Method and system for predicting remaining endurance mileage of electric vehicle

Abstract

The invention provides a method and system for predicting the remaining endurance mileage of an electric vehicle, and belongs to the technical field of new energy vehicles. The prediction method comprises the following steps: acquiring time sequence data of a driving habit of the electric vehicle; driving habit features are extracted according to the time sequence data of the driving habits, and driving habit feature vectors are obtained; constructing a driving habit model according to the driving habit feature vector; integrating data acquisition, cleaning and calibration to obtain calibration data; calculating basic driving energy consumption, auxiliary system energy consumption, battery management system energy consumption and motor efficiency loss according to the calibration data, and constructing an energy consumption model; and calculating an initial endurance mileage according to the battery remaining capacity, sequentially correcting based on the driving habit correction coefficient, the battery capacity loss coefficient and the road condition correction coefficient, and predicting the remaining endurance mileage. The method solves the problem of mileage false report and the like caused by the fact that an existing electric vehicle endurance mileage prediction model is difficult to accurately consider the influences of vehicle parameters, battery performance, environmental factors and the like.

Description

Technical Field

[0001] The present invention belongs to the technical field of new energy vehicles, and in particular relates to a method and system for predicting the remaining cruising range of an electric vehicle. Background Art

[0002] In the application process of new energy electric vehicles, the cruising range is an important basis for judging whether the vehicle needs to be charged. Due to the limitation of the cruising range of electric vehicles and the uncertainty of the distribution of charging facilities, the promotion of electric vehicles is affected. Therefore, how to accurately feedback the cruising range value of electric vehicles to users is

[0003] With the development of intelligent networked vehicle technology, the range prediction technology of electric vehicles has also been significantly improved; intelligent networked vehicles use on-board sensors, controllers, actuators and communication devices to achieve environmental perception, intelligent decision-making and automatic control functions; in this context, energy consumption optimization, real-time data acquisition and processing, battery performance and safety, system reliability and stability of electric vehicles have become key areas of research and application; battery system thermal management control strategy and energy consumption evaluation research is particularly important, because battery performance and safety are directly related to the range and service life of electric vehicles. In addition, the motor conversion efficiency loss calculation formula is also important for energy consumption management, because motor efficiency directly affects the energy consumption of the entire vehicle.

[0004] Existing electric vehicle range prediction models find it difficult to accurately consider the impact of vehicle parameters, battery performance, and environmental factors, resulting in false mileage reporting, which causes the predicted value of the remaining range to be far from the actual value. Summary of the invention

[0005] In view of this, an object of the present invention is to provide a method and system for predicting the remaining cruising range of an electric vehicle, aiming to solve at least one technical problem in the background technology.

[0006] The present invention is achieved in that:

[0007] A first aspect of the present invention provides a method for predicting the remaining cruising range of an electric vehicle, comprising the following steps:

[0008] S1, obtaining time series data of driving habits of the electric vehicle, wherein the driving habits include accelerator pedal depression depth, brake pedal depression depth, vehicle speed and steering angle;

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

[0010] S3, constructing a driving habit model according to 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, navigation APP data;

[0012] S5, calculating basic driving energy consumption, auxiliary system energy consumption, battery management system energy consumption and motor efficiency loss according to the calibration data, and constructing an energy consumption model;

[0013] S6, calculating the initial cruising range according to the remaining battery power, and making corrections based on the driving habit correction factor, the battery capacity depreciation factor and the road condition correction factor in sequence to predict the remaining cruising range.

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

[0015] As the electric vehicle travels, steps S4 to S6 are repeated to update the remaining cruising range prediction value in real time;

[0016] If the predicted remaining range is lower than the safety threshold of the trip requirements, suggestions for adjusting the driving mode, adjusting the auxiliary system, and planning the charging or battery replacement route are provided.

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

[0018] Calculate the average value, maximum value 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 brake pedal depth change rate to obtain a brake feature set;

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

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

[0022] The acceleration feature set, the braking feature set, the vehicle speed feature set, and the steering feature set constitute 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] Performing standardization on the driving habit feature vector;

[0025] The decision tree algorithm is used to train the standardized driving habit feature vector and the corresponding driving habit classification label to obtain the driving habit model.

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

[0027] The vehicle system data includes the vehicle predicted mileage, driving mode identification and power output power;

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

[0029] The environmental condition data includes external environment temperature, humidity, air pressure, wind direction angle, wind speed, road slope, road curvature and road surface material identification;

[0030] The navigation APP data includes an array of congestion coefficient, traffic flow change rate, estimated travel time, and waiting time for traffic lights along the way;

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

[0032] Furthermore, the step of calculating the basic driving energy consumption, auxiliary system energy consumption, battery management system energy consumption and motor efficiency loss according to the calibration data and constructing an energy consumption model specifically includes:

[0033] Calculate basic driving energy consumption based on calibration data; basic driving energy consumption includes air resistance energy consumption, rolling resistance energy consumption, climbing resistance energy consumption, and acceleration resistance energy consumption;

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

[0035] Calculate the energy consumption of the battery management system based on the remaining battery power, temperature distribution, charge and discharge current, and battery management system characteristic coefficient;

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

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

[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] Other auxiliary system energy consumption

[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 frontal area of ​​the vehicle; C d is the drag coefficient; v is the real-time vehicle speed; μ 滚动 is the tire rolling resistance coefficient; m is the vehicle curb mass; g is the acceleration of gravity; θ is the road slope angle; a is the vehicle real-time acceleration; P 空调 is the air conditioning power; t 使用 P is the air conditioning usage time; i is the power of system i; t 使用i is the usage time of system i; SOC is the remaining power; T is the battery temperature; I is the battery charge and discharge current; P 输入 is the motor input power; P 输出 Output power for the motor.

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

[0050] The initial cruising range is calculated based on the current remaining battery power and the rated capacity after considering battery loss. The calculation formula is: Initial cruising range C 额定is the rated capacity of the battery;

[0051] The driving habit data is input into the driving habit model to obtain the driving habit correction coefficient, and the initial cruising range is corrected for the first time; the cruising range after the first correction R 修正 =R 初始 × Driving habit correction factor;

[0052] Determine the battery capacity depreciation coefficient according to the external ambient temperature, and make a second correction to the cruising range after the first correction; the cruising range R after the second correction 温度修正 =R 修正 ×Battery capacity loss factor;

[0053] Calculate the road condition correction coefficient based on the road condition information, make a third correction to the cruising range after the second correction, and get the remaining cruising range prediction value 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 cruising range of an electric vehicle, which is used to execute the above-mentioned method for predicting the remaining cruising range of an electric vehicle, and the prediction system comprises:

[0055] A driving habit information acquisition module, used to acquire time series data of driving habits, wherein the driving habits include accelerator pedal stepping depth, brake pedal stepping depth, vehicle speed and steering angle;

[0056] An extraction module, used for extracting driving habit features according to the time series data of the driving habit to obtain a driving habit feature vector;

[0057] A driving habit model building module, used to build a driving habit model according to the driving habit feature vector;

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

[0059] An energy consumption model building module, used to calculate basic driving energy consumption, auxiliary system energy consumption, battery management system energy consumption and motor efficiency loss according to the calibration data, and build an energy consumption model;

[0060] The remaining cruising range prediction module is used to calculate the initial cruising range according to the remaining battery power, and then correct the initial cruising range based on the driving habit correction factor, battery capacity depreciation factor and road condition correction factor to predict the remaining cruising range;

[0061] It also includes a dynamic update and adjustment module, which is used to update the remaining mileage prediction value in real time. When the remaining mileage prediction value is lower than the safety threshold of the trip requirements, it provides suggestions for adjusting the driving mode, auxiliary system adjustment, and charging or battery replacement route planning.

[0062] A third aspect of the present invention provides a readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of a method for predicting the remaining cruising range of an electric vehicle as described above are implemented.

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

[0064] The present invention provides a method and system for predicting the remaining cruising range of an electric vehicle, which solves the problem that the electric vehicle cruising range prediction model in the prior art is difficult to accurately consider the influence of vehicle parameters, battery performance, and environmental factors, resulting in false mileage reporting and other problems.

[0065] Compared with the prior art, the beneficial effect of the present invention lies in: the present invention collects multi-dimensional time series data of the accelerator pedal, brake pedal, vehicle speed, steering angle, etc., and deeply extracts its change rate characteristics, constructs a comprehensive driving habit feature vector, and then uses the decision tree algorithm to train the driving habit model. It can accurately classify and identify different driving habits, which is helpful for subsequent correction of the cruising range prediction value according to driving habits, so that the prediction result is more in line with the energy consumption in the actual driving scenario, avoids the false reporting of mileage due to failure to consider the differences in driving habits, and can more accurately reflect the energy consumption of the vehicle in actual driving, thereby providing a more reliable basis for cruising range prediction and reducing the mileage prediction error caused by inaccurate energy consumption calculation. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0067] Figure 2 Schematic diagram of the structure of the system for predicting the remaining cruising range of an electric vehicle in Example 3 of the present invention. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific implementation cases described herein are only used to explain the present invention and are not used to limit the present invention.

[0069] Example 1

[0070] like Figure 1 As shown in the flowchart, this embodiment provides a method for predicting the remaining cruising range of an electric vehicle, and the steps of the prediction method include S1 to S7.

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

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

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

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

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

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

[0077] The average value, maximum value and standard deviation of the accelerator pedal depth change rate are calculated to obtain the acceleration feature set, which is calculated as follows:

[0078] Accelerator pedal depth change rate

[0079] Average value of accelerator pedal depth change rate

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

[0081] Standard deviation of accelerator pedal depth change rate

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

[0083] The average value, maximum value and standard deviation of the brake pedal depth change rate are calculated 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] Maximum value of brake pedal depth change rate β max =max(β(t i ));

[0087] Standard deviation of brake pedal depth change rate

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

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

[0090] Vehicle speed change rate:

[0091] Average speed

[0092] Speed ​​standard deviation

[0093] Speeding time ratio

[0094] Speeding frequency

[0095] In the formula, v(t i ) represents the time t i The vehicle speed; t 超速 (t i ) represents the time point (t i ) Whether it is in overspeed state (Boolean value, 1 means overspeed, 0 means normal); N 超速 It indicates the total number of speeding events in the statistical period; T indicates the total time of the statistical period (unit: second).

[0096] The average value, maximum value and standard deviation of the steering angle change rate and the number of turns per unit mileage are calculated to obtain the steering feature set; the calculation formula is as follows:

[0097] Steering angle change rate:

[0098] The average value of the steering angle change rate

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

[0100] Standard deviation of steering angle change rate

[0101] Number of turns per unit mileage

[0102] In the formula, δ(t i ) represents the rate of change of the steering angle at time ti; N 转向 Indicates the number of steering wheel movements; L indicates the mileage.

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

[0104] S3, constructing a driving habit model according to the driving habit feature vector;

[0105] The driving habit feature vector is standardized, and the standardized processing formula is as follows:

[0106]

[0107] Among them, F 标准化 is the driving habit feature vector after standardized processing; 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] The decision tree algorithm is used to train the standardized driving habit feature vector and the corresponding driving habit classification label to obtain the driving habit model.

[0109] S4, comprehensive data collection, cleaning and calibration to obtain calibration data.

[0110] Comprehensive data includes basic driving data, vehicle system data, battery status data, environmental condition data, and navigation APP data; comprehensive data can be collected through sensors and communication equipment.

[0111] Basic driving data includes vehicle speed, acceleration and slope, which can be measured in real time by vehicle speed sensor, acceleration sensor (gyroscope or accelerometer) and slope sensor;

[0112] The vehicle system data includes the vehicle predicted mileage, driving mode identification and power output power; data is obtained from the BMS and energy consumption management module through the vehicle CAN bus;

[0113] The battery status data includes the remaining power, battery voltage array, battery current and battery temperature array; the battery status is monitored by the battery status sensor (including voltage, current, temperature sensor, etc.);

[0114] Environmental condition data includes external ambient temperature, humidity, air pressure, wind direction angle, wind speed, road slope, road curvature and road surface material identification; environmental conditions during vehicle operation are collected through environmental sensors (temperature sensor, humidity sensor, vehicle-mounted air pressure sensor, vehicle-mounted meteorological sensor, inertial measurement unit (IMU) combined with GPS elevation data, high-precision map data or front-view camera combined with lane line recognition algorithm, etc.);

[0115] Navigation APP data includes congestion coefficient, traffic flow change rate, estimated travel time and waiting time of traffic lights along the way; navigation APP data is obtained through communication equipment from external devices or other vehicle systems;

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

[0117] S5, calculating basic driving energy consumption, auxiliary system energy consumption, battery management system energy consumption and motor efficiency loss according to the calibration data, and constructing an energy consumption model;

[0118] Calculate basic driving energy consumption based on calibration data; basic driving energy consumption includes air resistance energy consumption, rolling resistance energy consumption, climbing resistance energy consumption, and acceleration resistance energy consumption;

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

[0120] Calculate the energy consumption of the battery management system based on the remaining battery power, temperature distribution, charge and discharge current, and battery management system characteristic coefficient;

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

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

[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] Other auxiliary system energy consumption

[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 frontal area of ​​the vehicle; C d is the drag coefficient; v is the real-time vehicle speed; μ 滚动 is the tire rolling resistance coefficient; m is the vehicle curb mass; g is the acceleration of gravity; θ is the road slope angle; a is the vehicle real-time acceleration; P 空调 is the air conditioning power; t 使用 P is the air conditioning usage time; i is the power of system i; t 使用i is the usage time of system i; SOC is the remaining power; T is the battery temperature; I is the battery charge and discharge current; P 输入 is the motor input power; P 输出 Output power for the motor.

[0134] S6, calculating the initial cruising range according to the remaining battery power, and making corrections based on the driving habit correction factor, the battery capacity depreciation factor and the road condition correction factor in sequence to predict the remaining cruising range.

[0135] Specifically, in S61, the initial cruising range is calculated based on the current remaining power of the battery and the rated capacity after considering the battery loss. The calculation formula is: Initial cruising range C 额定 is the rated capacity of the battery.

[0136] S62, input the driving habit data into the driving habit model, obtain the driving habit correction coefficient, and make a first correction to the initial cruising range; the cruising range after the first correction R 修正 =R 初始× Driving habit correction factor;

[0137] Among them, the classification results are output through the driving habit model (decision tree algorithm training), and the historical energy consumption data is mapped into the driving habit correction coefficient. The acquisition method and steps include:

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

[0139] Model training: Using a decision tree algorithm, we input the standardized feature vector and driving habit classification labels, such as "aggressive" and "gentle", and train the model to predict the driving habit category;

[0140] Coefficient mapping: According to the correlation between driving habit category and energy consumption, the correction coefficient is determined through experimental data or historical statistics; aggressive driving (frequent sudden acceleration / sudden braking) → correction coefficient 0.8; gentle driving (smooth acceleration / deceleration) → correction coefficient 1.1;

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

[0142]

[0143] Where: E 基准 is the average energy consumption in standard driving mode and the energy consumption under the test conditions of the Ministry of Industry and Information Technology;

[0144] E 驾驶习惯 :The actual energy consumption corresponding to the current driving habits, predicted by the model or calculated in real time.

[0145] S63, determining the battery capacity depreciation coefficient according to the external environment temperature, and making a second correction to the cruising range after the first correction; the cruising range R after the second correction 温度修正 =R 修正 ×Battery capacity degradation factor.

[0146] The battery capacity depreciation coefficient is obtained by comprehensive calculation based on battery temperature, aging degree (number of cycles) and current remaining power (SOC).

[0147] Based on the influence of temperature and aging: the battery capacity decays as the temperature decreases, and the battery capacity decays exponentially with the increase of the number of cycles. It can be calculated by the battery health state SOH model, and the battery capacity depreciation 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 of the battery; T 最优 is the optimal operating temperature of the battery, such as 25°C); α: temperature attenuation coefficient (such as 0.005 / °C); β: aging attenuation coefficient (such as 0.0001 / time); N 循环 : The number of charge and discharge cycles the battery has completed.

[0150] S64, calculating the road condition correction coefficient based on the road condition information, and performing a third correction on the cruising range after the second correction to obtain a remaining cruising range prediction value R 最终 =R 温度修正 ×Road condition correction factor.

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

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

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

[0154] S7, dynamic update and adjustment; the specific steps include:

[0155] As the electric vehicle travels, steps S4 to S6 are repeated to update the remaining cruising range prediction value in real time;

[0156] If the predicted remaining range is lower than the safety threshold of the trip requirements, suggestions for adjusting the driving mode, adjusting the auxiliary system, and planning the charging or battery replacement route are provided.

[0157] The prediction method of the present invention collects multi-dimensional time series data such as the accelerator pedal, brake pedal, vehicle speed, steering angle, etc., and deeply extracts its change rate characteristics to construct a comprehensive driving habit feature vector, and then uses the decision tree algorithm to train the driving habit model, which can accurately classify and identify different driving habits. This helps to correct the range prediction value according to driving habits in the future, so that the prediction results are more in line with the energy consumption in the actual driving scene, and avoids mileage false reporting due to failure to consider differences in driving habits.

[0158] The total energy consumption is calculated by comprehensively considering multiple 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 loss. Compared with the traditional method that only considers some energy consumption factors, this comprehensive energy consumption calculation method can more accurately reflect the energy consumption of the vehicle in actual driving, thereby providing a more reliable basis for mileage prediction and reducing mileage prediction errors caused by inaccurate energy consumption calculations.

[0159] The initial cruising range is corrected multiple times based on the battery SOC, driving habit correction factor, battery capacity depreciation factor and road condition correction factor. The battery capacity depreciation factor can reflect the actual capacity change of the battery with use and environmental changes. The road condition correction factor can adjust the predicted value according to the impact of different road conditions on energy consumption. Combined with the driving habit correction factor, it fully considers the comprehensive impact of vehicle parameters, battery performance and environmental factors on cruising range. Such a multi-factor correction mechanism can effectively improve the accuracy of cruising range prediction, avoid mileage false reporting, and provide drivers with more real and reliable cruising range information, so that they can better plan their trips and reduce "mileage anxiety" and possible risks of breaking down halfway due to misjudgment of cruising range.

[0160] It can update the predicted range in real time, reflecting the actual changes in the vehicle during driving, such as the real-time impact of driving habits, road conditions, battery status fluctuations, etc. on the range. It also provides adjustment suggestions when the predicted value is lower than the safety threshold, which helps the driver take timely measures, such as adjusting the driving mode, finding charging piles, etc., further improving the safety and convenience of electric vehicle use and enhancing users' confidence in the use of electric vehicles.

[0161] Equipped with a variety of sensor modules, such as accelerator pedal, brake pedal, steering angle, battery status, environment and other auxiliary sensors, it can comprehensively collect vehicle operation-related data; perform operations such as cleaning, calibration, feature extraction and model training on the collected data, store various data and model parameters, and interact with external devices. This complete data collection and processing architecture ensures the efficient operation of the entire prediction method and device and the effective use of data, providing solid technical support for accurate mileage prediction.

[0162] Example 2

[0163] An electric car is traveling on a city road. The vehicle has traveled 120 kilometers. The current battery SOC is 60%. The external ambient temperature is 5°C. The vehicle is traveling on a flat road at a speed of 50 kilometers per hour. The prediction method of Example 1 is used to predict the remaining cruising range. The specific steps include S1 to S7.

[0164] S1. Data collection:

[0165] Accelerator pedal depression depth: D 加速 (t) The collected data show that the average pedaling depth of the driver in the last 5 minutes is 30%;

[0166] Brake pedal depression depth: Dbrake (t) The data collected show that the average depression depth in the last 5 minutes is 15%;

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

[0168] Steering angle: θ(t) shows that the vehicle made several small turns 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 parameters: 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 parameters: Mean Maximum β max =0.8, standard deviation σ β =0.15.

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

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

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

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

[0178] S3. Driving habit model construction:

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

[0180] Standardization: Standardize the feature vector.

[0181] Decision Tree Algorithm: Use the decision tree algorithm to train the driving habit model, inputting the standardized feature vector and driving habit classification label.

[0182] S4. Comprehensive data collection, cleaning and calibration:

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

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

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

[0186] Environmental condition data: outside temperature 5°C, 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 of traffic lights along the way.

[0188] Data cleaning and calibration: Remove outliers and correct errors in comprehensive 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. The calculation formula is as follows:

[0191] Air resistance energy consumption:

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

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

[0194] Acceleration resistance 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 (the air conditioner power is 6000W and the usage time is 0.5 hours);

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

[0198] Battery management system energy consumption: E 电池管理 =0.02×70000=1400Wh (the 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. Remaining cruising range prediction:

[0202] Initial cruising range:

[0203] Driving habit correction factor: 0.9.

[0204] Ambient temperature loss coefficient: 0.8.

[0205] Road condition correction factor: 1.1.

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

[0207] S7. Dynamic update and adjustment:

[0208] Real-time update: As the vehicle moves, steps S4 to S6 are repeated to update the remaining range prediction value in real time.

[0209] Safety threshold judgment: If the predicted remaining range is lower than the trip requirement safety threshold, which is set at 50 kilometers, suggestions for adjusting the driving mode, adjusting the auxiliary system, and planning the charging or battery replacement route are provided.

[0210] The predicted value of the remaining cruising range of this embodiment 2 is compared with the actual value, 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 cruising 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, wherein the driving habits include the accelerator pedal stepping depth, the brake pedal stepping depth, the vehicle speed and the steering angle, which can be acquired through sensors in specific implementations, such as the accelerator pedal sensor for detecting the accelerator pedal stepping depth; the brake pedal sensor for detecting the brake pedal stepping depth; the vehicle speed sensor for measuring the vehicle speed in real time; and the steering angle sensor for measuring the steering angle of the steering wheel;

[0216] An extraction module 200 is used to extract driving habit features according to the time series data of the driving habit to obtain a driving habit feature vector; for example, driving habit features such as an accelerator pedal depth change rate, a brake pedal depth change rate, a vehicle speed change rate, and a steering angle change rate are extracted to form a driving habit feature vector;

[0217] The driving habit model building module 300 is used to build a driving habit model according to the driving habit feature vector; using the extracted feature vector and other data, the model is trained through a decision tree algorithm to achieve classification of driving habits and analysis and calculation of related conditions such as energy consumption;

[0218] The comprehensive data processing module 400 is used to collect, clean and calibrate comprehensive data to obtain calibration data. The comprehensive data includes basic driving data, vehicle system data, battery status data, environmental condition data, and navigation APP data; basic driving data: vehicle speed, acceleration, slope, etc.; vehicle system data: vehicle predicted mileage, driving mode identification, power output power; battery status data: remaining power SOC, battery voltage array, battery current, battery temperature array; environmental condition data: outside temperature, humidity, air pressure, wind direction angle, wind speed, road slope, road curvature, road surface material identification; navigation APP data: congestion coefficient, traffic flow change rate, estimated travel time, and waiting time array of traffic lights along the way. Data cleaning: remove outliers and correct errors in the comprehensive data acquisition equipment;

[0219] An 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 according to the calibration data to build an energy consumption model;

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

[0221] Dynamic update and adjustment module 700 is used to update the remaining range prediction value in real time; when the remaining range prediction value is lower than the safety threshold of the travel demand, it provides driving mode adjustment suggestions, auxiliary system adjustment suggestions, and charging or battery replacement route planning suggestions

[0222] Example 4

[0223] This embodiment provides a readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for predicting the remaining cruising range of an electric vehicle in Embodiment 1 are implemented.

[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, the steps of a method for predicting the remaining cruising range of an electric vehicle in Embodiment 1 are implemented.

[0226] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, 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 appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be embodied in any computer-readable storage medium for use by an instruction execution system, device, or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device, or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices, or apparatuses. For purposes of this specification, a "computer-readable storage medium" may be any device that can contain, store, communicate, propagate, or transmit a program for use by an instruction execution system, device, or apparatus, or in conjunction with such instruction execution systems, devices, or apparatuses.

[0228] More specific examples of computer-readable storage media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable storage medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or processing in another suitable manner as necessary, and then stored in a computer memory.

[0229] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of 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, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0230] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0231] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for predicting the remaining cruising range of an electric vehicle, characterized in that: The prediction method comprises the following steps: S1, obtaining time series data of driving habits of the electric vehicle, wherein the driving habits include accelerator pedal depression depth, brake pedal depression depth, vehicle speed and steering angle; S2, extracting driving habit features according to the time series data of the driving habit to obtain a driving habit feature vector; the driving habit features include an accelerator pedal depth change rate, a brake pedal depth change rate, a vehicle speed change rate, and a steering angle change rate; S3, constructing a driving habit model according to 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, navigation APP data; S5, calculating basic driving energy consumption, auxiliary system energy consumption, battery management system energy consumption and motor efficiency loss according to the calibration data, and constructing an energy consumption model; S6, calculating the initial cruising range according to the remaining battery power, and making corrections based on the driving habit correction factor, the battery capacity depreciation factor and the road condition correction factor in sequence to predict the remaining cruising range.

2. The method for predicting the remaining cruising range of an electric vehicle according to claim 1, characterized in that: The prediction method further includes S7, dynamic updating and adjustment; the specific steps include: As the electric vehicle travels, steps S4 to S6 are repeated to update the remaining cruising range prediction value in real time; If the predicted remaining range is lower than the safety threshold of the trip requirements, suggestions for adjusting the driving mode, adjusting the auxiliary system, and planning the charging or battery replacement route are provided.

3. The method for predicting the remaining cruising range of an electric vehicle according to claim 1, characterized in that: The step of extracting driving habit features according to the time series data of the driving habit to obtain a driving habit feature vector specifically includes: Calculate the average value, maximum value 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 brake pedal depth change rate to obtain a brake feature set; Calculate the average vehicle speed, vehicle speed standard deviation, and speeding time ratio and frequency at different driving stages to obtain the vehicle speed feature set; The average value, maximum value and standard deviation of the steering angle change rate and the number of turns per unit mileage are calculated to obtain the steering feature set; The acceleration feature set, the braking feature set, the vehicle speed feature set, and the steering feature set constitute a driving habit feature vector.

4. The method for predicting the remaining cruising range of an electric vehicle according to claim 3, characterized in that: The step of constructing a driving habit model based on the driving habit feature vector specifically includes: Performing standardization on the driving habit feature vector; The decision tree algorithm is used to train the standardized driving habit feature vector and the corresponding driving habit classification label to obtain the driving habit model.

5. The method for predicting the remaining cruising range of an electric vehicle according to claim 1, characterized in that: The basic driving data includes vehicle speed, acceleration and slope; The vehicle system data includes the vehicle predicted mileage, driving mode identification and power output power; The battery status data includes remaining power, battery voltage array, battery current and battery temperature array; The environmental condition data includes external environment temperature, humidity, air pressure, wind direction angle, wind speed, road slope, road curvature and road surface material identification; The navigation APP data includes an array of congestion coefficient, traffic flow change rate, estimated travel time, and waiting time for traffic lights along the way; The cleaning and calibration includes removing outliers and correcting errors in the integrated data acquisition equipment.

6. A method for predicting the remaining cruising range of an electric vehicle according to claim 5, characterized in that: The steps of calculating the basic driving energy consumption, auxiliary system energy consumption, battery management system energy consumption and motor efficiency loss according to the calibration data and constructing an energy consumption model specifically include: Calculate basic driving energy consumption based on calibration data; basic driving energy consumption includes air resistance energy consumption, rolling resistance energy consumption, climbing resistance energy consumption, and acceleration resistance energy consumption; Calculate auxiliary system energy consumption; the auxiliary system energy consumption includes air conditioning energy consumption and other auxiliary system energy consumption; Calculate the energy consumption of the battery management system based on the remaining battery power, temperature distribution, charge and discharge current, and battery management system characteristic coefficient; The difference between the motor input power and the output power is calculated based on the motor speed, torque, motor temperature and motor efficiency characteristic curve to obtain the motor efficiency loss; The sum of basic driving energy consumption, auxiliary system energy consumption, battery management system energy consumption and motor efficiency loss is the total energy consumption; The calculation formula is as follows: Air resistance energy consumption Rolling resistance energy consumption E 滚动 =μ 滚动 mgv; Climbing resistance energy consumption E 爬坡 = mgsin(θ)v; Acceleration resistance energy consumption Air conditioning energy consumption E 空调 =P 空调 ×t 使用 ; Other auxiliary system energy consumption Battery management system energy consumption E 电池管理 =f(SOC,T,I); Motor efficiency loss E 电机损耗 =P 输入 -P 输出 ; 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 ; Where ρ is the air density; A is the frontal area of ​​the vehicle; C d is the drag coefficient; v is the real-time vehicle speed; μ 滚动 is the tire rolling resistance coefficient; m is the vehicle curb mass; g is the acceleration of gravity; θ is the road slope angle; a is the vehicle real-time acceleration; P 空调 is the air conditioning power; t 使用 P is the air conditioning usage time; i is the power of system i; t 使用i is the usage time of system i; SOC is the remaining power; T is the battery temperature; I is the battery charge and discharge current; P 输入 is the motor input power; P 输出 Output power for the motor.

7. The method for predicting the remaining cruising range of an electric vehicle according to claim 6, characterized in that: The step of calculating the initial cruising range based on the remaining battery power and correcting the initial cruising range according to the driving habit correction coefficient, the battery capacity depreciation coefficient and the road condition correction coefficient specifically includes: The initial cruising range is calculated based on the current remaining battery power and the rated capacity after considering battery loss. The calculation formula is: Initial cruising range C 额定 is the rated capacity of the battery; The driving habit data is input into the driving habit model to obtain the driving habit correction coefficient, and the initial cruising range is corrected for the first time; the cruising range after the first correction R 修正 =R 初始 × Driving habit correction factor Determine the battery capacity depreciation coefficient according to the external ambient temperature, and make a second correction to the cruising range after the first correction; the cruising range R after the second correction 温度修正 =R 修正 ×Battery capacity loss factor; Calculate the road condition correction coefficient based on the road condition information, make a third correction to the cruising range after the second correction, and get the remaining cruising range prediction value R 最终 =R 温度修正 ×Road condition correction factor.

8. A system for predicting the remaining cruising range of an electric vehicle, characterized in that: The prediction system is used to execute the method for predicting the remaining cruising range of an electric vehicle according to any one of claims 1 to 7, and the prediction system comprises: A driving habit information acquisition module, used to acquire time series data of driving habits, wherein the driving habits include accelerator pedal stepping depth, brake pedal stepping depth, vehicle speed and steering angle; An extraction module, used for extracting driving habit features according to the time series data of the driving habit to obtain a driving habit feature vector; A driving habit model building module, used to build a driving habit model according to the driving habit feature vector; A comprehensive data processing module is used to collect, clean and calibrate comprehensive data to obtain calibration data. The comprehensive data includes basic driving data, vehicle system data, battery status data, environmental condition data, and navigation APP data; An energy consumption model building module, used to calculate basic driving energy consumption, auxiliary system energy consumption, battery management system energy consumption and motor efficiency loss according to the calibration data, and build an energy consumption model; The remaining cruising range prediction module is used to calculate the initial cruising range according to the remaining battery power, and then correct the initial cruising range based on the driving habit correction factor, battery capacity depreciation factor and road condition correction factor to predict the remaining cruising range; It also includes a dynamic update and adjustment module, which is used to update the remaining mileage prediction value in real time. When the remaining mileage prediction value is lower than the safety threshold of the trip requirements, it provides suggestions for adjusting the driving mode, auxiliary system adjustment, and charging or battery replacement route planning.

9. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for predicting the remaining cruising range of an electric vehicle as described in any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of a method for predicting the remaining cruising range of an electric vehicle as claimed in any one of claims 1 to 7 are implemented.

Images