Method for simulating and calculating standard cruising range of pure electric vehicle, electronic device and medium

Abstract

The application discloses a kind of pure electric vehicle standard cruising range simulation measurement method, electronic equipment, medium, comprising: obtaining the data field required for standard cruising range simulation measurement and its value, constructs standard operating condition test data set;Standard operating condition test data set is input into the energy consumption prediction model trained in advance, the time experienced by battery state of charge from 100% to 0% is predicted;According to the time and pure electric vehicle speed, the standard cruising range of pure electric vehicle is obtained;Wherein, the training process of energy consumption prediction model includes: collecting actual vehicle driving data and screening;Using sliding window, the actual vehicle driving data after preprocessing is resampled;Based on XGBoost algorithm, energy consumption prediction model is constructed and trained;The energy consumption prediction model uses actual vehicle driving data as input data, the battery state of charge predicted at window end time is output data, and the real battery state of charge at window end time is used as label.

Description

Technical Field

[0001] This invention belongs to the field of pure electric vehicle performance evaluation, and particularly relates to a method for simulating and calculating the standard driving range of pure electric vehicles, electronic equipment, and media. Background Technology

[0002] New energy vehicles, represented by pure electric vehicles, have become the mainstream of the automotive industry. However, the development of pure electric vehicles is relatively recent, requiring extensive testing to ensure their reliability and safety. Therefore, real-time status monitoring and prediction for pure electric vehicles are particularly important: on the one hand, they can accurately reflect the vehicle's performance status, allowing owners to promptly identify problems and perform vehicle maintenance, ensuring safety and reliability; on the other hand, they can utilize big data from the driving process to innovate automotive digital and intelligent technologies, providing more operational feedback for the research and development of new energy vehicles.

[0003] Driving range reflects the maximum distance a vehicle can travel continuously after a full charge, and is one of the key indicators for measuring the performance of pure electric vehicles. Unlike remaining driving range, standard driving range is the maximum distance an electric vehicle can continuously travel under specified standard driving conditions while fully charged. Its performance evaluation is often conducted before the vehicle leaves the factory. Due to the long testing time and high cost of standard driving range testing, car owners can only obtain the standard driving range specified before the vehicle's market launch, and cannot obtain information about the performance maintenance status of the vehicle's driving range during the usage phase.

[0004] Therefore, there is an urgent need to propose a method that can effectively and feasiblely measure the standard driving range during the vehicle usage phase. Summary of the Invention

[0005] This invention addresses the shortcomings of existing technologies by providing a method, electronic device, and medium for simulating and calculating the standard driving range of pure electric vehicles. Through this method, vehicle owners can obtain the standard driving range under actual driving conditions.

[0006] In a first aspect, embodiments of the present invention provide a method for simulating and calculating the standard driving range of a pure electric vehicle, the method comprising:

[0007] Based on the test requirements for standard driving range and the factors affecting driving range, the data fields required for the simulation calculation of standard driving range are obtained, and the value of each data field is confirmed to construct a standard operating condition test dataset.

[0008] The standard operating condition test dataset is input into a pre-trained energy consumption prediction model to predict the time it takes for the battery state of charge to drop from 100% to 0%. Based on the time it takes for the battery state of charge to drop from 100% to 0% and the speed of the pure electric vehicle, the standard driving range of the pure electric vehicle is obtained.

[0009] The training process for the energy consumption prediction model includes:

[0010] Collect actual vehicle driving data and filter the actual vehicle driving data according to the data fields required for the simulation calculation of the standard driving range.

[0011] The preprocessed actual vehicle driving data is resampled using a sliding time window method.

[0012] An energy consumption prediction model is constructed and trained based on the XGBoost algorithm. The energy consumption prediction model takes the resampled actual vehicle driving data as input data, the predicted state of charge of the battery at the end of the window as output data, and the actual state of charge of the battery at the end of the window as the label.

[0013] Secondly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory is coupled to the processor; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the above-described method for simulating and calculating the standard driving range of a pure electric vehicle.

[0014] Thirdly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the above-described method for simulating and calculating the standard driving range of a pure electric vehicle.

[0015] The beneficial effects of this invention are as follows:

[0016] 1. This invention constructs a standard operating condition test dataset and uses a pre-trained energy consumption prediction model to predict the time it takes for the battery state of charge to decrease from 100% to 0%. Based on the time it takes for the battery state of charge to decrease from 100% to 0% and the speed of the pure electric vehicle, the standard driving range of the pure electric vehicle is obtained. This enables vehicle owners and OEMs to accurately grasp the standard driving range during the vehicle's usage phase, while providing an effective method for online monitoring and feedback of the vehicle's driving status and performance maintenance, and providing an information foundation for after-sales maintenance, recycling performance evaluation, and other aspects of the vehicle.

[0017] 2. In the process of training the energy consumption prediction model, this invention filters actual vehicle driving data according to the data fields required for the simulation calculation of the standard driving range, thereby reducing data redundancy and improving the accuracy of predicting the battery state of charge. Attached Figure Description

[0018] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings:

[0019] Figure 1This is a flowchart of a method for predicting the standard driving range of a pure electric vehicle provided in an embodiment of the present invention;

[0020] Figure 2 This is a flowchart of constructing a standard operating condition test dataset provided in an embodiment of the present invention;

[0021] Figure 3 This is a flowchart of preprocessing actual vehicle driving data provided in an embodiment of the present invention;

[0022] Figure 4 This is a flowchart of the training energy consumption prediction model provided in the embodiments of the present invention;

[0023] Figure 5 This is a flowchart illustrating the standard driving range of a pure electric vehicle provided in an embodiment of the present invention;

[0024] Figure 6 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0025] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] It should be noted that, unless otherwise specified, the features in the following embodiments and implementation methods can be combined with each other.

[0027] like Figure 1 As shown in the figure, this invention provides a method for predicting the standard driving range of a pure electric vehicle, the method comprising:

[0028] Step S1: Based on the test requirements for standard driving range and the factors affecting driving range, obtain the data fields required for the simulation calculation of standard driving range, confirm the value of each data field, and construct the standard operating condition test dataset.

[0029] Specifically, such as Figure 2 As shown, step S1 specifically includes the following sub-steps:

[0030] Step S101: By analyzing the test requirements for standard driving range and the influencing factors of driving range, the key factors of standard driving range test are defined, and the data fields required for standard driving range simulation calculation are proposed.

[0031] According to GB / T 18386.1-2021 Test Methods for Energy Consumption and Driving Range of Electric Vehicles Part 1: Light Vehicles, the test requirements for standard driving range are specified: the vehicle speed needs to be varied according to regulations, and other state and environmental factors need to be kept at specified constants.

[0032] It should be noted that during actual driving, the vehicle's state and the external environment are constantly changing, which may affect the battery's state of charge (SOC) and thus the driving range. To simulate the standard driving range test from a data perspective, it is necessary to study the requirements of the standard driving range test and reproduce the test process using multi-dimensional data settings. Therefore, the key factors for the standard driving range test are defined, which need to meet the following conditions: factors affecting the change of the battery's SOC in pure electric vehicles; and factors related to driver usage or external environmental factors.

[0033] Step S102: Based on the test requirements and test procedures for standard driving conditions, confirm the values ​​of each data field required for the simulation calculation of standard driving range, and construct the standard driving condition test dataset.

[0034] In this example, the CLTC (China Light-duty Vehicle Test Cycle) driving condition is used as the standard condition. Alternatively, the WLTP (World Light Vehicle Test Procedure) or EPA (United States Environmental Protection Agency) standards can be used for testing.

[0035] In the standard driving range test, the vehicle is driven by test personnel on a chassis dynamometer at the speed specified by CLTC, always traveling in a straight line without turning, and the brake energy recovery system and all auxiliary equipment are turned off.

[0036] The values ​​in the CLTC test dataset fields are set according to GB / T 18386.1-2021 Test Methods for Energy Consumption and Driving Range of Electric Vehicles Part 1: Light Vehicles: The vehicle speed must meet the speed specified by CLTC; the load is set to the average weight of Chinese men and women of 65 kg; the brake energy recovery rate is 0%; the air conditioning power, lighting power, wiper power, and ventilation power are all set to 0 kW; the steering wheel angle is 0°; the steering wheel angular velocity is 0 rad / s; the road slope is 0°; the curve curvature is 0°; the road type is asphalt road; the ambient temperature is 23℃; the atmospheric pressure is the standard pressure under normal conditions; since the test is conducted indoors, the weather is set to cloudy.

[0037] Step S2: Collect actual vehicle driving data, filter the actual vehicle driving data according to the data fields required for the standard driving range simulation calculation, and preprocess the filtered actual vehicle driving data.

[0038] Specifically, such as Figure 3 As shown, step S2 specifically includes the following sub-steps:

[0039] Step S201: Collect actual vehicle driving data according to the data fields required for the standard driving range simulation calculation and the data fields required for data preprocessing, and perform missing value processing and normalization processing on the actual vehicle driving data.

[0040] Based on the above conditions, the actual vehicle driving data collected in this example includes the overall vehicle status, vehicle auxiliary system status, vehicle braking energy recovery rate, vehicle driving operation data, and geographical environment data.

[0041] The vehicle status includes vehicle identification, data time, whether it is charging, start / stop status, speed, battery state of charge (SOC), cumulative mileage, and load.

[0042] The vehicle assistance system status includes air conditioning power, lighting power, wiper power, and ventilation power.

[0043] The vehicle driving operation data includes steering wheel angle and steering wheel angular velocity.

[0044] The geographic environment data includes road slope, curve curvature, road type, ambient temperature, atmospheric pressure, and weather.

[0045] Step S202: The normalized actual vehicle driving data is marked with discharge cycle and the effective driving segment is extracted. The battery state of charge (SOC) in the effective driving segment is smoothed.

[0046] It should be noted that the energy consumption prediction model constructed in this invention aims to accurately predict the change process of the battery's state of charge (SOC) during a complete discharge cycle, i.e., the process of the battery's SOC decreasing from 100% to 0% during continuous driving, by inputting the corresponding data fields. During this process, the battery's SOC decreases monotonically, and charging behavior will cause the battery's SOC value to increase significantly, thus disrupting the cumulative effect of driving state on the battery's SOC.

[0047] To eliminate interference from charging factors, a discharge cycle needs to be defined. A discharge cycle is the time period from the end of the previous charge to the start of the next charge. The vehicle driving data within a discharge cycle is the sum of driving segments within that time period. Each discharge cycle is independent of the others, and changes in the vehicle's state during the cycle do not affect the state in other discharge cycles.

[0048] During the discharge cycle, there are a large number of data segments of vehicle shutdown and malfunction. During this period, the battery state of charge (SOC) hardly changes, which adds redundant information to the training of the energy consumption prediction model. Therefore, it is necessary to extract effective information and define effective driving segments: delete the remaining driving segments in the driving segments where the speed is 0 for a long time and the battery SOC does not change.

[0049] If the accuracy of the collected data is low, the SOC value may remain unchanged for a certain continuous time period. Therefore, it is necessary to smooth the SOC in the effective driving segment corresponding to each discharge cycle. In this example, the mean smoothing method is used for smoothing, and the expression is as follows:

[0050]

[0051] Where n is the amount of data in the effective driving segment corresponding to each discharge cycle, SR is the smoothing radius of the mean, and q i The actual value of the battery's state of charge (SOC) in the i-th battery state of charge (SOC) during the effective driving segment corresponding to each discharge cycle. The smoothed State of Charge (SOC) value of the i-th battery in the effective driving segment corresponding to each discharge cycle; the selection of SR is related to the degree of data variation, acquisition accuracy, and acquisition cycle, and an appropriate SR value needs to be selected according to the characteristics of the data.

[0052] Step S3: Construct and train an energy consumption prediction model based on the XGBoost algorithm; wherein, training the energy consumption prediction model includes: resampling the preprocessed actual vehicle driving data using a sliding time window method, using the resampled actual vehicle driving data as input data, using the predicted battery state of charge at the end of the window as output data, and using the actual battery state of charge at the end of the window as a label; the resampled actual vehicle driving data includes the battery state of charge at the beginning of the window, the battery state of charge at the end of the window, and the data fields required for the standard driving range simulation calculation.

[0053] Specifically, such as Figure 4 As shown, step S3 specifically includes the following sub-steps:

[0054] Step S301: Use the sliding time window method to resample the preprocessed actual vehicle driving data to obtain several training sets and corresponding test sets.

[0055] It should be noted that, due to the characteristics of the actual vehicle driving data collected in each discharge cycle, such as variable collection time, non-fixed start and end points, large quantity, and causal relationship between energy consumption changes, the training set and test set do not meet the input requirements of the energy consumption prediction model. Therefore, this example uses a sliding time window to resample the actual vehicle driving data to construct a training set and test set suitable for the input of the energy consumption prediction model.

[0056] The preprocessed actual vehicle driving data is divided into training and test sets, and the sliding time window method is used to resample the training and test sets.

[0057] The resampling of the training set using a sliding time window method includes:

[0058] Based on the data length of each discharge cycle, the range of values ​​for the sliding window size and the moving step size is determined. A set of values ​​for the window size and the moving step size is constructed according to a preset value interval. Different parameter combinations are constructed by combining the parameters in the set of values ​​in pairs. Based on the different parameter combinations, the preprocessed actual vehicle driving data is resampled using the sliding time window method to construct different training sets.

[0059] Furthermore, the data in the training set is time-series data, including the battery state of charge at the start of the window, the battery state of charge at the end of the window, and the data fields required for the standard driving range simulation calculation.

[0060] The method of resampling the test set using a sliding time window includes:

[0061] The energy consumption prediction model predicts energy consumption over the entire discharge cycle. To ensure accuracy, the test set does not use a single sliding time window but employs cyclic testing. Specifically, the window size for the test set is the same as the window size for the training set, but the sliding step size for the test set is reduced by one. The output of the first sliding time window (the predicted state of charge) is used as the input state of charge for the second sliding time window, and so on, until the end of a discharge cycle. Different training sets have corresponding test sets.

[0062] Step S302: Construct and train an energy consumption prediction model based on the XGBoost algorithm, using the training set as input data, the predicted state of charge of the battery at the end of the window as output data, and the actual state of charge of the battery at the end of the window as the label; thus obtaining several trained energy consumption prediction models.

[0063] Step S302 further includes: determining the coefficient of determination R 2Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) are used as evaluation metrics for the energy consumption prediction model. The model is repeatedly trained using the training set until R0 is achieved. 2 The three indicators, MAPE and RMSE, remain basically unchanged before and after training. Different energy consumption prediction models are obtained by training on training sets constructed with different parameters.

[0064] Step S303: Input the test set into the corresponding trained energy consumption prediction model for verification, and select the model with the best test performance as the final energy consumption prediction model.

[0065] The test set is input into the corresponding energy consumption prediction model for testing. The energy consumption prediction model is evaluated by a cyclic testing method, that is, the comparison is not based on a window, but on a discharge cycle. The prediction results obtained after inputting the data of each discharge cycle into the model are compared with the actual values, the evaluation index is calculated, and the evaluation index of each discharge cycle is summed and averaged to obtain the test result of the energy consumption prediction model.

[0066] Based on the test results of the energy consumption prediction model, and taking into account R... 2 The energy consumption prediction model needs to satisfy the values ​​of three indicators: MAPE, RMSE, and R. 2 The energy consumption prediction model must be greater than 0.9 and at least satisfy either RMSE < 2 or MAPE < 4. Under the premise of meeting the requirements, the energy consumption prediction models with different parameters are ranked and the energy consumption prediction model with the best test performance is selected as the final energy consumption prediction model.

[0067] Step S4: Input the standard operating condition test dataset into the optimal energy consumption prediction model to predict the time it takes for the battery state of charge to drop from 100% to 0%; based on the time it takes for the battery state of charge to drop from 100% to 0% and the speed of the pure electric vehicle, obtain the standard driving range of the pure electric vehicle.

[0068] Specifically, such as Figure 5 As shown, step S4 specifically includes the following sub-steps:

[0069] Step S401: Resample the standard operating condition test dataset according to the sampling frequency and sliding time window size of the training set corresponding to the optimal energy consumption prediction model.

[0070] Furthermore, since the collection frequencies of actual driving data and standard operating condition test data may differ, it is necessary to resample the standard operating condition test data based on the actual data to ensure the consistency of the collection frequency between the standard operating condition test dataset and the training data. The standard operating condition test dataset is reconstructed using a sliding time window. According to the purpose of the energy consumption prediction model mentioned above, the sliding time window and the moving step size should be consistent with the test set, that is, the sliding time window size is the same as the training set, and the moving step size is the sliding time window size minus 1.

[0071] Step S402: Input the resampled standard operating condition test dataset into the optimal energy consumption prediction model to predict the time it takes for the SOC to drop from 100% to 0%.

[0072] Specifically, the initial SOC is set to 100%; the standard driving condition data of the first window is input into the trained optimal energy consumption prediction model to obtain the battery SOC result predicted for the first window; the battery SOC result predicted for the first window and the standard driving condition data of the second window are input into the optimal energy consumption prediction model to continue prediction to obtain the battery SOC result predicted for the second window; and so on, until the battery SOC prediction result output by the energy consumption prediction model is 0% or less than 0%, then the prediction stops, and the battery SOC change curve is obtained.

[0073] Calculate the time it takes for the battery's state of charge (SOC) to decrease from 100% to 0%, within a certain sliding time window n. w If the predicted state of charge (SOC) of the battery at the end is exactly 0% or less than 0%, then the total time T is obtained by summing the times of all sliding time windows, as shown in the following expression:

[0074]

[0075] In the formula, n w t is the sequence number of the sliding time window. w SOC is the time corresponding to a sliding time window. start For the nth w The battery state of charge (SOC) at the start of each sliding time window, SOC end For the nth w The battery state of charge (SOC) at the end of each sliding time window is then... start >0 and SOC end <0.

[0076] The total time T is rounded down for calculation.

[0077] Step S403: Based on the time and speed taken for the battery's state of charge to decrease from 100% to 0%, the standard driving range of the pure electric vehicle is obtained. The expression is as follows:

[0078]

[0079] Where Range is the standard driving range of a pure electric vehicle, T is the time it takes for the State of Charge (SOC) to decrease from 100% to 0%, and v i Let Δt be the speed at each moment, and Δt be the time interval, which is the sampling time interval of the actual vehicle driving data.

[0080] like Figure 6 As shown, this application provides an electronic device including a memory 101 for storing one or more programs and a processor 102. When the one or more programs are executed by the processor 102, they implement the method as described in any of the first aspects above.

[0081] The system also includes a communication interface 103. The memory 101, processor 102, and communication interface 103 are electrically connected directly or indirectly to each other to enable data transmission or interaction. For example, these components can be electrically connected to each other via one or more communication buses or signal lines. The memory 101 can be used to store software programs and modules, and the processor 102 executes various functional applications and data processing by executing the software programs and modules stored in the memory 101. The communication interface 103 can be used for signaling or data communication with other node devices.

[0082] The memory 101 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0083] The processor 102 can be an integrated circuit chip with signal processing capabilities. The processor 102 can be a general-purpose processor 102, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0084] In the embodiments provided in this application, it should be understood that the disclosed methods and systems can also be implemented in other ways. The method and system embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0085] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0086] On the other hand, embodiments of this application provide a computer-readable storage medium storing a computer program thereon. When executed by processor 102, the computer program implements the methods described in any of the first aspects above. If the functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory 101 (ROM), random access memory 101 (RAM), magnetic disks, or optical disks.

[0087] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only.

[0088] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A method for simulating and calculating the standard driving range of a pure electric vehicle, characterized in that, The method includes: Based on the test requirements for standard driving range and the factors affecting driving range, the data fields required for the simulation calculation of standard driving range are obtained, and the value of each data field is confirmed to construct a standard operating condition test dataset. The standard operating condition test dataset is input into a pre-trained energy consumption prediction model to predict the time it takes for the battery state of charge to drop from 100% to 0%. Based on the time it takes for the battery state of charge to drop from 100% to 0% and the speed of the pure electric vehicle, the standard driving range of the pure electric vehicle is obtained. The training process for the energy consumption prediction model includes: Collect and preprocess actual vehicle driving data; The preprocessed actual vehicle driving data is resampled using a sliding time window method. An energy consumption prediction model is constructed and trained based on the XGBoost algorithm. The energy consumption prediction model takes resampled actual vehicle driving data as input data, outputs battery state of charge predicted at the end of the window, and uses the actual battery state of charge at the end of the window as the label. The resampled actual vehicle driving data includes the battery state of charge at the beginning of the window and the battery state of charge at the end of the window.

2. The method for simulating and calculating the standard driving range of a pure electric vehicle according to claim 1, characterized in that, The standard operating condition test dataset is input into a pre-trained energy consumption prediction model to predict the time it takes for the battery state of charge to decrease from 100% to 0%. The standard operating condition test dataset is resampled based on the sampling frequency and sliding time window size of the actual vehicle driving data corresponding to the pre-trained energy consumption prediction model. The initial battery state of charge is set to 100%. The standard driving condition data of the first window is input into the trained energy consumption prediction model to obtain the battery state of charge result predicted for the first window. The battery state of charge result predicted for the first window and the standard driving condition data of the second window are input into the trained energy consumption prediction model to continue to participate in the prediction to obtain the battery state of charge result predicted for the second window. This process continues until the battery state of charge prediction result output by the energy consumption prediction model is 0% or less than 0%, at which point the prediction stops. Calculate the time it takes for the battery's state of charge to decrease from 100% to 0%, within a certain sliding time window. If the predicted battery state of charge is exactly 0% or less than 0% after the end, the total time T is obtained by summing the times of all sliding time windows, as shown in the following expression: ； In the formula, This is the sequence number of the sliding time window. This represents the time corresponding to a sliding time window. For the first The state of charge of the battery at the start of each sliding time window For the first The state of charge of the battery at the end of each sliding time window, and and ; The total time T is rounded down for calculation.

3. The method for simulating and calculating the standard driving range of a pure electric vehicle according to claim 1 or 2, characterized in that, The standard driving range of a pure electric vehicle is calculated based on the time it takes for the battery to go from 100% to 0% state of charge and the speed of the pure electric vehicle, as shown in the following expression: ； In the formula, Range represents the standard driving range of a pure electric vehicle, and T represents the time it takes for the battery to go from 100% to 0% state of charge. The velocity at each moment, The time interval is the sampling time interval for actual vehicle driving data.

4. The method for simulating and calculating the standard driving range of a pure electric vehicle according to claim 1, characterized in that, The actual vehicle driving data includes: overall vehicle status, vehicle auxiliary system status, vehicle braking energy recovery rate, vehicle driving operation data, and geographical environment data; The vehicle status includes vehicle identification, data time, whether it is charging, start / stop status, speed, battery state of charge, cumulative mileage, and load. The vehicle assistance system status includes air conditioning power, lighting power, wiper power, and ventilation power; The vehicle driving operation data includes steering wheel angle and steering wheel angular velocity; The geographic environment data includes road slope, curve curvature, road type, ambient temperature, atmospheric pressure, and weather.

5. A method for simulating and calculating the standard driving range of a pure electric vehicle according to claim 1 or 4, characterized in that, Collecting actual vehicle driving data and performing preprocessing includes: Based on the data fields required for standard driving range simulation calculation and data preprocessing, actual vehicle driving data is collected, and missing value processing and normalization are performed on the actual vehicle driving data. The normalized actual vehicle driving data is marked with discharge cycles and effective driving segments are extracted. The battery state of charge in the effective driving segments is smoothed.

6. A method for simulating and calculating the standard driving range of a pure electric vehicle according to claim 1 or 4, characterized in that, Resampling of preprocessed real vehicle driving data using a sliding time window method includes: The preprocessed actual vehicle driving data is divided into training data and test data, and the sliding time window method is used to resample the training data and test data. The method of resampling training data using a sliding time window includes: setting the range of values ​​for the sliding window size and the moving step size, and resampling the training data according to different sliding window sizes and different moving step sizes to obtain several training sets. The test data is resampled using a sliding time window method, which includes: the window size corresponding to the test data is the same as the window size corresponding to the training data, and the sliding step size is set to the window size minus 1, so that the battery state of charge predicted by the first sliding time window is used as the battery state of charge input for the second sliding time window, and so on, until the end of a discharge cycle.

7. The method for simulating and calculating the standard driving range of a pure electric vehicle according to claim 6, characterized in that, The energy consumption prediction model constructed and trained based on the XGBoost algorithm includes: By constructing and training an energy consumption prediction model based on the XGBoost algorithm for each training set, several trained energy consumption prediction models are obtained. The energy consumption prediction model takes the resampled actual vehicle driving data as input data, the predicted battery state of charge at the end of the window as output data, and the actual battery state of charge at the end of the window as the label. The resampled actual vehicle driving data includes the battery state of charge at the beginning of the window, the battery state of charge at the end of the window, and the data fields required for the standard driving range simulation calculation. The test set is input into the corresponding trained energy consumption prediction model for verification. The model must satisfy the following conditions: coefficient of determination R² > 0.9, root mean square error RMSE < 2 or mean absolute percentage error MAPE < 4. The coefficient of determination R², mean absolute percentage error MAPE, and root mean square error RMSE are then summed and averaged as the test result. The energy consumption prediction model with the best test result is selected as the final energy consumption prediction model.

8. The method for simulating and calculating the standard driving range of a pure electric vehicle according to claim 7, characterized in that, Training energy consumption prediction models also includes: The coefficient of determination R², mean absolute percentage error (MAPE), and root mean square error (RMSE) are used as evaluation indicators for the energy consumption prediction model. The energy consumption prediction model is repeatedly trained using the training set until the coefficient of determination R², mean absolute percentage error (MAPE), and root mean square error (RMSE) tend to stabilize.

9. An electronic device comprising a memory and a processor, characterized in that, The memory is coupled to the processor; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the simulation calculation method for the standard driving range of pure electric vehicles according to any one of claims 1-8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the simulation calculation method for the standard driving range of pure electric vehicles as described in any one of claims 1-8.

Images