A method and apparatus for predicting the range of a vehicle

Abstract

The application discloses a kind of vehicle endurance mileage prediction method and device, including obtaining the self-vehicle data and environmental data of vehicle on current section;First residual endurance mileage of vehicle on current section is obtained based on vehicle driving history data and current position;Environment temperature is input in preset battery discharge model, and the optimization coefficient reflecting the influence of environment temperature on battery discharge capacity is obtained;According to optimization coefficient and battery data, the actual output power of battery is calculated;Second residual endurance mileage of vehicle on current section is obtained;According to the weight influence of first residual endurance mileage and second residual endurance mileage, the endurance mileage prediction of vehicle is carried out.The vehicle endurance mileage prediction method and device provided in the embodiment of the application are analyzed by double through historical data and battery discharge capacity, the influence of historical data and environment temperature on vehicle endurance capacity is comprehensively considered, so as to improve the accuracy of vehicle endurance mileage, and promote the intelligent process of vehicle.

Description

Technical Field

[0001] This invention relates to the field of vehicle range technology, and in particular to a method and apparatus for predicting vehicle range. Background Technology

[0002] With the continuous development of new energy technologies, electric vehicles, with their many advantages such as fast start-up, zero emissions, low noise, and low energy consumption, are gradually gaining market recognition and consumer favor.

[0003] The driving range of an electric vehicle is a crucial aspect of vehicle control. Drivers need to check the driving range displayed on the electric vehicle's instrument panel to plan their trips and avoid the vehicle running out of energy and having to stop. Therefore, how to accurately predict the driving range of a vehicle has become a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0004] This invention provides a method and apparatus for predicting vehicle driving range. By performing dual analysis of historical data and battery discharge capacity, and comprehensively considering the impact of historical data and ambient temperature on vehicle driving range, the accuracy of vehicle driving range is improved, thus promoting the intelligentization of vehicles.

[0005] To address the aforementioned technical problems, embodiments of the present invention provide a method for predicting vehicle driving range, comprising:

[0006] Acquire vehicle data and environmental data on the current road segment, wherein the vehicle data includes battery data, vehicle speed data, and torque data, and the environmental data includes current location and ambient temperature;

[0007] Based on the vehicle driving history data pre-existing on the big data platform and the current location, the vehicle's first remaining driving range on the current road segment is obtained;

[0008] The ambient temperature is input into a preset battery discharge model to obtain an optimization coefficient that reflects the influence of ambient temperature on battery discharge capacity.

[0009] The actual output power of the battery is calculated based on the optimization coefficients and the battery data.

[0010] Based on the actual output power, the vehicle speed data, and the torque data, the second remaining driving range of the vehicle on the current road segment is obtained;

[0011] The vehicle's remaining driving range is predicted based on the weighted influence of the first remaining driving range and the second remaining driving range.

[0012] As one preferred embodiment, obtaining the vehicle's first remaining driving range on the current road segment based on vehicle driving history data pre-existing on a big data platform and the current location specifically includes:

[0013] The vehicle driving history data is preprocessed, including data cleaning, missing data filling, standardization and normalization.

[0014] Based on the preprocessed vehicle driving history data, a correspondence table between the remaining mileage and location of the current road segment is obtained;

[0015] Input the current location into the corresponding table to obtain the vehicle's first remaining driving range on the current road segment.

[0016] As one preferred embodiment, the preprocessing also includes dimensionality reduction processing;

[0017] The preprocessing of the vehicle driving history data specifically includes:

[0018] The vehicle driving history data is sequentially cleaned, missing data is filled, and standardized and normalized.

[0019] Based on Pearson correlation coefficient analysis, the normalized vehicle driving history data is subjected to dimensionality reduction processing.

[0020] Vehicle driving history data with a Pearson coefficient less than a first set value were selected and used as the dimensionality-reduced vehicle driving history data.

[0021] As one preferred embodiment, the preset battery discharge model is constructed using the following method:

[0022] Obtain a sample set consisting of different temperatures and the battery discharge efficiency ratio corresponding to each temperature;

[0023] The sample set is trained based on neural network model technology and deep forest learning algorithm;

[0024] After obtaining the output results after training, the output results are tested;

[0025] Based on the test results, the corresponding battery discharge model is constructed.

[0026] As one preferred embodiment, the process of predicting the vehicle's remaining driving range based on the weighted influence of the first remaining driving range and the second remaining driving range specifically includes:

[0027] The first remaining driving range and the second remaining driving range are input into a preset driving range weighted calculation formula to calculate the vehicle's driving range.

[0028] The weighted calculation formula for the driving range is:

[0029] P = ρ × F1 + μ × F2

[0030] Where P is the vehicle's driving range, ρ is the historical data influence coefficient, ρ = 0.37, F1 is the first remaining driving range, μ is the ambient temperature influence coefficient, μ = 0.63, and F2 is the second remaining driving range.

[0031] Another embodiment of the present invention provides a vehicle range prediction device, comprising:

[0032] The data acquisition module is used to acquire vehicle data and environmental data on the current road segment. The vehicle data includes battery data, vehicle speed data, and torque data, and the environmental data includes the current location and ambient temperature.

[0033] The first remaining driving range module is used to obtain the first remaining driving range of the vehicle on the current road segment based on the vehicle driving history data pre-existing on the big data platform and the current location.

[0034] The optimization coefficient module is used to input the ambient temperature into a preset battery discharge model to obtain optimization coefficients that reflect the influence of ambient temperature on battery discharge capability.

[0035] An output power module is used to calculate the actual output power of the battery based on the optimization coefficient and the battery data.

[0036] The second remaining driving range module is used to obtain the second remaining driving range of the vehicle on the current road segment based on the actual output power, the vehicle speed data and the torque data;

[0037] The driving range prediction module is used to predict the vehicle's driving range based on the weighted influence of the first remaining driving range and the second remaining driving range.

[0038] As one preferred embodiment, obtaining the vehicle's first remaining driving range on the current road segment based on vehicle driving history data pre-existing on a big data platform and the current location specifically includes:

[0039] The vehicle driving history data is preprocessed, including data cleaning, missing data filling, standardization and normalization.

[0040] Based on the preprocessed vehicle driving history data, a correspondence table between the remaining mileage and location of the current road segment is obtained;

[0041] Input the current location into the corresponding table to obtain the vehicle's first remaining driving range on the current road segment.

[0042] As one preferred embodiment, the preprocessing also includes dimensionality reduction processing;

[0043] The preprocessing of the vehicle driving history data specifically includes:

[0044] The vehicle driving history data is sequentially cleaned, missing data is filled, and standardized and normalized.

[0045] Based on Pearson correlation coefficient analysis, the normalized vehicle driving history data is subjected to dimensionality reduction processing.

[0046] Vehicle driving history data with a Pearson coefficient less than a first set value were selected and used as the dimensionality-reduced vehicle driving history data.

[0047] As one preferred embodiment, the preset battery discharge model is constructed using the following method:

[0048] Obtain a sample set consisting of different temperatures and the battery discharge efficiency ratio corresponding to each temperature;

[0049] The sample set is trained based on neural network model technology and deep forest learning algorithm;

[0050] After obtaining the output results after training, the output results are tested;

[0051] Based on the test results, the corresponding battery discharge model is constructed.

[0052] As one preferred embodiment, the process of predicting the vehicle's remaining driving range based on the weighted influence of the first remaining driving range and the second remaining driving range specifically includes:

[0053] The first remaining driving range and the second remaining driving range are input into a preset driving range weighted calculation formula to calculate the vehicle's driving range.

[0054] The weighted calculation formula for the driving range is:

[0055] P = ρ × F1 + μ × F2

[0056] Where P is the vehicle's driving range, ρ is the historical data influence coefficient, ρ = 0.37, F1 is the first remaining driving range, μ is the ambient temperature influence coefficient, μ = 0.63, and F2 is the second remaining driving range.

[0057] Compared with the prior art, the beneficial effects of the embodiments of the present invention are at least one of the following:

[0058] (1) First, acquire the vehicle's own data and environmental data on the current road segment. The vehicle data includes battery data, vehicle speed data, and torque data. The environmental data includes the current location and ambient temperature. Then, based on the vehicle's driving history data pre-stored on the big data platform and the current location, acquire the vehicle's first remaining driving range on the current road segment. Next, input the ambient temperature into a preset battery discharge model to obtain an optimization coefficient reflecting the influence of ambient temperature on battery discharge capacity. Then, calculate the battery's actual output power based on the optimization coefficient and the battery data. Next, acquire the vehicle's second remaining driving range on the current road segment based on the actual output power, the vehicle speed data, and the torque data. Finally, predict the vehicle's driving range based on the weighted influence of the first remaining driving range and the second remaining driving range.

[0059] (2) The combined analysis of the historical data of the current road section and the dual impact of ambient temperature improves the accuracy of range prediction. Secondly, the impact of ambient temperature on battery discharge capacity is taken into account. By calculating the optimization coefficient reflecting the impact of ambient temperature on battery discharge capacity, the second range under the current ambient temperature is calculated. Finally, based on the weighted impact of the first and second remaining ranges obtained from historical data, the final range is calculated, thereby further improving the accuracy of range prediction. This helps to prevent electric vehicles from stopping due to energy depletion during driving, ensuring the passenger's driving experience and promoting the intelligentization of vehicles. Attached Figure Description

[0060] Figure 1 This is a flowchart illustrating a method for predicting vehicle driving range in one embodiment of the present invention.

[0061] Figure 2 This is the vehicle range under different ambient temperatures in one embodiment of the present invention;

[0062] Figure 3 This is a schematic diagram of the vehicle range prediction device in one embodiment of the present invention.

[0063] Figure label:

[0064] Among them, 11 is the data acquisition module; 12 is the first remaining driving range module; 13 is the optimization coefficient module; 14 is the output power module; 15 is the second remaining driving range module; and 16 is the driving range prediction module. Detailed Implementation

[0065] 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. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0066] In the description of this application, the terms "first," "second," "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined with "first," "second," "third," etc., may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0067] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to the internal communication between two components. The terms "vertical," "horizontal," "left," "right," "upper," "lower," and similar expressions used herein are for illustrative purposes only and do not indicate or imply that the device or component referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as limiting the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0068] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this specification is for the purpose of describing specific embodiments only and is not intended to limit the invention. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0069] One embodiment of the present invention provides a method for predicting vehicle driving range. For details, please refer to [link to documentation]. Figure 1 , Figure 1 The diagram shows a flowchart of a method for predicting vehicle driving range according to one embodiment of the present invention, specifically including the following steps S1 to S6:

[0070] S1. Obtain vehicle data and environmental data on the current road segment, wherein the vehicle data includes battery data, vehicle speed data and torque data, and the environmental data includes current location and ambient temperature;

[0071] S2. Based on the vehicle driving history data pre-existing on the big data platform and the current location, obtain the first remaining driving range of the vehicle on the current road segment;

[0072] S3. Input the ambient temperature into the preset battery discharge model to obtain the optimization coefficient that reflects the influence of ambient temperature on battery discharge capacity.

[0073] S4. Calculate the actual output power of the battery based on the optimization coefficient and the battery data;

[0074] S5. Based on the actual output power, the vehicle speed data and the torque data, obtain the second remaining driving range of the vehicle on the current road segment;

[0075] S6. Based on the weighted influence of the first remaining driving range and the second remaining driving range, predict the vehicle's driving range.

[0076] It should be noted that the embodiments of the present invention are applicable to electric vehicles and hybrid vehicles. In the prior art, the prediction of driving range relies heavily on the influence of single factors, without comprehensively considering the combined effects of various factors. In the embodiments of the present invention, not only are historical data included in the factors affecting the prediction of driving range, but the influence of ambient temperature on battery discharge capacity is also considered. The discharge capacity of the power battery varies under different ambient temperatures, and the inventors have found that this has a certain impact on driving range. For details, please refer to [link / reference]. Figure 2 , Figure 2 The figure shows the vehicle range under different ambient temperatures in one embodiment of the present invention. The upper line in the figure is a fitting curve obtained by data fitting software, and the lower D(T) / D(25℃) represents the ratio of the range of the power battery system at different temperatures to the range at a temperature of 25℃. It can be seen that the vehicle range will change under different ambient temperatures.

[0077] By comprehensively analyzing the two types of data and combining them with weighting parameters, an accurate driving range is finally obtained, thereby improving the accuracy of driving range prediction. This helps prevent electric vehicles from running out of energy and stopping during driving, ensuring the passenger's driving experience and promoting the intelligentization of vehicles.

[0078] Further, in the above embodiment, step S2: obtaining the vehicle's first remaining driving range on the current road segment based on the vehicle's driving history data pre-existing on the big data platform and the current location, specifically includes:

[0079] S21. Preprocess the vehicle driving history data, including data cleaning, data missing filling, standardization and normalization.

[0080] S22. Based on the preprocessed vehicle driving history data, obtain a correspondence table between the remaining mileage and location of the current road segment;

[0081] S23. Input the current location into the corresponding table to obtain the vehicle's first remaining driving range on the current road segment.

[0082] Furthermore, in the above embodiments, the preprocessing also includes dimensionality reduction processing;

[0083] The preprocessing of the vehicle driving history data specifically includes:

[0084] The vehicle driving history data is sequentially cleaned, missing data is filled, and standardized and normalized.

[0085] Based on Pearson correlation coefficient analysis, the normalized vehicle driving history data is subjected to dimensionality reduction processing.

[0086] Vehicle driving history data with a Pearson coefficient less than a first set value were selected and used as the dimensionality-reduced vehicle driving history data.

[0087] The aforementioned data cleaning, missing data imputation, standardization, and normalization processes can effectively improve data accuracy, thereby providing accurate data support for subsequent calculations of driving range. At the same time, considering that the vehicle driving history data on the big data platform may be obtained through neural network training, the benefits of data dimensionality reduction are improved data visualization, enhanced algorithm usability, and reduced data storage space.

[0088] In this embodiment of the invention, the battery discharge model in step S3 is constructed using the following method:

[0089] S31. Obtain a sample set consisting of different temperatures and the battery discharge efficiency ratio corresponding to each temperature;

[0090] S32. The sample set is trained based on neural network model technology and deep forest learning algorithm;

[0091] S33. After obtaining the output results after training, test the output results;

[0092] S34. Based on the test results, construct the corresponding battery discharge model.

[0093] Battery discharge models can effectively reflect the effect of ambient temperature on battery discharge capacity. This approach takes into account the influence of ambient temperature on battery discharge capacity, thereby further improving the accuracy of vehicle range prediction.

[0094] In the above embodiments, the step of predicting the vehicle's remaining driving range based on the weighted influence of the first remaining driving range and the second remaining driving range specifically includes:

[0095] The first remaining driving range and the second remaining driving range are input into a preset driving range weighted calculation formula to calculate the vehicle's driving range.

[0096] The weighted calculation formula for the driving range is:

[0097] P = ρ × F1 + μ × F2

[0098] Where P is the vehicle's driving range, ρ is the historical data influence coefficient, ρ = 0.37, F1 is the first remaining driving range, μ is the ambient temperature influence coefficient, μ = 0.63, and F2 is the second remaining driving range.

[0099] It should be noted that the vehicle data in the embodiments of the present invention can be obtained by relevant sensors or by the corresponding vehicle-side control domain, such as the VDCM domain, BDCM domain, IDVM domain, etc. The calculation process of battery parameters can refer to the relevant information on lithium battery capacity analysis in the prior art, and will not be repeated here. Similarly, the calculation of the second remaining driving range based on the battery output power, vehicle speed information and torque information can also refer to the relevant information on lithium battery capacity analysis in the prior art, and will not be repeated here. As for environmental data, the current location information can be obtained by relevant GPS positioning software, and then the ambient temperature data can be obtained by relevant vehicle-side sensors. Of course, it can also be obtained by other means, which are not specifically limited in the present invention.

[0100] For details, please see Figure 3 , Figure 3 The diagram shown illustrates the structure of a vehicle range prediction device according to one embodiment of the present invention. Another embodiment of the present invention provides a vehicle range prediction device, comprising:

[0101] The data acquisition module 11 is used to acquire vehicle data and environmental data on the current road segment, wherein the vehicle data includes battery data, vehicle speed data and torque data, and the environmental data includes current location and ambient temperature;

[0102] The first remaining driving range module 12 is used to obtain the first remaining driving range of the vehicle on the current road segment based on the vehicle driving history data pre-existing on the big data platform and the current location.

[0103] The optimization coefficient module 13 is used to input the ambient temperature into a preset battery discharge model to obtain optimization coefficients that reflect the influence of ambient temperature on battery discharge capability.

[0104] Output power module 14 is used to calculate the actual output power of the battery based on the optimization coefficient and the battery data;

[0105] The second remaining driving range module 15 is used to obtain the second remaining driving range of the vehicle on the current road segment based on the actual output power, the vehicle speed data and the torque data.

[0106] The driving range prediction module 16 is used to predict the driving range of the vehicle based on the weighted influence of the first remaining driving range and the second remaining driving range.

[0107] Furthermore, in the above embodiments, obtaining the vehicle's first remaining driving range on the current road segment based on the vehicle's driving history data pre-existing on the big data platform and the current location specifically includes:

[0108] The vehicle driving history data is preprocessed, including data cleaning, missing data filling, standardization and normalization.

[0109] Based on the preprocessed vehicle driving history data, a correspondence table between the remaining mileage and location of the current road segment is obtained;

[0110] Input the current location into the corresponding table to obtain the vehicle's first remaining driving range on the current road segment.

[0111] Furthermore, in the above embodiments, the preprocessing also includes dimensionality reduction processing;

[0112] The preprocessing of the vehicle driving history data specifically includes:

[0113] The vehicle driving history data is sequentially cleaned, missing data is filled, and standardized and normalized.

[0114] Based on Pearson correlation coefficient analysis, the normalized vehicle driving history data is subjected to dimensionality reduction processing.

[0115] Vehicle driving history data with a Pearson coefficient less than a first set value were selected and used as the dimensionality-reduced vehicle driving history data.

[0116] Furthermore, in the above embodiments, the preset battery discharge model is constructed using the following method:

[0117] Obtain a sample set consisting of different temperatures and the battery discharge efficiency ratio corresponding to each temperature;

[0118] The sample set is trained based on neural network model technology and deep forest learning algorithm;

[0119] After obtaining the output results after training, the output results are tested;

[0120] Based on the test results, the corresponding battery discharge model is constructed.

[0121] Furthermore, in the above embodiments, the step of predicting the vehicle's remaining driving range based on the weighted influence of the first remaining driving range and the second remaining driving range specifically includes:

[0122] The first remaining driving range and the second remaining driving range are input into a preset driving range weighted calculation formula to calculate the vehicle's driving range.

[0123] The weighted calculation formula for the driving range is:

[0124] P = ρ × F1 + μ × F2

[0125] Where P is the vehicle's driving range, ρ is the historical data influence coefficient, ρ = 0.37, F1 is the first remaining driving range, μ is the ambient temperature influence coefficient, μ = 0.63, and F2 is the second remaining driving range.

[0126] The vehicle range prediction method and apparatus provided in this invention have the following advantages:

[0127] (1) First, acquire the vehicle's own data and environmental data on the current road segment. The vehicle data includes battery data, vehicle speed data, and torque data. The environmental data includes the current location and ambient temperature. Then, based on the vehicle's driving history data pre-stored on the big data platform and the current location, acquire the vehicle's first remaining driving range on the current road segment. Next, input the ambient temperature into a preset battery discharge model to obtain an optimization coefficient reflecting the influence of ambient temperature on battery discharge capacity. Then, calculate the battery's actual output power based on the optimization coefficient and the battery data. Next, acquire the vehicle's second remaining driving range on the current road segment based on the actual output power, the vehicle speed data, and the torque data. Finally, predict the vehicle's driving range based on the weighted influence of the first remaining driving range and the second remaining driving range.

[0128] (2) The combined analysis of the historical data of the current road section and the dual impact of ambient temperature improves the accuracy of range prediction. Secondly, the impact of ambient temperature on battery discharge capacity is taken into account. By calculating the optimization coefficient reflecting the impact of ambient temperature on battery discharge capacity, the second range under the current ambient temperature is calculated. Finally, based on the weighted impact of the first and second remaining ranges obtained from historical data, the final range is calculated, thereby further improving the accuracy of range prediction. This helps to prevent electric vehicles from stopping due to energy depletion during driving, ensuring the passenger's driving experience and promoting the intelligentization of vehicles.

[0129] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

Claims

1. A method for predicting vehicle driving range, characterized in that, include: Acquire vehicle data and environmental data on the current road segment, wherein the vehicle data includes battery data, vehicle speed data, and torque data, and the environmental data includes current location and ambient temperature; Based on the vehicle driving history data pre-existing on the big data platform and the current location, the vehicle's first remaining driving range on the current road segment is obtained; The ambient temperature is input into a preset battery discharge model to obtain an optimization coefficient that reflects the influence of ambient temperature on battery discharge capacity. The actual output power of the battery is calculated based on the optimization coefficients and the battery data. Based on the actual output power, the vehicle speed data, and the torque data, the second remaining driving range of the vehicle on the current road segment is obtained; The vehicle's range is predicted based on the weighted influence of the first remaining range and the second remaining range. The preset battery discharge model is constructed using the following method: Obtain a sample set consisting of different temperatures and the battery discharge efficiency ratio corresponding to each temperature; The sample set is trained based on neural network model technology and deep forest learning algorithm; After obtaining the output results after training, the output results are tested; Based on the test results, the corresponding battery discharge model is constructed.

2. The method for predicting vehicle driving range as described in claim 1, characterized in that, The process of obtaining the vehicle's first remaining driving range on the current road segment based on vehicle driving history data pre-existing on a big data platform and the current location specifically includes: The vehicle driving history data is preprocessed, including data cleaning, missing data filling, standardization and normalization. Based on the preprocessed vehicle driving history data, a correspondence table between the remaining mileage and location of the current road segment is obtained; Input the current location into the corresponding table to obtain the vehicle's first remaining driving range on the current road segment.

3. The method for predicting vehicle driving range as described in claim 2, characterized in that, The preprocessing also includes dimensionality reduction processing; The preprocessing of the vehicle driving history data specifically includes: The vehicle driving history data is sequentially cleaned, missing data is filled, and standardized and normalized. Based on Pearson correlation coefficient analysis, the normalized vehicle driving history data is subjected to dimensionality reduction processing. Vehicle driving history data with a Pearson coefficient less than a first set value were selected as the dimensionality-reduced vehicle driving history data.

4. The method for predicting vehicle driving range as described in claim 1, characterized in that, The step of predicting the vehicle's remaining driving range based on the weighted influence of the first remaining driving range and the second remaining driving range specifically includes: The first remaining driving range and the second remaining driving range are input into a preset driving range weighted calculation formula to calculate the vehicle's driving range. The weighted calculation formula for the driving range is: Where P represents the vehicle's driving range, and ρ is the historical data influence coefficient, ρ=0.

37. The remaining driving range is the initial range, and μ is the ambient temperature influence coefficient, μ=0.

63. This is the second remaining driving range.

5. A device for predicting vehicle driving range, characterized in that, include: The data acquisition module is used to acquire vehicle data and environmental data on the current road segment. The vehicle data includes battery data, vehicle speed data, and torque data, and the environmental data includes the current location and ambient temperature. The first remaining driving range module is used to obtain the first remaining driving range of the vehicle on the current road segment based on the vehicle driving history data pre-existing on the big data platform and the current location. The optimization coefficient module is used to input the ambient temperature into a preset battery discharge model to obtain optimization coefficients that reflect the influence of ambient temperature on battery discharge capability. An output power module is used to calculate the actual output power of the battery based on the optimization coefficient and the battery data. The second remaining driving range module is used to obtain the second remaining driving range of the vehicle on the current road segment based on the actual output power, the vehicle speed data and the torque data; The driving range prediction module is used to predict the vehicle's driving range based on the weighted influence of the first remaining driving range and the second remaining driving range. The preset battery discharge model is constructed using the following method: Obtain a sample set consisting of different temperatures and the battery discharge efficiency ratio corresponding to each temperature; The sample set is trained based on neural network model technology and deep forest learning algorithm; After obtaining the output results after training, the output results are tested; Based on the test results, the corresponding battery discharge model is constructed.

6. The vehicle range prediction device as described in claim 5, characterized in that, The process of obtaining the vehicle's first remaining driving range on the current road segment based on vehicle driving history data pre-existing on a big data platform and the current location specifically includes: The vehicle driving history data is preprocessed, including data cleaning, missing data filling, standardization and normalization. Based on the preprocessed vehicle driving history data, a correspondence table between the remaining mileage and location of the current road segment is obtained; Input the current location into the corresponding table to obtain the vehicle's first remaining driving range on the current road segment.

7. The vehicle range prediction device as described in claim 6, characterized in that, The preprocessing also includes dimensionality reduction processing; The preprocessing of the vehicle driving history data specifically includes: The vehicle driving history data is sequentially cleaned, missing data is filled, and standardized and normalized. Based on Pearson correlation coefficient analysis, the normalized vehicle driving history data is subjected to dimensionality reduction processing. Vehicle driving history data with a Pearson coefficient less than a first set value were selected as the dimensionality-reduced vehicle driving history data.

8. The vehicle range prediction device as described in claim 5, characterized in that, The step of predicting the vehicle's remaining driving range based on the weighted influence of the first remaining driving range and the second remaining driving range specifically includes: The first remaining driving range and the second remaining driving range are input into a preset driving range weighted calculation formula to calculate the vehicle's driving range. The weighted calculation formula for the driving range is: Where P represents the vehicle's driving range, and ρ is the historical data influence coefficient, ρ=0.

37. The remaining driving range is the initial range, and μ is the ambient temperature influence coefficient, μ=0.

63. This is the second remaining driving range.

Images