchmark in each working condition, where the preset energy consumption calculation formula is:

[0016]

[0017] where E 基准预测 is the predicted energy consumption of the energy consumption prediction benchmark to be predicted, k spd_工况 is the speed intensity factor of the current working condition, k spd_预测基准 is the speed intensity factor of the energy consumption prediction benchmark to be predicted, B spd_工况 is the speed sensitivity of the current working condition, k h_b_工况 is the medium-high speed braking intensity factor of the current working condition, k h_b_预测基准 is the medium-high speed braking intensity factor of the energy consumption prediction benchmark to be predicted, B h_b_工况 is the medium-high speed braking sensitivity of the current working condition, k l_b_工况 is the low speed braking intensity factor of the current working condition, k l_b_预测基准 is the low speed braking intensity factor of the energy consumption prediction benchmark to be predicted, B l_b_工况 is the low speed braking sensitivity of the current working condition, C ECR_预测基准 is the ECR constant under the energy consumption prediction benchmark to be predicted.

[0018] Optionally, obtaining the final predicted energy consumption of the current vehicle according to the target energy consumption prediction benchmark includes:

[0019] Obtaining the average idling energy consumption of the current vehicle;

[0020] Calculating the driving energy consumption of the current vehicle based on the target energy consumption prediction benchmark;

[0021] Calculating the energy consumption of the air conditioning system and the low-voltage system of the current vehicle;

[0022] Obtaining the final predicted energy consumption according to the average idling energy consumption, the driving energy consumption, the energy consumption of the air conditioning system, and the energy consumption of the low-voltage system.

[0023] Optionally, calculating the driving energy consumption of the current vehicle based on the target energy consumption prediction benchmark includes:

[0024] Calculating the predicted energy consumption of the target energy consumption prediction benchmark;

[0025] Obtaining the current temperature from the real-time environment data, and based on a preset multi-dimensional look-up table MAP, obtaining a predicted energy consumption correction coefficient according to the intensity factor corresponding to the vehicle speed curve and the current temperature;

[0026] Obtaining the driving energy consumption of the current vehicle according to the predicted energy consumption of the target energy consumption prediction benchmark and the predicted energy consumption correction coefficient.

[0027] Optionally, before obtaining the predicted energy consumption correction coefficient according to the intensity factor corresponding to the vehicle speed curve and the current temperature based on a preset multi-dimensional look-up table MAP, it further includes:

[0028] Calculating the intensity factors of different working conditions;

[0029] Based on the same intensity factor, calculating the ratio of the non-idling driving energy consumption of the vehicle at different combined temperatures to the non-idling driving energy consumption of the vehicle at a preset temperature; based on a preset multi-dimensional linear surface fitting algorithm, obtaining the preset multi-dimensional look-up table MAP according to the intensity factors of different working conditions, the temperatures corresponding to the intensity factors of different working conditions, and the ratio of the non-idling driving energy consumption of the vehicle at different combined temperatures to the non-idling driving energy consumption of the vehicle at a preset temperature corresponding to the intensity factors of different working conditions.

[0030] An embodiment of the second aspect of the present application provides a device for predicting the travel energy consumption of a vehicle, including:

[0031] An acquisition module, configured to acquire the real-time road data and real-time environment data of the current vehicle;

[0032] A calculation module, configured to generate a vehicle speed curve of the current vehicle according to the real-time road data and the real-time environment data, and calculate an intensity factor corresponding to the vehicle speed curve;

[0033] A prediction module, configured to input the intensity factor corresponding to the vehicle speed curve into a preset energy consumption prediction benchmark decision model to obtain a target energy consumption prediction benchmark, and obtain a final predicted energy consumption of the current vehicle according to the target energy consumption prediction benchmark.

[0034] Optionally, before inputting the intensity factor corresponding to the vehicle speed curve into a preset energy consumption prediction benchmark decision model to obtain the target energy consumption prediction benchmark, the prediction module is further configured to:

[0035] Obtain vehicle non-idle driving energy consumption data of multiple different working conditions under at least one energy consumption prediction benchmark, and calculate the actual energy consumption of the current vehicle for each energy consumption prediction benchmark under each working condition according to the vehicle non-idle driving energy consumption data of multiple different working conditions under each energy consumption prediction benchmark;

[0036] Calculate the predicted energy consumption of each energy consumption prediction benchmark under each working condition, and obtain the error of each energy consumption prediction benchmark under each working condition according to the predicted energy consumption of each energy consumption prediction benchmark under each working condition and the actual energy consumption of each energy consumption prediction benchmark under each working condition;

[0037] Based on the error of each energy consumption prediction benchmark under each working condition, determine the energy consumption prediction benchmark with the smallest error under each working condition, and perform machine learning training based on a binary tree classifier with the intensity factors of all working conditions as inputs and the energy consumption prediction benchmark with the smallest error under each working condition as responses to obtain the preset energy consumption prediction benchmark decision model.

[0038] Optionally, the prediction module is specifically configured to:

[0039] Calculate the predicted energy consumption of each energy consumption prediction benchmark under each working condition based on a preset energy consumption calculation formula, where the preset energy consumption calculation formula is:

[0040]

[0041] where E 基准预测 is the predicted energy consumption of the energy consumption prediction benchmark to be predicted, k spd_工况 is the speed intensity factor of the current working condition, k spd_预测基准 is the speed intensity factor of the energy consumption prediction benchmark to be predicted, B spd_工况 is the speed sensitivity of the current working condition, k h_b_工况 is the medium and high speed braking intensity factor of the current working condition, k h_b_预测基准 is the medium and high speed braking intensity factor of the energy consumption prediction benchmark to be predicted, Bh_b_工况 is the medium and high speed braking sensitivity for the current working condition, k l_b_工况 is the low speed braking intensity factor for the current working condition, k l_b_预测基准 is the low speed braking intensity factor for the energy consumption prediction benchmark to be predicted, B l_b_工况 is the low speed braking sensitivity for the current working condition, C ECR_预测基准 is the ECR constant under the energy consumption prediction benchmark to be predicted.

[0042] Optionally, the prediction module is specifically configured to:

[0043] Obtain the average idling energy consumption of the current vehicle;

[0044] Based on the target energy consumption prediction benchmark, calculate the driving energy consumption of the current vehicle;

[0045] Calculate the energy consumption of the air conditioning system and the low voltage system of the current vehicle;

[0046] Obtain the final predicted energy consumption according to the average idling energy consumption, the driving energy consumption, the energy consumption of the air conditioning system and the energy consumption of the low voltage system.

[0047] Optionally, the prediction module is specifically configured to:

[0048] Calculate the predicted energy consumption of the target energy consumption prediction benchmark;

[0049] Obtain the current temperature from the real-time environmental data, and based on a preset multi-dimensional look-up table MAP, obtain a predicted energy consumption correction coefficient according to the intensity factor corresponding to the vehicle speed curve and the current temperature;

[0050] Obtain the driving energy consumption of the current vehicle according to the predicted energy consumption of the target energy consumption prediction benchmark and the predicted energy consumption correction coefficient.

[0051] Optionally, before obtaining the predicted energy consumption correction coefficient according to the intensity factor corresponding to the vehicle speed curve and the current temperature based on a preset multi-dimensional look-up table MAP, the prediction module is further configured to:

[0052] Calculate the intensity factors of different working conditions;

[0053] Based on the same intensity factor, calculate the ratio of the non-idling driving energy consumption of the vehicle at different combined temperatures to the non-idling driving energy consumption of the vehicle at a preset temperature; based on a preset multi-dimensional linear surface fitting algorithm, according to the intensity factors of different working conditions, the temperatures corresponding to the intensity factors of different working conditions, and the ratio of the non-idling driving energy consumption of the vehicle at different combined temperatures corresponding to the intensity factors of different working conditions to the non-idling driving energy consumption of the vehicle at a preset temperature, obtain the preset multi-dimensional look-up table MAP.

[0054] A third aspect embodiment of the present application provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are configured to execute the vehicle travel energy consumption prediction method as described in the above embodiments.

[0055] A fourth aspect embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and the program is executed by a processor to implement the vehicle travel energy consumption prediction method as described in the above embodiments.

[0056] A fifth aspect embodiment of the present application provides a computer program product, the computer program product stores a computer program, and when the program is executed by a processor, it implements the vehicle travel energy consumption prediction method as described in the above embodiments.

[0057] Thus, the embodiments of the present application obtain the real-time road data and real-time environmental data of the current vehicle, generate the vehicle speed curve of the current vehicle according to the real-time road data and real-time environmental data, calculate the intensity factor corresponding to the vehicle speed curve, input the intensity factor corresponding to the vehicle speed curve into a preset energy consumption prediction benchmark decision model to obtain the target energy consumption prediction benchmark, and obtain the final predicted energy consumption of the current vehicle according to the target energy consumption prediction benchmark. Thus, problems such as inaccurate energy consumption prediction of electric vehicles under different driving conditions are solved, the accuracy and real-time performance of energy consumption prediction are improved, which helps users better plan their trips, provides a scientific basis for charging station operators, and promotes the healthy development of the electric vehicle industry.

[0058] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be understood through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description of the embodiments in conjunction with the drawings, wherein:

[0060] Figure 1 is a flowchart of a vehicle travel energy consumption prediction method according to an embodiment of the present application;

[0061] Figure 2 is a flowchart of a vehicle travel energy consumption prediction method according to an embodiment of the present application;

[0062] Figure 3 is a block diagram of a vehicle travel energy consumption prediction device according to an embodiment of the present application;

[0063] Figure 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application. Specific Embodiments

[0064] The embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application, and should not be construed as limiting the present application.

[0065] The method, device, electronic device, and storage medium for predicting travel energy consumption of a vehicle according to an embodiment of the present application will be described below with reference to the accompanying drawings. In view of the problem that the energy consumption prediction of electric vehicles is inaccurate under different driving conditions mentioned in the above background art, the present application provides a method for predicting travel energy consumption of a vehicle. In this method, the embodiment of the present application obtains real-time road data and real-time environmental data of the current vehicle, generates a vehicle speed curve of the current vehicle according to the real-time road data and the real-time environmental data, calculates an intensity factor corresponding to the vehicle speed curve, inputs the intensity factor corresponding to the vehicle speed curve into a preset energy consumption prediction benchmark decision model to obtain a target energy consumption prediction benchmark, and obtains the final predicted energy consumption of the current vehicle according to the target energy consumption prediction benchmark. Thereby, problems such as inaccurate energy consumption prediction of electric vehicles under different driving conditions are solved, the accuracy and real-time performance of energy consumption prediction are improved, which helps users better plan their trips, provides a scientific basis for charging station operators, and promotes the healthy development of the electric vehicle industry.

[0066] Specifically, Figure 1 is a schematic flowchart of a method for predicting travel energy consumption of a vehicle provided by an embodiment of the present application.

[0067] As Figure 1 shown, the method for predicting travel energy consumption of the vehicle includes the following steps:

[0068] In step S101, real-time road data and real-time environmental data of the current vehicle are obtained.

[0069] Among them, obtaining the real-time road data and real-time environmental data of the current vehicle means that after the user inputs relevant configuration parameters in the in-vehicle navigation interface, the road data and environmental data can be obtained from the data interface provided by the map provider.

[0070] Specifically, obtaining the real-time road data of the current vehicle includes but is not limited to route segments, route segment distances, etc.; obtaining the real-time environmental data of the current vehicle includes but is not limited to data of relevant environmental attributes such as weather and temperature.

[0071] In step S102, a vehicle speed curve of the current vehicle is generated according to the real-time road data and the real-time environmental data, and an intensity factor corresponding to the vehicle speed curve is calculated.

[0072] Specifically, the embodiment of the present application obtains real-time road data and environmental data according to the navigation route selected by the user, generates a vehicle speed curve for the corresponding route according to the driving condition generation algorithm, and at least obtains temperature, wind force, and wind direction data.

[0073] Among them, the driving condition generation algorithm refers to a series of algorithms for generating the vehicle speed curve of the user's future travel using real-time road data and environmental data, such as the driving condition generation algorithm based on Markov, the short-trip driving condition generation algorithm, etc.

[0074] It can be understood that by generating the vehicle speed curve and calculating the intensity factor through real-time data, the embodiment of the present application can more accurately reflect the impact of actual driving conditions on energy consumption, thereby improving the accuracy of energy consumption prediction; the dynamic update of real-time data enables energy consumption prediction to quickly adapt to different driving conditions and environmental changes, enhancing the adaptability of the system; combined with the user's historical driving data, the generated vehicle speed curve and intensity factor can better reflect the user's driving habits, realizing personalized energy consumption prediction.

[0075] In step S103, the intensity factor corresponding to the vehicle speed curve is input into a preset energy consumption prediction benchmark decision model to obtain a target energy consumption prediction benchmark, and the final predicted energy consumption of the current vehicle is obtained according to the target energy consumption prediction benchmark.

[0076] Among them, the preset energy consumption prediction benchmark decision model is constructed based on machine learning algorithms, and determines the best energy consumption prediction benchmark by analyzing the intensity factor and the error of actual energy consumption (i.e., non-idle driving energy consumption) under different driving conditions.

[0077] Specifically, calculate the intensity factor corresponding to the vehicle speed curve generated by the current vehicle based on real-time road data and real-time environmental data, that is, the speed intensity factor k spd , the medium-high speed braking intensity factor k h_b and the low-speed braking intensity factor k l_b ; different intensity factor thresholds are built into the preset energy consumption prediction benchmark decision model. After the calculated intensity factor is input into the preset energy consumption prediction benchmark decision model, the model will automatically compare it with the preset intensity factor threshold, and select a target energy consumption prediction benchmark that matches the input intensity factor and is located at the corresponding intensity factor threshold; calculate the predicted energy consumption based on the selected target energy consumption prediction benchmark, and combine the predicted energy consumption and the predicted energy consumption correction coefficient to obtain the final predicted energy consumption of the current vehicle.

[0078] Optionally, in some embodiments, obtaining the final predicted energy consumption of the current vehicle according to the target energy consumption prediction benchmark includes: obtaining the average idling energy consumption of the current vehicle; calculating the driving energy consumption of the current vehicle based on the target energy consumption prediction benchmark; calculating the energy consumption of the air conditioning system and the low-voltage system of the current vehicle; and obtaining the final predicted energy consumption according to the average idling energy consumption, the driving energy consumption, the energy consumption of the air conditioning system, and the energy consumption of the low-voltage system.

[0079] Specifically, in the embodiments of the present application, calculating the average idling energy consumption of the current vehicle can be achieved by statistically calculating the average idling power consumption when the user's vehicle idles at the speed in the last 5 trips.

[0080] Furthermore, in the embodiments of the present application, calculating the energy consumption of the air conditioning system of the current vehicle involves obtaining the vehicle air conditioning energy consumption data at different temperatures and under different vehicle air conditioning settings. The data can be from actual tests or simulation results or a combination of both. The air conditioning settings at least include the target temperature and the air conditioning mode. Algorithms such as multi-dimensional linear surface fitting are used to construct a multi-dimensional look-up table Map with temperature and air conditioning settings as inputs and actual air conditioning energy consumption data as outputs. The vehicle air conditioning energy consumption is obtained by looking up the multi-dimensional look-up table MAP with the temperature data of the real-time environment data of the current vehicle and the current vehicle air conditioning setting parameters.

[0081] Furthermore, in the embodiments of the present application, calculating the energy consumption of the low-voltage system of the current vehicle involves obtaining the vehicle low-voltage energy consumption data at different temperatures. The data can be from actual tests or simulation results or a combination of both. Algorithms such as one-dimensional linear interpolation are used to construct a one-dimensional look-up table Map with temperature as the input and actual low-voltage energy consumption data as the output. The vehicle low-voltage energy consumption is obtained by looking up the one-dimensional look-up table MAP with the temperature data of the real-time environment data of the current vehicle.

[0082] Optionally, in some embodiments, calculating the driving energy consumption of the current vehicle based on the target energy consumption prediction benchmark includes: calculating the predicted energy consumption of the target energy consumption prediction benchmark; obtaining the current temperature from the real-time environment data, and based on a preset multi-dimensional look-up table MAP, obtaining a predicted energy consumption correction coefficient according to the intensity factor corresponding to the vehicle speed curve and the current temperature; and obtaining the driving energy consumption of the current vehicle according to the predicted energy consumption of the target energy consumption prediction benchmark and the predicted energy consumption correction coefficient.

[0083] It can be understood that, in the embodiments of the present application, the predicted energy consumption of the target energy consumption prediction benchmark is calculated according to the intensity factor corresponding to the vehicle speed curve, and the non-idle driving energy consumption (actual energy consumption) data of the vehicle at different temperatures is obtained. The data can come from actual tests or simulation results or a combination of both; the intensity factors under different working conditions are calculated, and the ratio of the non-idle driving energy consumption of the vehicle at different temperatures with the same intensity factor combination to the non-idle driving energy consumption of the vehicle at room temperature of 23°C is calculated; algorithms such as multi-dimensional linear surface fitting are used to construct a 4D look-up MAP with the intensity factors under different working conditions and the corresponding temperatures as inputs and the ratio of the non-idle driving energy consumption of the vehicle at different temperatures with the same intensity factor combination to the non-idle driving energy consumption of the vehicle at room temperature of 23°C as the output; according to the intensity factor corresponding to the vehicle speed curve and the obtained temperature, the 4D look-up MAP is searched, and the output ratio is used as the predicted energy consumption correction coefficient; the predicted energy consumption of the corresponding energy consumption prediction benchmark calculated according to the intensity factor corresponding to the vehicle speed curve is multiplied by the predicted energy consumption correction coefficient to obtain the final vehicle driving energy consumption.

[0084] Thus, in the embodiments of the present application, the sum of the driving power consumption, idle energy consumption, air conditioning system energy consumption, and low-voltage system energy consumption is calculated as the final vehicle predicted energy consumption.

[0085] For the convenience of those skilled in the art to understand, the following will detail how to determine the energy consumption prediction benchmark decision model preset in the embodiments of the present application.

[0086] Optionally, in some embodiments, before inputting the intensity factor corresponding to the vehicle speed curve into the preset energy consumption prediction benchmark decision model to obtain the target energy consumption prediction benchmark, it further includes: obtaining the non-idle driving energy consumption data of the vehicle under multiple different working conditions under at least one energy consumption prediction benchmark, and calculating the actual energy consumption of the current vehicle under each energy consumption prediction benchmark in each working condition according to the non-idle driving energy consumption data of the vehicle under multiple different working conditions under each energy consumption prediction benchmark; calculating the predicted energy consumption of each energy consumption prediction benchmark in each working condition, and obtaining the error of each energy consumption prediction benchmark in each working condition according to the predicted energy consumption of each energy consumption prediction benchmark in each working condition and the actual energy consumption of each energy consumption prediction benchmark in each working condition; based on the error of each energy consumption prediction benchmark in each working condition, determining the energy consumption prediction benchmark with the smallest error in each working condition, and performing machine learning training based on a binary tree classifier with the intensity factors of all working conditions as inputs and the energy consumption prediction benchmark with the smallest error in each working condition as the response to obtain the preset energy consumption prediction benchmark decision model.

[0087] Among them, multiple different working conditions refer to the operating states of the vehicle under different driving conditions and environments. These working conditions reflect various situations that the vehicle may encounter in actual use and are important bases for evaluating and predicting energy consumption; the non-idle driving energy consumption data of the vehicle refers to the energy consumption data of the vehicle when it is not idling (i.e., the vehicle is in a driving state).

[0088] It is understandable that before predicting the energy consumption of each energy consumption prediction benchmark under each working condition, the embodiments of the present application select CLTC-P (China Light-Duty Vehicle Test Cycle), WLTC (Worldwide harmonized Light vehicles Test Cycle), NEDC (New European Driving Cycle), and user typical driving conditions as the energy consumption prediction benchmarks, and obtain all energy consumption-related data corresponding to the energy consumption prediction benchmarks.

[0089] Among them, the user typical driving condition refers to the time-speed curve that can represent the user's travel habits generated by collecting the user's historical data. The energy consumption prediction benchmark refers to a series of specific or general time-speed curves that can reflect the impact of the user's driving behavior on energy consumption. The energy consumption-related data at least includes the driving energy consumption of the electric drive system, the settings and energy consumption of the air conditioning system, and the energy consumption at the DCDC input end.

[0090] Furthermore, after obtaining all energy consumption-related data corresponding to the energy consumption prediction benchmarks, the embodiments of the present application calculate the intensity factors of all energy consumption prediction benchmarks based on real-time data; the intensity factors are the speed intensity factor k spd , the medium-high speed braking intensity factor k h_b , and the low-speed braking intensity factor k l_b , and the specific calculation formulas are as follows:

[0091]

[0092]

[0093] Among them, v is the vehicle speed data of each point of the energy consumption prediction benchmark, E b is the theoretically recoverable energy during the braking process, v lim is the speed threshold for distinguishing low speed and medium-high speed, and T is the time interval corresponding to the vehicle speed data of each point of the energy consumption prediction benchmark.

[0094] Furthermore, after calculating the intensity factors of all energy consumption prediction benchmarks, the embodiments of the present application calculate the ECR constant and speed sensitivity of all energy consumption prediction benchmarks based on real-time data. The embodiments of the present application obtain the constant-speed energy consumption test data of the vehicle at no less than 3 speed points. The test data can come from experiments or simulations. The difference between the maximum value and the minimum value of the speed points should not be less than 80 km / h, and the speed points should be selected as evenly as possible; count the energy consumption of the non-idle segments of all constant-speed energy consumption test data to avoid the influence of the start and end segments of the experiment on the results; according to the speed points and the corresponding energy consumption values of all constant-speed energy consumption tests, perform linear fitting based on the least squares method. The slope of the straight line in the fitting result is the speed sensitivity B spd , and the intercept of the straight line is the ECR constant C ECR . The embodiments of the present application count all non-idle segment energy consumption test data E in the energy consumption prediction benchmark test data no_idle; Intercept the continuous vehicle speed segments where all vehicle speeds in the energy consumption prediction benchmark are between 0 and 2 times the low-speed and medium-high-speed thresholds as low-speed segments, intercept the continuous vehicle speed segments where all vehicle speeds are between 0 and 6 times the low-speed and medium-high-speed thresholds as medium-high-speed segments, and the starting and ending vehicle speeds of the intercepted segments should both be 0; Calculate the intensity factor, ECR constant, and speed sensitivity of the low-speed segments and medium-high-speed segments respectively; According to the formula and the two sets of data of the low-speed segments and medium-high-speed segments, the system of equations can be solved to obtain the medium-high-speed braking sensitivity B h_b and the low-speed braking sensitivity B l_b , and the specific calculation formula is as follows:

[0095] B h_b I hb +B l_b I lb =E no_idle -C ECR -B spd I spd ;

[0096] Optionally, in some embodiments, calculating the predicted energy consumption of each energy consumption prediction benchmark under each working condition includes: calculating the predicted energy consumption of each energy consumption prediction benchmark under each working condition based on a preset energy consumption calculation formula, where the preset energy consumption calculation formula is:

[0097]

[0098] where E 基准预测 is the predicted energy consumption of the energy consumption prediction benchmark to be predicted, k spd_工况 is the speed intensity factor of the current working condition, k spd_预测基准 is the speed intensity factor of the energy consumption prediction benchmark to be predicted, B spd_工况 is the speed sensitivity of the current working condition, k h_b_工况 is the medium-high-speed braking intensity factor of the current working condition, k h_b_预测基准 is the medium-high-speed braking intensity factor of the energy consumption prediction benchmark to be predicted, B h_b_工况 is the medium-high-speed braking sensitivity of the current working condition, k l_b_工况 is the low-speed braking intensity factor of the current working condition, k l_b_预测基准 is the low-speed braking intensity factor of the energy consumption prediction benchmark to be predicted, B l_b_工况 is the low-speed braking sensitivity of the current working condition, C ECR_预测基准 is the ECR constant under the energy consumption prediction benchmark to be predicted.

[0099] It can be understood that when calculating the predicted energy consumption of each energy consumption prediction benchmark under each working condition based on a preset energy consumption calculation formula in the embodiments of the present application, first, vehicle non-idle driving energy consumption data of no less than 50 different working conditions under each energy consumption prediction benchmark is obtained. The data can come from actual tests or simulation results or a combination of both. Then, the intensity factors of all different working conditions and the predicted energy consumption of all energy consumption prediction benchmarks under all different working conditions are calculated. Next, the errors between the predicted energy consumption and the actual energy consumption (i.e., non-idle driving energy consumption) of all 4 energy consumption prediction benchmarks under all different working conditions are calculated. The benchmark with the smallest error among the 4 energy consumption prediction benchmarks is recorded and saved. CLTC-P is recorded as 1, WLTC is recorded as 2, NEDC is recorded as 3, and the user's typical working condition is recorded as 4. According to the recorded data, with the intensity factors of all different working conditions as the input and the energy consumption prediction benchmark corresponding to the minimum error of all working conditions as the response, machine learning training based on a binary tree classifier is performed to generate a series of binary judgment conditions and their thresholds regarding the intensity factors as the decision conditions for energy consumption prediction benchmark selection, and a preset energy consumption prediction benchmark decision model is obtained.

[0100] It should be noted that the embodiments of the present application can significantly improve the accuracy of energy consumption prediction, not only considering different driving conditions but also selecting the optimal energy consumption prediction benchmark for each situation. Due to the adoption of a machine learning algorithm, the energy consumption prediction benchmark decision model can adapt to different driving environments and conditions, having strong generality and flexibility. For electric vehicle users, more accurate energy consumption prediction helps better plan trips and reduce anxiety caused by concerns about insufficient battery power. At the same time, the embodiments of the present application also provide a scientific basis for charging station operators, helping to reasonably layout charging facilities and promoting the sustainable development of the electric vehicle industry.

[0101] Thus, by dynamically selecting the energy consumption prediction benchmark with the smallest error, the preset energy consumption prediction benchmark decision model obtained in the embodiments of the present application can quickly adapt to different driving conditions and environmental changes, simplifies the calculation of energy consumption correction, and further improves the accuracy, adaptability, and reliability of electric vehicle energy consumption prediction.

[0102] Optionally, in some embodiments, before obtaining the predicted energy consumption correction coefficient based on a preset multi-dimensional look-up MAP according to the intensity factor corresponding to the vehicle speed curve and the current temperature, it further includes: calculating the intensity factors of different working conditions; based on the same intensity factors, calculating the ratio of the vehicle non-idle driving energy consumption at different combined temperatures to the vehicle non-idle driving energy consumption at a preset temperature; and based on a preset multi-dimensional linear surface fitting algorithm, obtaining a preset multi-dimensional look-up MAP according to the intensity factors of different working conditions, the temperatures corresponding to the intensity factors of different working conditions, and the ratio of the vehicle non-idle driving energy consumption at different combined temperatures to the vehicle non-idle driving energy consumption at a preset temperature corresponding to the intensity factors of different working conditions.

[0103] Among them, the preset temperature can be a threshold value preset by the user, a threshold value obtained through a limited number of experiments, or a threshold value obtained through a limited number of computer simulations, and no specific limitation is made here.

[0104] Thus, the multi-dimensional look-up table MAP can quickly respond to different working conditions and temperature changes, dynamically adjust the energy consumption correction coefficient, avoid complex real-time calculations, help users better plan their trips, reduce range anxiety. At the same time, it also supports charging station operators to optimize service strategies and promote the healthy development of the electric vehicle industry.

[0105] Thus, the travel energy consumption prediction method of the vehicle in the embodiment of the present application is reasonably designed. By reasonably using the real-time road data and environmental data of the navigation route, it solves the problems that the existing electric vehicle energy consumption prediction methods fail to fully consider the influence of driving conditions on energy consumption and the calculation amount is extremely large, making it difficult to meet the real-time requirement of the vehicle's energy consumption prediction calculation. The embodiment of the present application uses a machine learning algorithm to select the energy consumption prediction benchmark, introduces environmental data and actual vehicle configuration parameters to correct the predicted energy consumption, and further improves the energy consumption prediction accuracy. The embodiment of the present application realizes the accurate prediction of the energy consumption of electric vehicles under different driving conditions by integrating advanced data analysis algorithms and real-time data acquisition systems. This method can not only help users better plan their trips, but also provide a scientific basis for charging station operators, thus promoting the healthy development of the electric vehicle industry.

[0106] The travel energy consumption prediction method of the vehicle will be described in detail below in combination with a specific embodiment of the present application.

[0107] Specifically, as Figure 2 shown, the travel energy consumption prediction method of the vehicle includes the following steps:

[0108] S201: Select an energy consumption prediction benchmark and obtain all energy consumption-related data corresponding to the energy consumption prediction benchmark.

[0109] S202: Calculate the intensity factor for each energy consumption prediction benchmark based on the obtained data.

[0110] S203: Calculate the ECR constant and speed sensitivity for each energy consumption prediction benchmark.

[0111] S204: Calculate the high-speed braking sensitivity and low-speed braking sensitivity for each energy consumption prediction benchmark.

[0112] S205: According to the navigation route input by the user, obtain real-time road data (such as road conditions, slopes, etc.) and environmental data (such as temperature, wind force, wind direction, etc.), and generate a vehicle speed curve for the corresponding route through a working condition generation algorithm.

[0113] S206: Calculate the intensity factor corresponding to the generated vehicle speed curve based on the generated vehicle speed curve.

[0114] S207: Compare all the intensity factors calculated previously and select the best energy consumption prediction benchmark.

[0115] S208: Calculate the driving energy consumption of the vehicle based on the selected best energy consumption prediction benchmark.

[0116] S209: Calculate the idling energy consumption of the vehicle.

[0117] S210: Calculate the energy consumption of the vehicle air conditioning system.

[0118] S211: Calculate the energy consumption of the vehicle low - voltage system.

[0119] S212: Add up the above - mentioned energy consumptions to obtain the final predicted energy consumption of the vehicle.

[0120] According to the vehicle travel energy consumption prediction method proposed in the embodiments of the present application, obtain the real - time road data and real - time environment data of the current vehicle, generate the vehicle speed curve of the current vehicle according to the real - time road data and real - time environment data, calculate the intensity factor corresponding to the vehicle speed curve, input the intensity factor corresponding to the vehicle speed curve into the preset energy consumption prediction benchmark decision model to obtain the target energy consumption prediction benchmark, and obtain the final predicted energy consumption of the current vehicle according to the target energy consumption prediction benchmark. Thus, problems such as inaccurate energy consumption prediction of electric vehicles under different driving conditions are solved, the accuracy and real - time performance of energy consumption prediction are improved, which helps users better plan their trips, provides a scientific basis for charging station operators, and promotes the healthy development of the electric vehicle industry.

[0121] Secondly, describe the vehicle travel energy consumption prediction device proposed in the embodiments of the present application with reference to the accompanying drawings.

[0122] Figure 3 It is a block diagram of the vehicle travel energy consumption prediction device according to the embodiments of the present application.

[0123] As Figure 3 shown, the vehicle travel energy consumption prediction device 10 includes: an acquisition module 100, a calculation module 200, and a prediction module 300.

[0124] Among them, the acquisition module 100 is used to acquire the real - time road data and real - time environment data of the current vehicle;

[0125] The calculation module 200 is used to generate the vehicle speed curve of the current vehicle according to the real - time road data and real - time environment data, and calculate the intensity factor corresponding to the vehicle speed curve;

[0126] The prediction module 300 is configured to input the intensity factor corresponding to the vehicle speed curve into a preset energy consumption prediction benchmark decision model to obtain a target energy consumption prediction benchmark, and obtain the final predicted energy consumption of the current vehicle based on the target energy consumption prediction benchmark.

[0127] Optionally, in some embodiments, before inputting the intensity factor corresponding to the vehicle speed curve into the preset energy consumption prediction benchmark decision model to obtain the target energy consumption prediction benchmark, the prediction module 300 is further configured to: obtain the non-idle driving energy consumption data of the vehicle under multiple different working conditions under at least one energy consumption prediction benchmark, and calculate the actual energy consumption of the current vehicle for each energy consumption prediction benchmark under each working condition based on the non-idle driving energy consumption data of the vehicle under multiple different working conditions under each energy consumption prediction benchmark; calculate the predicted energy consumption of each energy consumption prediction benchmark under each working condition, and obtain the error of each energy consumption prediction benchmark under each working condition based on the predicted energy consumption of each energy consumption prediction benchmark under each working condition and the actual energy consumption of each energy consumption prediction benchmark under each working condition; based on the error of each energy consumption prediction benchmark under each working condition, determine the energy consumption prediction benchmark with the minimum error under each working condition, and perform machine learning training based on a binary tree classifier with the intensity factors of all working conditions as inputs and the energy consumption prediction benchmark with the minimum error under each working condition as the response to obtain the preset energy consumption prediction benchmark decision model.

[0128] Optionally, in some embodiments, the prediction module 300 is specifically configured to: calculate the predicted energy consumption of each energy consumption prediction benchmark under each working condition based on a preset energy consumption calculation formula, where the preset energy consumption calculation formula is:

[0129]

[0130] where E 基准预测 is the predicted energy consumption of the energy consumption prediction benchmark to be predicted, k spd_工况 is the speed intensity factor of the current working condition, k spd_预测基准 is the speed intensity factor of the energy consumption prediction benchmark to be predicted, B spd_工况 is the speed sensitivity of the current working condition, k h_b_工况 is the medium-high speed braking intensity factor of the current working condition, k h_b_预测基准 is the medium-high speed braking intensity factor of the energy consumption prediction benchmark to be predicted, B h_b_工况 is the medium-high speed braking sensitivity of the current working condition, k l_b_工况 is the low speed braking intensity factor of the current working condition, k l_b_预测基准 is the low speed braking intensity factor of the energy consumption prediction benchmark to be predicted, B l_b_工况 is the low speed braking sensitivity of the current working condition, C ECR_预测基准 is the ECR constant under the energy consumption prediction benchmark to be predicted.

[0131] Optionally, in some embodiments, the prediction module 300 is specifically configured to: obtain the average idle energy consumption of the current vehicle; calculate the driving energy consumption of the current vehicle based on the target energy consumption prediction benchmark; calculate the energy consumption of the air conditioning system and the low-voltage system of the current vehicle; and obtain the final predicted energy consumption according to the average idle energy consumption, the driving energy consumption, the energy consumption of the air conditioning system, and the energy consumption of the low-voltage system.

[0132] Optionally, in some embodiments, the prediction module 300 is specifically configured to: calculate the predicted energy consumption of the target energy consumption prediction benchmark; obtain the current temperature from the real-time environmental data, and based on a preset multi-dimensional look-up table MAP, obtain a predicted energy consumption correction coefficient according to the intensity factor corresponding to the vehicle speed curve and the current temperature; and obtain the driving energy consumption of the current vehicle according to the predicted energy consumption of the target energy consumption prediction benchmark and the predicted energy consumption correction coefficient.

[0133] Optionally, in some embodiments, before obtaining the predicted energy consumption correction coefficient according to the intensity factor corresponding to the vehicle speed curve and the current temperature based on the preset multi-dimensional look-up table MAP, the prediction module 300 is further configured to: calculate the intensity factors of different working conditions; based on the same intensity factor, calculate the ratio of the non-idle driving energy consumption of the vehicle at different combined temperatures to the non-idle driving energy consumption of the vehicle at the preset temperature; and based on a preset multi-dimensional linear surface fitting algorithm, obtain the preset multi-dimensional look-up table MAP according to the intensity factors of different working conditions, the temperatures corresponding to the intensity factors of different working conditions, and the ratio of the non-idle driving energy consumption of the vehicle at different combined temperatures to the non-idle driving energy consumption of the vehicle at the preset temperature corresponding to the intensity factors of different working conditions.

[0134] It should be noted that the foregoing explanation of the embodiments of the vehicle travel energy consumption prediction method also applies to the vehicle travel energy consumption prediction device of this embodiment, and will not be repeated here.

[0135] According to the vehicle travel energy consumption prediction device provided by the embodiments of the present application, the embodiments of the present application obtain the real-time road data and real-time environmental data of the current vehicle, generate the vehicle speed curve of the current vehicle according to the real-time road data and real-time environmental data, calculate the intensity factor corresponding to the vehicle speed curve, input the intensity factor corresponding to the vehicle speed curve into a preset energy consumption prediction benchmark decision model to obtain a target energy consumption prediction benchmark, and obtain the final predicted energy consumption of the current vehicle according to the target energy consumption prediction benchmark. Thereby, problems such as inaccurate energy consumption prediction of electric vehicles under different driving conditions are solved, the accuracy and real-time performance of energy consumption prediction are improved, it helps users better plan their trips, provides a scientific basis for charging station operators, and promotes the healthy development of the electric vehicle industry.

[0136] Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. The electronic device may include:

[0137] A memory 401, a processor 402, and a computer program stored on the memory 401 and executable on the processor 402.

[0138] When the processor 402 executes the program, it implements the travel energy consumption prediction method for vehicles provided in the above embodiments.

[0139] Furthermore, the electronic device further includes:

[0140] A communication interface 403 for communication between the memory 401 and the processor 402.

[0141] The memory 401 is used to store a computer program that can run on the processor 402.

[0142] The memory 401 may include a high-speed RAM memory, and may also include non-volatile memory, such as at least one disk memory.

[0143] If the memory 401, the processor 402, and the communication interface 403 are implemented independently, the communication interface 403, the memory 401, and the processor 402 can be interconnected through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity of representation, Figure 4 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0144] Optionally, in a specific implementation, if the memory 401, the processor 402, and the communication interface 403 are integrated on a chip, the memory 401, the processor 402, and the communication interface 403 can communicate with each other through an internal interface.

[0145] The processor 402 may be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0146] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned travel energy consumption prediction method for a vehicle is implemented.

[0147] An embodiment of the present application further provides a computer program product. The computer program product stores a computer program, and when the program is executed by a processor, the above-mentioned travel energy consumption prediction method for a vehicle is implemented.

[0148] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0149] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0150] Any process or method description shown in the flowchart or described in other ways herein can be understood as representing a module, segment, or part of code including one or more executable instructions for implementing a customized logical function or process. The scope of the preferred embodiments of the present application includes additional implementations, where the functions can be executed in a substantially simultaneous manner or in a reverse order according to the functions involved, rather than in the order shown or discussed, which should be understood by those skilled in the art of the embodiments of the present application.

[0151] It should be understood that each part of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0152] Those of ordinary skill in the art can understand that all or part of the steps carried by the method of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

Claims

1. A method for predicting vehicle travel energy consumption, characterized in that: The following steps are involved: Obtain real-time road data and real-time environmental data of the current vehicle; generating a vehicle speed curve of the current vehicle according to the real-time road data and the real-time environment data, and calculating an intensity factor corresponding to the vehicle speed curve; The intensity factor corresponding to the vehicle speed curve is input into a preset energy consumption prediction benchmark decision model to obtain a target energy consumption prediction benchmark, and the final predicted energy consumption of the current vehicle is obtained based on the target energy consumption prediction benchmark.

2. The method according to claim 1, characterized in that Before inputting the intensity factor corresponding to the vehicle speed curve into a preset energy consumption prediction benchmark decision model to obtain the target energy consumption prediction benchmark, the method further includes: Acquire vehicle non-idling driving energy consumption data of multiple different working conditions under at least one energy consumption prediction benchmark, and calculate the actual energy consumption of each energy consumption prediction benchmark of the current vehicle under each working condition according to the vehicle non-idling driving energy consumption data of multiple different working conditions under each energy consumption prediction benchmark; Calculating the predicted energy consumption of each energy consumption prediction benchmark under each operating condition, and obtaining the error of each energy consumption prediction benchmark under each operating condition according to the predicted energy consumption of each energy consumption prediction benchmark under each operating condition and the actual energy consumption of each energy consumption prediction benchmark under each operating condition; Based on the error of each energy consumption prediction benchmark under each operating condition, the energy consumption prediction benchmark with the smallest error under each operating condition is determined, and machine learning training based on a binary tree classifier is performed with the intensity factor of all operating conditions as input and the energy consumption prediction benchmark with the smallest error under each operating condition as response to obtain the preset energy consumption prediction benchmark decision model.

3. The method according to claim 2, characterized in that The calculation of the predicted energy consumption of each energy consumption prediction benchmark under each operating condition includes: Based on the preset energy consumption calculation formula, the predicted energy consumption of each energy consumption prediction benchmark under each working condition is calculated, wherein the preset energy consumption calculation formula is: Among them, E base prediction is the predicted energy consumption of the energy consumption prediction benchmark to be predicted, k spd_ Working condition is the velocity intensity factor of the current working condition, k spd_ The prediction benchmark is the speed intensity factor of the energy consumption prediction benchmark to be predicted, B spd_ The working condition is the speed sensitivity of the current working condition, k h_b_ The working condition is the medium and high speed braking intensity factor of the current working condition, k h_b_ The prediction benchmark is the medium and high speed braking intensity factor of the energy consumption prediction benchmark to be predicted, B h_b_ The working condition is the medium and high speed braking sensitivity of the current working condition, k l_b_ The working condition is the low-speed braking intensity factor of the current working condition, k l_b_ The prediction basis is the low-speed braking intensity factor of the energy consumption prediction basis to be predicted, B l_b_ The working condition is the low-speed braking sensitivity of the current working condition, C ECR_ The prediction benchmark is the ECR constant under the energy consumption prediction benchmark which is the energy consumption prediction benchmark to be predicted.

4. The method according to claim 1, characterized in that The obtaining the final predicted energy consumption of the current vehicle according to the target energy consumption prediction benchmark includes: Obtaining an average idle energy consumption value of the current vehicle; Calculating the driving energy consumption of the current vehicle based on the target energy consumption prediction benchmark; Calculating the air conditioning system energy consumption and the low-pressure system energy consumption of the current vehicle; The final predicted energy consumption is obtained according to the average idle energy consumption, the driving energy consumption, the air conditioning system energy consumption and the low-pressure system energy consumption.

5. The method according to claim 4, characterized in that The calculating the current driving energy consumption of the vehicle based on the target energy consumption prediction benchmark includes: Calculating the predicted energy consumption of the target energy consumption prediction benchmark; Acquire the current temperature from the real-time environmental data, and obtain a predicted energy consumption correction coefficient based on a preset multi-dimensional lookup table MAP according to an intensity factor corresponding to the vehicle speed curve and the current temperature; The driving energy consumption of the current vehicle is obtained according to the predicted energy consumption of the target energy consumption prediction benchmark and the predicted energy consumption correction coefficient.

6. The method according to claim 5, characterized in that Before obtaining the predicted energy consumption correction coefficient according to the intensity factor corresponding to the vehicle speed curve and the current temperature based on the preset multi-dimensional lookup table MAP, the method further includes: Calculate the intensity factors for different working conditions; Based on the same intensity factor, the ratio of the vehicle non-idle driving energy consumption under different combined temperatures to the vehicle non-idle driving energy consumption under a preset temperature is calculated; based on a preset multidimensional linear surface fitting algorithm, the preset multidimensional lookup table MAP is obtained according to the intensity factors of the different operating conditions, the temperatures corresponding to the intensity factors of the different operating conditions, and the ratio of the vehicle non-idle driving energy consumption under different combined temperatures corresponding to the intensity factors of the different operating conditions to the vehicle non-idle driving energy consumption under a preset temperature.

7. A vehicle travel energy consumption prediction device, characterized in that: include: An acquisition module is used to acquire real-time road data and real-time environmental data of the current vehicle; A calculation module, used to generate a speed curve of the current vehicle according to the real-time road data and the real-time environment data, and calculate an intensity factor corresponding to the speed curve; The prediction module is used to input the intensity factor corresponding to the vehicle speed curve into a preset energy consumption prediction benchmark decision model to obtain a target energy consumption prediction benchmark, and obtain the final predicted energy consumption of the current vehicle based on the target energy consumption prediction benchmark.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the vehicle travel energy consumption prediction method as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the vehicle travel energy consumption prediction method as described in any one of claims 1-6.

10. A computer program product, wherein the computer program product stores a computer program, characterized in that: When the program is executed by a processor, the vehicle travel energy consumption prediction method according to any one of claims 1 to 6 is implemented.

Images