A method and system for predicting the remaining range of an electric vehicle

Abstract

The application provides a kind of electric vehicle remaining range prediction method and system, belong to new energy vehicle technical field.The prediction method includes: obtaining the time series data of the driving habits of electric vehicle;According to the time series data of driving habits, extract driving habits features, obtain driving habits feature vector;According to driving habits feature vector, construct driving habits model;Comprehensive data acquisition, cleaning and calibration, obtain calibration data;According to the calibration data, calculate the basic driving energy consumption, auxiliary system energy consumption, battery management system energy consumption and motor efficiency loss, build energy consumption model;According to the remaining battery capacity, calculate the initial range, based on driving habits correction coefficient, battery capacity loss coefficient and road condition correction coefficient are modified in turn, predict the remaining range.The application solves the problem that the existing electric vehicle range prediction model is difficult to accurately consider the influence of vehicle parameters, battery performance and environmental factors, etc., resulting in false report of mileage.

Description

Technical Field

[0001] This invention belongs to the field of new energy vehicle technology, and specifically relates to a method and system for predicting the remaining driving range of electric vehicles. Background Technology

[0002] In the application of new energy electric vehicles, driving range is a crucial factor in determining whether a vehicle needs charging. The limitations of electric vehicle driving range and the uncertainty of charging infrastructure distribution have hindered the widespread adoption of electric vehicles. Therefore, accurately providing users with the driving range value of electric vehicles is essential.

[0003] With the development of intelligent connected vehicle technology, the technology for predicting the driving range of electric vehicles has also been significantly improved. Intelligent connected vehicles utilize onboard sensors, controllers, actuators, and communication devices to achieve functions such as environmental perception, intelligent decision-making, and automatic control. Against this backdrop, energy consumption optimization, real-time data acquisition and processing, battery performance and safety, and system reliability and stability have become key areas of research and application for electric vehicles. Research on battery system thermal management control strategies and energy consumption assessment is particularly important because battery performance and safety directly affect the driving range and lifespan of electric vehicles. Furthermore, the formula for calculating motor conversion efficiency losses is equally important for energy management, as motor efficiency directly impacts the overall vehicle energy consumption.

[0004] Existing electric vehicle range prediction models struggle to accurately account for the effects of vehicle parameters, battery performance, and environmental factors, leading to inaccurate range estimates and significant discrepancies between predicted and actual remaining range values. Summary of the Invention

[0005] Therefore, the present invention aims to provide a method and system for predicting the remaining driving range of electric vehicles, in order to solve at least one of the technical problems in the background art.

[0006] This invention is implemented as follows:

[0007] The first aspect of this invention provides a method for predicting the remaining driving range of an electric vehicle, comprising the following steps:

[0008] S1, acquire time-series data of the driving habits of the electric vehicle, including accelerator pedal depth, brake pedal depth, vehicle speed and steering angle;

[0009] S2, extract driving habit features based on the time series data of the driving habits to obtain a driving habit feature vector; the driving habit features include the rate of change of accelerator pedal depth, the rate of change of brake pedal depth, the rate of change of vehicle speed, and the rate of change of steering angle;

[0010] S3, Construct a driving habit model based on the driving habit feature vector;

[0011] S4. Comprehensive data collection, cleaning and calibration to obtain calibration data. The comprehensive data includes basic driving data, vehicle system data, battery status data, environmental condition data and navigation APP data.

[0012] S5. Calculate the basic driving energy consumption, auxiliary system energy consumption, battery management system energy consumption and motor efficiency loss based on the calibration data, and construct an energy consumption model.

[0013] The S6 calculates the initial driving range based on the remaining battery power, and then adjusts it sequentially based on driving habit correction coefficient, battery capacity loss coefficient, and road condition correction coefficient to predict the remaining driving range.

[0014] Furthermore, the prediction method also includes S7, dynamic updating and adjustment; the specific steps include:

[0015] As the electric vehicle moves, repeat steps S4 to S6 to update the remaining driving range prediction in real time.

[0016] If the predicted remaining driving range is lower than the safe threshold for the trip, suggestions will be provided to adjust the driving mode, adjust the driver assistance system, and plan the charging or battery swapping route.

[0017] Furthermore, the step of extracting driving habit features from the time-series data of the driving habits to obtain a driving habit feature vector specifically includes:

[0018] Calculate the average, maximum, and standard deviation of the accelerator pedal depth change rate to obtain the acceleration feature set;

[0019] Calculate the average, maximum, and standard deviation of the rate of change of brake pedal depth to obtain the brake feature set;

[0020] Calculate the average vehicle speed, vehicle speed standard deviation, and the proportion and frequency of speeding time in different driving stages to obtain the vehicle speed feature set;

[0021] The average, maximum and standard deviation of the rate of change of steering angle and the number of steering turns per unit distance are calculated to obtain the steering feature set;

[0022] The acceleration feature set, braking feature set, vehicle speed feature set, and steering feature set together form a driving habit feature vector.

[0023] Furthermore, the step of constructing a driving habit model based on the driving habit feature vector specifically includes:

[0024] The driving habit feature vector is standardized.

[0025] A driving habit model is obtained by training standardized driving habit feature vectors and corresponding driving habit classification labels using a decision tree algorithm.

[0026] Furthermore, the basic driving data includes vehicle speed, acceleration, and gradient;

[0027] The vehicle infotainment system data includes the vehicle's predicted mileage, driving mode identification, and power output.

[0028] The battery status data includes remaining power, battery voltage array, battery current, and battery temperature array;

[0029] The environmental condition data includes ambient temperature, humidity, air pressure, wind direction, wind speed, road slope, road curvature, and road surface material specifications.

[0030] The navigation app data includes congestion coefficient, traffic flow change rate, estimated travel time, and waiting time arrays for traffic lights along the route.

[0031] The cleaning and calibration process includes removing outliers and correcting errors in the integrated data acquisition equipment.

[0032] Furthermore, the steps of calculating the basic driving energy consumption, auxiliary system energy consumption, battery management system energy consumption, and motor efficiency loss based on the calibration data, and constructing an energy consumption model, specifically include:

[0033] The basic driving energy consumption is calculated based on the calibration data; the basic driving energy consumption includes air resistance energy consumption, rolling resistance energy consumption, climbing resistance energy consumption, and acceleration resistance energy consumption.

[0034] Calculate the energy consumption of the auxiliary system; the energy consumption of the auxiliary system includes air conditioning energy consumption and energy consumption of other auxiliary systems.

[0035] The energy consumption of the battery management system is calculated based on the remaining battery capacity, temperature distribution, charging and discharging current, and the characteristic coefficient of the battery management system.

[0036] The difference between the motor's input power and output power is calculated based on the motor's speed, torque, temperature, and efficiency characteristic curve to obtain the motor efficiency loss.

[0037] The total energy consumption is the sum of basic driving energy consumption, auxiliary system energy consumption, battery management system energy consumption, and motor efficiency loss.

[0038] The calculation formula is as follows:

[0039] Air resistance energy consumption

[0040] Rolling resistance energy consumption E 滚动 =μ 滚动 mgv;

[0041] Climbing resistance energy consumption E 爬坡 =mgsin(θ)v;

[0042] Acceleration resistance energy consumption

[0043] Air conditioning energy consumption E 空调 =P 空调 ×t 使用 ;

[0044] Energy consumption of other auxiliary systems

[0045] Battery Management System Energy Consumption E 电池管理 = f(SOC,T,I);

[0046] Motor efficiency loss E 电机损耗 =P 输入 -P 输出 ;

[0047] Total energy consumption E 总 =E 空气 +E 滚动 +E 爬坡 +E 加速 +E 空调 +E 其他 +E 电池管理 +E 电机损耗 ;

[0048] Where ρ is the air density; A is the vehicle's frontal area; C d μ is the drag coefficient; v is the real-time vehicle speed; μ 滚动 ρ is the tire rolling resistance coefficient; m is the vehicle curb weight; g is the acceleration due to gravity; θ is the road slope angle; a is the real-time vehicle acceleration; P 空调 For air conditioner power; t 使用 For air conditioning usage time; P i The power of system i; t 使用i The usage time of system i is denoted by SOC; the remaining battery capacity is denoted by T; the battery temperature is denoted by I; and the battery charging / discharging current is denoted by P. 输入 P is the input power to the motor. 输出 This refers to the output power of the motor.

[0049] Furthermore, the step of calculating the initial driving range based on the remaining battery power, and correcting the initial driving range according to the driving habit correction factor, battery capacity loss factor, and road condition correction factor, specifically includes:

[0050] The initial driving range is calculated based on the battery's current remaining charge and the rated capacity after considering battery degradation. The formula is: Initial Driving Range C 额定This refers to the battery's rated capacity.

[0051] Driving habit data is input into the driving habit model to obtain driving habit correction coefficients, which are then used to make the first correction to the initial driving range; the driving range R after the first correction is... 修正 =R 初始 × Driving habit correction factor;

[0052] Based on the battery capacity degradation factor determined by the ambient temperature, a second correction is made to the driving range after the first correction; the driving range R after the second correction. 温度修正 =R 修正 ×Battery capacity loss coefficient;

[0053] Based on road condition information, a road condition correction factor is calculated. The remaining driving range is then corrected a third time to obtain the predicted remaining driving range R. 最终 =R 温度修正 × Road condition correction factor.

[0054] A second aspect of the present invention provides a system for predicting the remaining driving range of an electric vehicle, which is used to perform the above-described method for predicting the remaining driving range of an electric vehicle, the prediction system comprising:

[0055] The driving habit information acquisition module is used to acquire time-series data of driving habits, including accelerator pedal depth, brake pedal depth, vehicle speed, and steering angle.

[0056] The extraction module is used to extract driving habit features based on the time series data of the driving habits to obtain a driving habit feature vector;

[0057] A driving habit model construction module is used to construct a driving habit model based on the driving habit feature vector.

[0058] The integrated data processing module is used to collect, clean, and calibrate integrated data to obtain calibration data. The integrated data includes basic driving data, vehicle system data, battery status data, environmental condition data, and navigation APP data.

[0059] The energy consumption model building module is used to calculate the basic driving energy consumption, auxiliary system energy consumption, battery management system energy consumption and motor efficiency loss based on the calibration data, and to build an energy consumption model.

[0060] The remaining driving range prediction module is used to calculate the initial driving range based on the remaining battery power, and then correct the initial driving range based on driving habit correction coefficient, battery capacity loss coefficient and road condition correction coefficient to predict the remaining driving range.

[0061] It also includes a dynamic update and adjustment module, which updates the predicted remaining driving range in real time. When the predicted remaining driving range is lower than the safety threshold for the trip, it provides suggestions for adjusting the driving mode, adjusting the assistance system, and planning charging or battery swapping routes.

[0062] A third aspect of the present invention provides a readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the steps of the above-described method for predicting the remaining driving range of an electric vehicle.

[0063] A fourth aspect of the present invention provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for predicting the remaining driving range of an electric vehicle as described above.

[0064] This invention provides a method and system for predicting the remaining driving range of electric vehicles, which solves the problem that existing electric vehicle driving range prediction models are difficult to accurately consider the influence of vehicle parameters, battery performance, and environmental factors, leading to false mileage reports.

[0065] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention collects multi-dimensional time-series data such as accelerator pedal, brake pedal, vehicle speed, and steering angle, and deeply extracts their rate of change characteristics to construct a comprehensive driving habit feature vector. Then, it uses a decision tree algorithm to train a driving habit model, which can accurately classify and identify different driving habits. This helps to correct the predicted driving range value based on driving habits, making the prediction results more consistent with the energy consumption in actual driving scenarios. It avoids false mileage reports caused by not considering differences in driving habits, and can more accurately reflect the energy consumption of the vehicle in actual driving. This provides a more reliable basis for driving range prediction and reduces mileage prediction errors caused by inaccurate energy consumption calculations. Attached Figure Description

[0066] Figure 1 This is a flowchart of the method for predicting the remaining driving range of an electric vehicle in Embodiment 1 of the present invention;

[0067] Figure 2 This is a schematic diagram of the structure of the electric vehicle remaining range prediction system in Embodiment 3 of the present invention. Detailed Implementation

[0068] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0069] Example 1

[0070] like Figure 1 The flowchart shown illustrates a method for predicting the remaining driving range of an electric vehicle, comprising steps S1 to S7.

[0071] S1 acquires time-series data on the driving habits of electric vehicles, including accelerator pedal depth, brake pedal depth, vehicle speed, and steering angle.

[0072] The accelerator pedal depth is D 加速 (t), which represents the depth of the accelerator pedal at time t;

[0073] Brake pedal depth: D 刹车 (t), which represents the depth of the brake pedal at time t;

[0074] The vehicle speed is v(t); it represents the vehicle speed at time t.

[0075] The turning angle is θ(t); it represents the turning angle at time t.

[0076] S2, extract driving habit features based on the time series data of the driving habits to obtain a driving habit feature vector; the driving habit features include the rate of change of accelerator pedal depth, the rate of change of brake pedal depth, the rate of change of vehicle speed, and the rate of change of steering angle.

[0077] Calculate the average, maximum, and standard deviation of the accelerator pedal depth change rate to obtain the acceleration feature set. The calculation formula is as follows:

[0078] Accelerator pedal depth change rate

[0079] Average rate of change of accelerator pedal depth

[0080] The maximum value of the rate of change of accelerator pedal depth α max =max(α(t) i ));

[0081] Standard deviation of the rate of change of accelerator pedal depth

[0082] In the formula, α(t) i ) represents time t i The rate of change of accelerator pedal depth.

[0083] Calculate the average, maximum, and standard deviation of the brake pedal depth change rate to obtain the brake feature set; the calculation formula is as follows:

[0084] Brake pedal depth change rate

[0085] Average value of brake pedal depth change rate

[0086] The maximum value of the rate of change of brake pedal depth β max =max(β(t) i ));

[0087] Standard deviation of brake pedal depth change rate

[0088] In the formula, β(t) i ) represents time t i The rate of change of brake pedal depth;

[0089] The average vehicle speed, standard deviation of vehicle speed, and proportion and frequency of speeding time are calculated for different driving stages to obtain the vehicle speed feature set; the calculation formula is as follows:

[0090] Rate of change of vehicle speed:

[0091] Average speed

[0092] Standard deviation of vehicle speed

[0093] Percentage of time spent speeding

[0094] Frequency of speeding

[0095] In the formula, v(t) i ) represents time t i The vehicle speed; t 超速 (t i ) represents a point in time (t) i Is it in an overspeeding state? (Boolean value, 1 indicates overspeeding, 0 indicates normal); N 超速 This represents the total number of speeding events within the statistical period; T represents the total time of the statistical period (in seconds).

[0096] The steering feature set is obtained by calculating the average, maximum, and standard deviation of the rate of change of steering angle, as well as the number of steering turns per unit distance traveled; the calculation formula is as follows:

[0097] Steering angle change rate:

[0098] Average value of the rate of change of steering angle

[0099] The maximum value of the rate of change of steering angle δ max =max(δ(t) i ));

[0100] Standard deviation of steering angle change rate

[0101] Number of turns per unit distance traveled

[0102] In the formula, δ(t) i ) represents the rate of change of the steering angle over time ti; N 转向 The number of steering wheel movements indicates the number of times the steering wheel has been turned; L indicates the distance traveled.

[0103] The acceleration feature set, braking feature set, vehicle speed feature set, and steering feature set together form a driving habit feature vector.

[0104] S3, Construct a driving habit model based on the driving habit feature vector;

[0105] The driving habit feature vector is standardized using the following formula:

[0106]

[0107] Among them, F 标准化 σ is the standardized driving habit feature vector; F is the original driving habit feature vector, μ is the mean of the driving habit feature vector, and σ is the standard deviation of the driving habit feature vector.

[0108] A driving habit model is obtained by training standardized driving habit feature vectors and corresponding driving habit classification labels using a decision tree algorithm.

[0109] S4 integrates data acquisition, cleaning, and calibration to obtain calibration data.

[0110] The comprehensive data includes basic driving data, vehicle system data, battery status data, environmental condition data, and navigation app data; the comprehensive data can be collected through sensors and communication devices.

[0111] Basic driving data includes vehicle speed, acceleration, and gradient, which can be measured in real time using vehicle speed sensors, acceleration sensors (gyroscopes or accelerometers), and gradient sensors.

[0112] The vehicle infotainment system data includes predicted mileage, driving mode indication, and power output; data is obtained from the BMS and energy management modules via the vehicle's CAN bus.

[0113] Battery status data includes remaining charge, battery voltage array, battery current, and battery temperature array; battery status is monitored by battery status sensors (including voltage, current, and temperature sensors, etc.).

[0114] Environmental condition data includes ambient temperature, humidity, air pressure, wind direction, wind speed, road slope, road curvature, and road surface material markings; environmental conditions during vehicle operation are collected through environmental sensors (temperature sensors, humidity sensors, vehicle-mounted air pressure sensors, vehicle-mounted meteorological sensors, inertial measurement units (IMU) combined with GPS elevation data, high-precision map data, or forward-looking cameras combined with lane line recognition algorithms, etc.).

[0115] Navigation app data includes congestion coefficients, traffic flow change rates, estimated travel time, and waiting times at traffic lights along the route; navigation app data is obtained through communication devices from external devices or other vehicle systems.

[0116] Cleaning and calibration include removing outliers and correcting errors in the integrated data acquisition equipment.

[0117] S5. Calculate the basic driving energy consumption, auxiliary system energy consumption, battery management system energy consumption and motor efficiency loss based on the calibration data, and construct an energy consumption model.

[0118] The basic driving energy consumption is calculated based on the calibration data; the basic driving energy consumption includes air resistance energy consumption, rolling resistance energy consumption, climbing resistance energy consumption, and acceleration resistance energy consumption.

[0119] Calculate the energy consumption of the auxiliary system; the energy consumption of the auxiliary system includes air conditioning energy consumption and energy consumption of other auxiliary systems.

[0120] The energy consumption of the battery management system is calculated based on the remaining battery capacity, temperature distribution, charging and discharging current, and the characteristic coefficient of the battery management system.

[0121] The difference between the motor's input power and output power is calculated based on the motor's speed, torque, temperature, and efficiency characteristic curve to obtain the motor efficiency loss.

[0122] The total energy consumption is the sum of basic driving energy consumption, auxiliary system energy consumption, battery management system energy consumption, and motor efficiency loss.

[0123] The calculation formula is as follows:

[0124] Air resistance energy consumption

[0125] Rolling resistance energy consumption E 滚动 =μ 滚动 mgv;

[0126] Climbing resistance energy consumption E 爬坡 =mgsin(θ)v;

[0127] Acceleration resistance energy consumption

[0128] Air conditioning energy consumption E空调 =P 空调 ×t 使用 ;

[0129] Energy consumption of other auxiliary systems

[0130] Battery Management System Energy Consumption E 电池管理 = f(SOC,T,I);

[0131] Motor efficiency loss E 电机损耗 =P 输入 -P 输出 ;

[0132] Total energy consumption E 总 =E 空气 +E 滚动 +E 爬坡 +E 加速 +E 空调 +E 其他 +E 电池管理 +E 电机损耗 ;

[0133] Where ρ is the air density; A is the vehicle's frontal area; C d μ is the drag coefficient; v is the real-time vehicle speed; μ 滚动 ρ is the tire rolling resistance coefficient; m is the vehicle curb weight; g is the acceleration due to gravity; θ is the road slope angle; a is the real-time vehicle acceleration; P 空调 For air conditioner power; t 使用 For air conditioning usage time; P i The power of system i; t 使用i The usage time of system i is denoted by SOC; the remaining battery capacity is denoted by T; the battery temperature is denoted by I; and the battery charging / discharging current is denoted by P. 输入 P is the input power to the motor. 输出 This refers to the output power of the motor.

[0134] The S6 calculates the initial driving range based on the remaining battery power, and then adjusts it sequentially based on driving habit correction coefficient, battery capacity loss coefficient, and road condition correction coefficient to predict the remaining driving range.

[0135] Specifically, the S61 calculates the initial driving range based on the current remaining battery power and the rated capacity after considering battery degradation. The calculation formula is: Initial Driving Range C 额定 This is the battery's rated capacity.

[0136] S62, input driving habit data into the driving habit model to obtain driving habit correction coefficients, and perform the first correction on the initial driving range; the driving range R after the first correction. 修正 =R 初始× Driving habit correction factor;

[0137] The classification results output by the driving habit model (trained by a decision tree algorithm) are combined with historical energy consumption data to map driving habit correction coefficients. The steps for obtaining these coefficients include:

[0138] Feature extraction: Extract statistical features (mean, maximum, standard deviation, etc.) from time-series data of driving habits (acceleration, braking, vehicle speed, steering) to form a driving habit feature vector;

[0139] Model training: The decision tree algorithm is used. The input is a standardized feature vector and driving habit classification label, such as "aggressive" or "mild". The model is trained to predict the driving habit category.

[0140] Coefficient mapping: Based on the correlation between driving habit type and energy consumption, correction coefficients are determined through experimental data or historical statistics; Aggressive driving (frequent rapid acceleration / sudden braking) → correction coefficient 0.8; Mild driving (smooth acceleration / deceleration) → correction coefficient 1.1;

[0141] Driving habit correction factor (k) 驾驶 This can be represented as:

[0142]

[0143] Where: E 基准 The average energy consumption is under standard driving mode, and the energy consumption is under the test conditions conducted by the Ministry of Industry and Information Technology.

[0144] E 驾驶习惯 : This represents the actual energy consumption corresponding to current driving habits, predicted through models or calculated in real time.

[0145] S63 determines the battery capacity degradation factor based on the ambient temperature and performs a second correction on the range after the first correction; the range after the second correction is R. 温度修正 =R 修正 × Battery capacity loss factor.

[0146] The battery capacity depreciation factor is obtained by comprehensively calculating based on battery temperature, aging degree (number of cycles), and current remaining charge (SOC).

[0147] Based on the effects of temperature and aging: battery capacity decreases as temperature decreases, and battery capacity decreases exponentially with increasing cycle number. This can be calculated using the State of Health (SOH) model, with a battery capacity loss coefficient k. 电池 The calculation formula is as follows:

[0148] k 电池 =f(T,SOH)=(1-α·ΔT)·(1-β·N 循环 );

[0149] Where: ΔT=∣T 环境 -T 最优 ∣(T 环境 The ambient temperature at which the battery operates; T 最优 α: Optimal battery operating temperature (e.g., 25℃); β: Temperature degradation coefficient (e.g., 0.005 / ℃); β: Aging degradation coefficient (e.g., 0.0001 / cycle); N 循环 The number of charge-discharge cycles the battery has completed.

[0150] S64, calculates the road condition correction factor based on road condition information, and then performs a third correction on the remaining driving range after the second correction to obtain the predicted remaining driving range value R. 最终 =R 温度修正 × Road condition correction factor.

[0151] Road condition correction factor k 路况 It can be represented as:

[0152] k 路况 =)1+w1·C 拥堵 +w2·sinθ+w3·μ 路面 0;

[0153] Among them, C 拥堵 θ is the congestion coefficient (0-1, 0 represents smooth traffic, 1 represents severe congestion); μ is the road slope angle (in radians); θ is the road gradient angle (in radians); μ is the road slope angle (in radians). 路面 The friction coefficient is 0.015 for asphalt roads and 0.03 for gravel roads; w1, w2, w3 are all weighting coefficients (calibrated experimentally and set to 0.2, 0.1, and 0.05 respectively).

[0154] S7, dynamic updates and adjustments; specific steps include:

[0155] As the electric vehicle moves, repeat steps S4 to S6 to update the remaining driving range prediction in real time.

[0156] If the predicted remaining driving range is lower than the safe threshold for the trip, suggestions will be provided to adjust the driving mode, adjust the driver assistance system, and plan the charging or battery swapping route.

[0157] This invention's prediction method collects multi-dimensional time-series data on accelerator pedal movement, brake pedal movement, vehicle speed, and steering angle, and deeply extracts their rate-of-change features to construct a comprehensive driving habit feature vector. Then, it uses a decision tree algorithm to train a driving habit model, enabling accurate classification and identification of different driving habits. This helps to subsequently adjust the predicted driving range based on driving habits, making the prediction results more consistent with energy consumption in actual driving scenarios and avoiding inaccurate mileage reporting due to failure to consider differences in driving habits.

[0158] The total energy consumption is calculated by comprehensively considering factors such as basic driving energy consumption, auxiliary system energy consumption (air conditioning and other auxiliary systems), battery management system energy consumption, and motor efficiency losses. Compared with traditional methods that only consider some energy consumption factors, this comprehensive energy consumption calculation method can more accurately reflect the energy consumption of the vehicle in actual driving, thus providing a more reliable basis for range prediction and reducing range prediction errors caused by inaccurate energy consumption calculations.

[0159] The initial driving range is adjusted multiple times based on battery SOC, driving habit correction factor, battery capacity degradation factor, and road condition correction factor. The battery capacity degradation factor reflects the actual capacity change of the battery with usage and environmental changes. The road condition correction factor adjusts the predicted value according to the impact of different road conditions on energy consumption. Combined with the driving habit correction factor, the overall impact of vehicle parameters, battery performance, and environmental factors on driving range is fully considered. This multi-factor correction mechanism can effectively improve the accuracy of driving range prediction, avoid false mileage reporting, provide drivers with more realistic and reliable driving range information, enable them to better plan their trips, and reduce "range anxiety" and the risk of breakdowns due to misjudgment of driving range.

[0160] It can update the predicted driving range in real time, reflecting changes in actual conditions during vehicle operation, such as changes in driving habits, road conditions, and battery status fluctuations, all of which affect the driving range in real time. Furthermore, it provides adjustment suggestions when the predicted range falls below a safe threshold. This helps drivers take timely measures, such as adjusting driving modes or finding charging stations, further improving the safety and convenience of using electric vehicles and enhancing user confidence in electric vehicles.

[0161] Equipped with multiple sensor modules, such as sensors for the accelerator pedal, brake pedal, steering angle, battery status, and environment, as well as other auxiliary sensors, it can comprehensively collect vehicle operation-related data. The collected data undergoes cleaning, calibration, feature extraction, and model training. Various data and model parameters are stored, and the system interacts with external devices. This comprehensive data acquisition and processing architecture ensures the efficient operation of the entire prediction method and device, as well as the effective utilization of data, providing solid technical support for accurate driving range prediction.

[0162] Example 2

[0163] An electric vehicle is driving on a city road. The vehicle has traveled 120 kilometers, the current battery SOC is 60%, the ambient temperature is 5°C, and the vehicle is traveling at a speed of 50 km / h on a flat road. The remaining driving range is predicted using the prediction method of Example 1, and the specific steps include S1 to S7.

[0164] S1. Data Acquisition:

[0165] Accelerator pedal depth: D 加速 The data collected (t) shows that the driver's average pedal depth was 30% in the last 5 minutes;

[0166] Brake pedal depth: Data collected by D brake(t) shows that the average pedal depth over the past 5 minutes is 15%;

[0167] Vehicle speed: v(t) remains stable at 50 km / h;

[0168] Steering angle: θ(t) indicates how many small turns the vehicle made, with an average steering angle change rate of 2 degrees per minute.

[0169] S2. Feature Extraction:

[0170] Accelerator pedal depth change rate: The calculated rate of change is 0.5% / second.

[0171] Statistical parameter: mean Maximum value α max =1.0, standard deviation σ α =0.2.

[0172] Brake pedal depth change rate: The calculated rate of change is 0.3% / second.

[0173] Statistical parameter: mean Maximum value β max =0.8, standard deviation σ β =0.15.

[0174] Rate of change of vehicle speed: The calculated rate of change is 0 km / h / s.

[0175] Statistical parameter: average vehicle speed km / h, standard deviation of vehicle speed σ v = 5 km / h.

[0176] Steering angle change rate: The calculated rate of change is 2 degrees per minute.

[0177] Statistical parameter: mean degrees / minute, maximum value δ max = 5 degrees / minute, standard deviation σ δ = 1 degree / minute.

[0178] S3. Driving Habit Model Construction:

[0179] Eigenvector: F = [0.5, 1.0, 0.2, 0.3, 0.8, 0.15, 50, 5, 2, 5, 2, 5, 1].

[0180] Standardization processing: Standardize the feature vectors.

[0181] Decision tree algorithm: Use the decision tree algorithm to train the driving habit model, inputting standardized feature vectors and driving habit classification labels.

[0182] S4. Integrated Data Acquisition, Cleaning, and Calibration:

[0183] Basic driving data: vehicle speed, acceleration, gradient, etc.

[0184] Vehicle infotainment system data: vehicle predicted mileage, driving mode indication, and power output.

[0185] Battery status data: Remaining SOC is 60%, battery voltage array, battery current array, and battery temperature array.

[0186] Environmental conditions data: ambient temperature 5℃, humidity 60%, air pressure 101.3kPa, wind direction angle 0 degrees, wind speed 5km / h.

[0187] Navigation app data: Congestion coefficient 0.8, traffic flow change rate 0.05, estimated travel time 30 minutes, and waiting time array for traffic lights along the route.

[0188] Data cleaning and calibration: Remove outliers and correct errors in integrated data acquisition equipment.

[0189] S5. Energy Consumption Model Construction:

[0190] Basic driving energy consumption includes air resistance energy consumption, rolling resistance energy consumption, climbing resistance energy consumption, and acceleration resistance energy consumption, and its calculation formula is as follows:

[0191] Energy consumption due to air resistance:

[0192] Rolling resistance energy consumption: E 滚滚 =00.15×1500×9.81×50=1113.75Wh / km;

[0193] Energy consumption due to climbing resistance: E 爬坡 =0 (flat road);

[0194] Acceleration drag energy consumption:

[0195] Auxiliary system energy consumption includes air conditioning energy consumption and other auxiliary system energy consumption, and its calculation formula is as follows:

[0196] Air conditioning energy consumption: E空调 =6000 × 0.5 = 3000Wh (Air conditioner power is 6000W, usage time is 0.5 hours);

[0197] Energy consumption of other auxiliary systems: E 其他 =100×10=1000Wh (the total power of other systems is 100W).

[0198] Battery Management System Energy Consumption: E 电池管理 =0.02×70000=1400Wh (Battery management system characteristic coefficient is 0.02).

[0199] Motor efficiency loss: E 电机损耗 =20000-19000=1000Wh (motor input power is 20000W, output power is 19000W).

[0200] Total energy consumption: E 总 =193.75+1113.75+0+0+3000+1000+1400+1000=6717.5Wh / km.

[0201] S6. Estimated Remaining Driving Range:

[0202] Initial driving range:

[0203] Driving habit correction factor: 0.9.

[0204] Ambient temperature loss factor: 0.8.

[0205] Road condition correction factor: 1.1.

[0206] Final driving range: R 最终 =64.4×0.9×0.8×1.1=48.1km.

[0207] S7. Dynamic Updates and Adjustments:

[0208] Real-time updates: As the vehicle travels, repeat steps S4 to S6 to update the predicted remaining driving range in real time.

[0209] Safety threshold assessment: If the predicted remaining driving range is lower than the safety threshold for the trip, set at 50 kilometers, suggestions for adjusting the driving mode, adjusting the assistance system, and planning the charging or battery swapping route will be provided.

[0210] The predicted and actual remaining driving range values ​​in Example 2 are compared, and the results are shown in Table 1.

[0211] Table 1

[0212]

[0213] Example 3

[0214] like Figure 2 As shown, this embodiment provides a prediction system for the remaining driving range of an electric vehicle, the prediction system comprising:

[0215] The driving habit information acquisition module 100 is used to acquire time-series data of driving habits, including accelerator pedal depth, brake pedal depth, vehicle speed, and steering angle. In specific implementations, these can be acquired through sensors, such as an accelerator pedal sensor to detect the accelerator pedal depth; a brake pedal sensor to detect the brake pedal depth; a vehicle speed sensor to measure the vehicle speed in real time; and a steering angle sensor to measure the steering wheel angle.

[0216] The extraction module 200 is used to extract driving habit features based on the time series data of the driving habits to obtain a driving habit feature vector; for example, extracting driving habit features such as the rate of change of accelerator pedal depth, the rate of change of brake pedal depth, the rate of change of vehicle speed, and the rate of change of steering angle, and then forming a driving habit feature vector.

[0217] The driving habit model construction module 300 is used to construct a driving habit model based on the driving habit feature vector; and to train the model using the extracted feature vector and other data through a decision tree algorithm to achieve the classification of driving habits and the analysis and calculation of energy consumption and other related information.

[0218] The integrated data processing module 400 is used to collect, clean, and calibrate integrated data to obtain calibration data. The integrated data includes basic driving data, vehicle system data, battery status data, environmental condition data, and navigation app data. Basic driving data includes vehicle speed, acceleration, and gradient. Vehicle system data includes predicted mileage, driving mode indicator, and power output. Battery status data includes remaining state of charge (SOC), battery voltage, battery current, and battery temperature. Environmental condition data includes ambient temperature, humidity, air pressure, wind direction, wind speed, road gradient, road curvature, and road surface material. Navigation app data includes congestion coefficient, traffic flow rate change rate, estimated travel time, and traffic light waiting time arrays. Data cleaning removes outliers and corrects errors in the integrated data acquisition equipment.

[0219] The energy consumption model building module 500 is used to calculate the basic driving energy consumption, auxiliary system energy consumption, battery management system energy consumption and motor efficiency loss based on the calibration data, and to build an energy consumption model.

[0220] The remaining driving range prediction module 600 is used to calculate the initial driving range based on the remaining battery power, and then make corrections based on driving habit correction coefficient, battery capacity loss coefficient and road condition correction coefficient to predict the remaining driving range.

[0221] The dynamic update and adjustment module 700 is used to update the predicted remaining driving range in real time. When the predicted remaining driving range is lower than the safe threshold for travel needs, it provides suggestions for adjusting the driving mode, adjusting the assistance system, and planning charging or battery swapping routes.

[0222] Example 4

[0223] This embodiment provides a readable storage medium on which a computer program is stored, which, when executed by a processor, implements the steps of the method for predicting the remaining driving range of an electric vehicle in Embodiment 1.

[0224] Example 5

[0225] This embodiment provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the method for predicting the remaining driving range of an electric vehicle in Embodiment 1.

[0226] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0227] Those skilled in the art will understand that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequential list of executable instructions for implementing logical functions, and can be embodied in any computer-readable storage medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable storage medium" can mean any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0228] More specific examples (a non-exhaustive list) of computer-readable storage media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable storage media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0229] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0230] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0231] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

Claims

1. A method for predicting the remaining driving range of an electric vehicle, characterized in that, The prediction method includes the following steps: S1, acquire time-series data of the driving habits of the electric vehicle, including accelerator pedal depth, brake pedal depth, vehicle speed and steering angle; S2, extract driving habit features based on the time series data of the driving habits to obtain a driving habit feature vector; the driving habit features include the rate of change of accelerator pedal depth, the rate of change of brake pedal depth, the rate of change of vehicle speed, and the rate of change of steering angle; S3, Construct a driving habit model based on the driving habit feature vector; S4. Comprehensive data collection, cleaning and calibration to obtain calibration data. The comprehensive data includes basic driving data, vehicle system data, battery status data, environmental condition data and navigation APP data. The basic driving data includes vehicle speed, acceleration, and gradient; the vehicle system data includes predicted mileage, driving mode identification, and power output; the battery status data includes remaining charge, battery voltage, battery current, and battery temperature; the environmental condition data includes ambient temperature, humidity, air pressure, wind direction, wind speed, road gradient, road curvature, and road surface material; the navigation app data includes congestion coefficient, traffic flow rate change rate, estimated travel time, and traffic light waiting time arrays; the cleaning and calibration process includes removing outliers and correcting errors in the integrated data acquisition equipment. S5. Calculate the basic driving energy consumption, auxiliary system energy consumption, battery management system energy consumption and motor efficiency loss based on the calibration data, and construct an energy consumption model. S6 calculates the initial driving range based on the remaining battery power, and then adjusts it according to driving habit correction coefficient, battery capacity loss coefficient and road condition correction coefficient to predict the remaining driving range. S2 specifically includes: Calculate the average, maximum, and standard deviation of the accelerator pedal depth change rate to obtain the acceleration feature set; Calculate the average, maximum, and standard deviation of the rate of change of brake pedal depth to obtain the brake feature set; Calculate the average vehicle speed, vehicle speed standard deviation, and the proportion and frequency of speeding time in different driving stages to obtain the vehicle speed feature set; The average, maximum and standard deviation of the rate of change of steering angle and the number of steering turns per unit distance are calculated to obtain the steering feature set; The acceleration feature set, braking feature set, vehicle speed feature set, and steering feature set constitute a driving habit feature vector; S5 specifically includes: The basic driving energy consumption is calculated based on the calibration data; the basic driving energy consumption includes air resistance energy consumption, rolling resistance energy consumption, climbing resistance energy consumption, and acceleration resistance energy consumption. Calculate the energy consumption of the auxiliary system; the energy consumption of the auxiliary system includes air conditioning energy consumption and energy consumption of other auxiliary systems. The energy consumption of the battery management system is calculated based on the remaining battery capacity, temperature distribution, charging and discharging current, and the characteristic coefficient of the battery management system. The difference between the motor's input power and output power is calculated based on the motor's speed, torque, temperature, and efficiency characteristic curve to obtain the motor efficiency loss. The total energy consumption is the sum of basic driving energy consumption, auxiliary system energy consumption, battery management system energy consumption, and motor efficiency loss. The calculation formula is as follows: Air resistance energy consumption ; Rolling resistance energy consumption ; Climbing resistance energy consumption ; Acceleration resistance energy consumption ; Air conditioning energy consumption ; Energy consumption of other auxiliary systems ; Battery Management System Energy Consumption ; Motor efficiency loss ; Total energy consumption ; in, air density; The vehicle's frontal area; This refers to the drag coefficient; Real-time vehicle speed; This refers to the tire rolling resistance coefficient. For vehicle curb weight; It is the acceleration due to gravity; The road slope angle; Real-time acceleration for vehicles; This refers to the air conditioner's power rating. This refers to the air conditioning usage time. Let i be the power of system i; The usage time of system i; Remaining battery level; Battery temperature; The charging and discharging current of the battery; Input power to the motor; This refers to the output power of the motor.

2. The method for predicting the remaining driving range of an electric vehicle according to claim 1, characterized in that, The prediction method also includes S7, dynamic updating and adjustment; specific steps include: As the electric vehicle moves, repeat steps S4 to S6 to update the remaining driving range prediction in real time. If the predicted remaining driving range is lower than the safe threshold for the trip, suggestions will be provided to adjust the driving mode, adjust the driver assistance system, and plan the charging or battery swapping route.

3. The method for predicting the remaining driving range of an electric vehicle according to claim 1, characterized in that, The step of constructing a driving habit model based on the driving habit feature vector specifically includes: The driving habit feature vector is standardized. A driving habit model is obtained by training standardized driving habit feature vectors and corresponding driving habit classification labels using a decision tree algorithm.

4. The method for predicting the remaining driving range of an electric vehicle according to claim 1, characterized in that, The steps of calculating the initial driving range based on the remaining battery power, and correcting the initial driving range according to driving habit correction coefficient, battery capacity loss coefficient, and road condition correction coefficient, specifically include: The initial driving range is calculated based on the battery's current remaining charge and the rated capacity after considering battery degradation. The formula is: Initial Driving Range , This refers to the battery's rated capacity. Driving habit data is input into the driving habit model to obtain driving habit correction coefficients, which are then used to make the first correction to the initial driving range; the driving range after the first correction... Driving habit correction factor Based on the battery capacity degradation factor determined by the ambient temperature, a second correction is made to the driving range after the first correction; the driving range after the second correction... Battery capacity loss factor; Based on road condition information, a road condition correction factor is calculated. The remaining driving range is then corrected a third time based on the second correction to obtain the predicted driving range. Road condition correction factor.

5. A system for predicting the remaining driving range of an electric vehicle, characterized in that, The prediction system is used to execute the method for predicting the remaining driving range of an electric vehicle as described in any one of claims 1 to 4, the prediction system comprising: The driving habit information acquisition module is used to acquire time-series data of driving habits, including accelerator pedal depth, brake pedal depth, vehicle speed, and steering angle. The extraction module is used to extract driving habit features based on the time series data of the driving habits to obtain a driving habit feature vector; A driving habit model construction module is used to construct a driving habit model based on the driving habit feature vector. The integrated data processing module is used to collect, clean, and calibrate integrated data to obtain calibration data. The integrated data includes basic driving data, vehicle system data, battery status data, environmental condition data, and navigation APP data. The energy consumption model building module is used to calculate the basic driving energy consumption, auxiliary system energy consumption, battery management system energy consumption and motor efficiency loss based on the calibration data, and to build an energy consumption model. The remaining driving range prediction module is used to calculate the initial driving range based on the remaining battery power, and then correct the initial driving range based on driving habit correction coefficient, battery capacity loss coefficient and road condition correction coefficient to predict the remaining driving range. It also includes a dynamic update and adjustment module, which updates the predicted remaining driving range in real time. When the predicted remaining driving range is lower than the safety threshold for the trip, it provides suggestions for adjusting the driving mode, adjusting the assistance system, and planning charging or battery swapping routes.

6. A readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for predicting the remaining driving range of an electric vehicle as described in any one of claims 1 to 4.

7. An electronic device, characterized in that, The device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of a method for predicting the remaining driving range of an electric vehicle as described in any one of claims 1 to 4.

Images