Method and system for predicting endurance mileage of hybrid electric vehicle

Abstract

The invention discloses a hybrid electric vehicle endurance mileage prediction method and system, and the method comprises the steps: collecting traditional internal data and non-traditional external data of a vehicle, carrying out the preprocessing of the data, and obtaining the current vehicle state data and external environment data; based on the preprocessed current vehicle state data and external environment data, adopting a Transform structure to construct a short-term prediction model, and predicting the endurance mileage in a future short-term time; on the basis of the preprocessed historical vehicle state data, historical external environment data and historical endurance records, a Transform structure is adopted to construct a long-term prediction model, and the endurance mileage in the future long-term time is predicted; calculating an adaptive weight coefficient according to the real-time driving behavior data and the vehicle state data, and performing weighted fusion on the short-term endurance prediction result and the long-term endurance prediction result to obtain a final endurance mileage prediction value; the accuracy, the stability and the adaptability of endurance prediction can be improved, and the driving experience and the energy management efficiency are improved.

Description

A method and system for predicting the driving range of hybrid electric vehicles Technical Field

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

[0002] In the fields of hybrid electric vehicles (HEVs) and plug-in hybrid electric vehicles (PHEVs), accurately predicting remaining driving range is crucial for enhancing the driving experience, optimizing energy management, and improving the efficiency of intelligent vehicle dispatching. For drivers, accurate range prediction helps them plan their trips rationally and avoid sudden loss of power during driving. For vehicle systems, accurate range prediction provides a scientific basis for switching between the electric motor and engine, thereby improving fuel economy. In the context of intelligent connected vehicles, accurate range prediction can also be effectively integrated with charging / refueling station networks, significantly improving the efficiency of intelligent dispatching.

[0003] Currently, existing methods for predicting the range of hybrid electric vehicles mainly include the following categories:

[0004] 1. Linear model based on battery SOC: This method estimates the driving range by the battery's current state of charge (SOC) and energy consumption rate, and is the most common and simple prediction method. Its advantage lies in its simple calculation and ease of implementation in vehicle systems. However, because the prediction method is too direct and simple, it cannot take into account dynamic factors such as driving style, traffic conditions, and road gradient, resulting in low prediction accuracy.

[0005] 2. Statistical methods using historical data: This method uses historical vehicle driving data and employs regression analysis or time series analysis to predict driving range. Compared to simple linear models, its prediction accuracy is improved and it can adapt to different vehicles. However, it has a strong prediction lag for sudden driving behaviors such as rapid acceleration and sudden braking, and its prediction accuracy still needs to be improved.

[0006] 3. Prediction methods using machine learning: In recent years, machine learning and deep learning techniques such as support vector regression, long short-term memory networks, and variational autoencoders have been widely used in hybrid electric vehicle range prediction. These methods can learn complex nonlinear relationships, improving prediction accuracy to some extent. However, they rely on large amounts of historical data for model training, have insufficient generalization ability for new users, and suffer from high computational complexity, making them difficult to run in real-time on in-vehicle ECUs. Ordinary vehicles cannot meet their computational requirements.

[0007] 4. Prediction methods based on real-time traffic and map information: This method improves prediction accuracy by combining GPS data, map slope, traffic flow, and other information. For example, Google Maps and Tesla have optimized energy consumption calculations using real-time traffic information, and some vehicles also combine map data to predict range changes during navigation. This method considers external environmental factors, which improves prediction accuracy to some extent. However, it relies on high-quality external data, and network conditions and data latency may affect prediction stability. Furthermore, it still uses a single-layer prediction framework and does not incorporate short-term / long-term dynamic adjustment mechanisms, so the prediction effect needs further optimization.

[0008] Therefore, there is an urgent need for a hybrid electric vehicle range prediction method that can comprehensively consider multiple influencing factors, combine the advantages of short-term and long-term forecasting, and improve forecasting accuracy and adaptability to solve existing technical problems. Summary of the Invention

[0009] The present invention aims to solve at least one of the technical problems existing in the prior art, and proposes a method and system for predicting the driving range of hybrid electric vehicles.

[0010] In a first aspect, embodiments of the present invention provide a method for predicting the driving range of a hybrid electric vehicle, including:

[0011] Collect traditional internal data and non-traditional external data of the vehicle, preprocess the data to obtain current vehicle status data and external environment data;

[0012] Based on preprocessed current vehicle status data and external environment data, a short-term prediction model is constructed using a Transformer structure to predict the driving range in the short term. Based on preprocessed historical vehicle status data, historical external environment data, and historical driving range records, a long-term prediction model is constructed using a Transformer structure to predict the driving range in the long term.

[0013] Adaptive weighting coefficients are calculated based on real-time driving behavior data and vehicle status data. The short-term range prediction results and long-term range prediction results are then weighted and fused based on the weighting coefficients to obtain the final range prediction value.

[0014] Furthermore, the vehicle's conventional internal data includes state of charge, power battery voltage, power battery current, power battery temperature, vehicle speed, acceleration, wheel speed, instantaneous fuel consumption, engine power, motor power, engine temperature, and motor temperature; the vehicle's conventional external data includes GPS coordinates, road gradient, traffic flow density, traffic light status, temperature, humidity, wind speed, number of rapid accelerations, number of emergency brakings, and steering wheel angle.

[0015] Furthermore, the data is preprocessed, specifically including time synchronization, outlier handling, feature extraction, and standardization of the collected data; the time synchronization uses an interpolation method to align the data at different sampling frequencies.

[0016] Furthermore, the expression for the short-term prediction model is:

[0017]

[0018] in, This is a short-term range forecast, indicating the range at the current moment. The driving range is predicted based on real-time vehicle status and environmental conditions. It is a short-term forecasting model that uses a Transformer architecture. It is the traditional vehicle data of the current vehicle. This is current external environment data. That is, the training parameters of the short-term prediction model.

[0019] Furthermore, the expression for the long-term prediction model is:

[0020]

[0021] in, This is a short-term range forecast, indicating the range over a given time period. Internally, based on historical driving behavior and predictions of future driving range trends from the external environment, It is a long-term prediction model that uses a Transformer architecture. It is the range record over the past k time steps, including historical range data and range based on short-term predictions; It contains vehicle status data over the past k time steps, including historical vehicle speed, SOC, and acceleration behavior; It contains external environmental data over the past k time steps, including weather changes, road conditions, and traffic flow. These are model parameters.

[0022] Furthermore, the calculation expression for the adaptive weighting coefficient is as follows:

[0023]

[0024] It is a real-time adaptive weighting coefficient. For vehicle driving state function, This is the battery state function. For road and traffic state functions, Energy consumption function; weights , , , Dynamically adjust according to different driving situations.

[0025] Furthermore, the vehicle driving state function It is acceleration, reflecting whether the vehicle accelerates or brakes suddenly. It is vehicle speed, reflecting the vehicle's driving status; It is the maximum threshold of acceleration. It is the maximum threshold of vehicle speed;

[0026] Battery State Function Change in battery state of charge It is the maximum change in battery SOC. Temperature affects battery efficiency. This is the battery's reference temperature. It is the maximum change in temperature;

[0027] Road and traffic state functions It's the road slope. Traffic flow That is the maximum slope. It represents the maximum traffic flow, the specific value of which depends on environmental conditions.

[0028] Energy consumption function Energy consumption This is the maximum energy consumption, which depends on the specific vehicle.

[0029] Furthermore, the weights ; The ; The weights w1, w2, w3, and w4 change dynamically based on the real-time vehicle and environmental conditions.

[0030] Secondly, this invention also discloses a hybrid electric vehicle range prediction system, comprising: a data acquisition and preprocessing module, a short-term and long-term range prediction module, and an adaptive weighted fusion module; wherein:

[0031] The data acquisition and preprocessing module is used to collect traditional internal data and non-traditional external data of the vehicle, and preprocess the data to obtain current vehicle status data and external environment data.

[0032] The short-term and long-term range prediction modules are used to build a short-term prediction model based on preprocessed current vehicle status data and external environment data, using a Transformer structure to predict the range in the short term; and to build a long-term prediction model based on preprocessed historical vehicle status data, historical external environment data and historical range records, using a Transformer structure to predict the range in the long term.

[0033] The adaptive weighted fusion module is used to calculate adaptive weight coefficients based on real-time driving behavior data and vehicle status data, and to perform weighted fusion of short-term range prediction results and long-term range prediction results based on the weight coefficients to obtain the final range prediction value.

[0034] Thirdly, the present invention also discloses an electronic device, comprising:

[0035] One or more processors;

[0036] Memory, used to store one or more programs;

[0037] When the one or more programs are executed by the one or more processors, the one or more processors implement the driving range prediction method.

[0038] This invention discloses a method and system for predicting the driving range of a hybrid electric vehicle. The method includes: collecting traditional internal vehicle data and non-traditional external data; preprocessing the data to obtain current vehicle status data and external environment data; constructing a short-term prediction model using a Transformer structure based on the preprocessed current vehicle status data and external environment data to predict the driving range in the near future; constructing a long-term prediction model using a Transformer structure based on preprocessed historical vehicle status data, historical external environment data, and historical driving range records to predict the driving range in the long future; calculating adaptive weighting coefficients based on real-time driving behavior data and vehicle status data; and weighting and fusing the short-term and long-term driving range prediction results based on the weighting coefficients to obtain the final driving range prediction value. This invention can significantly improve the accuracy, stability, and adaptability of driving range prediction, thereby enhancing the driving experience and energy management efficiency. Attached Figure Description

[0039] Figure 1 is a flowchart illustrating a method for predicting the driving range of a hybrid electric vehicle according to an embodiment of the present invention.

[0040] Figure 2 is a structural block diagram of a hybrid electric vehicle range prediction system provided in an embodiment of the present invention;

[0041] Figure 3 is a structural block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0042] To enable those skilled in the art to better understand the technical solutions of the present invention, exemplary embodiments of the present invention are described below in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0043] Where there is no conflict, the various embodiments of the present invention and the features thereof may be combined with each other.

[0044] As used herein, the term “and / or” includes any and all combinations of one or more related enumerated entries.

[0045] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used herein, the singular forms “a” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded. Terms such as “connected” or “linked” are not limited to physical or mechanical connections but can include electrical connections, whether direct or indirect.

[0046] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having the meaning consistent with their meaning in the context of the relevant art and the invention, and will not be interpreted as having an idealized or overly formal meaning unless expressly so defined herein.

[0047] In the technical solution of this invention, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information all comply with relevant laws and regulations and do not violate public order and good morals. The use of user data in this technical solution follows relevant national laws and regulations (e.g., the "Information Security Technology - Personal Information Security Specification"). For example: appropriate measures are taken for personal information access control; restrictions are imposed on the display of personal information; the purpose of using personal information does not exceed the scope of direct or reasonable association; and explicit identity targeting is eliminated when using personal information to avoid precisely locating a specific individual.

[0048] Current technologies often employ methods based on machine learning and map data to predict driving range. This type of prediction utilizes machine learning or deep learning to optimize range forecasting, and some methods consider non-traditional data such as maps and traffic data. However, existing technologies still rely on a single-layer prediction framework, failing to combine real-time and historical data to improve adaptability. Therefore, the actual prediction performance still needs improvement.

[0049] To address at least one of the technical problems existing in the aforementioned related technologies, the present invention provides a method and system for predicting the driving range of hybrid electric vehicles.

[0050] This embodiment discloses a method for predicting the driving range of a hybrid electric vehicle, as shown in Figure 1, including:

[0051] S100. Collect traditional internal data and non-traditional external data of the vehicle, preprocess the data to obtain current vehicle status data and external environment data;

[0052] In this embodiment, the vehicle's conventional internal data includes state of charge, power battery voltage, power battery current, power battery temperature, vehicle speed, acceleration, wheel speed, instantaneous fuel consumption, engine power, motor power, engine temperature, and motor temperature; the vehicle's conventional external data includes GPS coordinates, road gradient, traffic flow density, traffic light status, temperature, humidity, wind speed, number of rapid accelerations, number of emergency brakings, and steering wheel angle.

[0053] Specifically, traditional vehicle data is collected through the onboard ECU, BMS, CAN bus, or OBD-II interface, including state of charge (SOC), battery voltage (Vb), current (Ib), temperature (Tb), vehicle speed (vt), acceleration (at), wheel speed (ωt), instantaneous fuel consumption (Ft), engine power (Pe), motor power (Pm), engine temperature (Tengine), and motor temperature (Tmotor). The collection frequencies for each data are as follows: 1Hz for SOC, battery voltage (Vb), current (Ib), temperature (Tb), instantaneous fuel consumption (Ft), engine power (Pe), motor power (Pm), engine temperature (Tengine), and motor temperature (Tmotor), and 10Hz for vehicle speed (vt), acceleration (at), and wheel speed (ωt).

[0054] Non-traditional external data is collected through cloud APIs, vehicle-to-everything (V2X) networks, and sensor networks. This includes GPS coordinates (Gt), road slope (Bt), traffic flow density (Tt), traffic light status (St), temperature (Wtemp), humidity (Whumid), wind speed (Wwind), number of rapid accelerations (Daccel), number of emergency brakings (Dbrake), and steering wheel angle (Dsteer). The collection frequencies for each data point are as follows: GPS coordinates (Gt), traffic light status (St), number of rapid accelerations (Daccel), number of emergency brakings (Dbrake), and steering wheel angle (Dsteer) are 1Hz; road slope (Bt) and traffic flow density (Tt) are 0.1Hz; and temperature (Wtemp), humidity (Whumid), and wind speed (Wwind) are 0.01Hz.

[0055] In this embodiment, the data is preprocessed, specifically including time synchronization, outlier handling, feature extraction, and standardization of the collected data; the time synchronization uses an interpolation method to align data with different sampling frequencies.

[0056] Because different data sources have different sampling frequencies, interpolation methods are needed to align the data in time to ensure the consistency of data points. For example, vehicle speed. Sampling is done at 10Hz, while the SOC samples at 1Hz, using a linear interpolation method.

[0057]

[0058] Where vtinterp represents the output value (such as velocity, numerical value, etc.) after interpolation at time t. This represents the original value corresponding to the time on the left. This represents the original value corresponding to the time on the right. t represents the target time (which can be a decimal) for which the interpolation result needs to be calculated. This indicates taking the floor function (rounded down) with respect to t (e.g., when t=2.3). =2; This indicates taking the floor function "rounded up" over t (e.g., when t=2.3). =3).

[0059] In this embodiment, the data will also be cleaned to remove outliers from the dataset, such as temperature data. When the temperature exceeds physical limits (<-40℃ or >85℃), it is set to NaN and padded with the mean of a sliding window. In this embodiment, a low-pass filter is used to smooth the GPS speed signal to avoid errors caused by GPS noise. After the data processing is complete, feature extraction is performed on the preprocessed data to extract features related to the range prediction, and then the data is standardized to meet the model input requirements.

[0060] S200. Based on preprocessed current vehicle status data and external environment data, a short-term prediction model is constructed using a Transformer structure to predict the driving range in the short term. Based on preprocessed historical vehicle status data, historical external environment data, and historical driving range records, a long-term prediction model is constructed using a Transformer structure to predict the driving range in the long term.

[0061] In this embodiment, the expression for the short-term prediction model is:

[0062]

[0063] in, This is a short-term range forecast, indicating the range at the current moment. The driving range is predicted based on real-time vehicle status and environmental conditions. It is a short-term forecasting model that uses a Transformer architecture. It is the traditional vehicle data of the current vehicle. This is current external environment data. That is, the training parameters of the short-term prediction model.

[0064] Short-term prediction is used to calculate the driving range in real time within the next Ts time (e.g., 10-30 minutes). The vehicle's current SOC, motor power, and driving behavior data are read. The road slope information for the next 5-10km is calculated in combination with the map API. The driving range for the next 10-30 minutes is calculated using a short-term LSTM model.

[0065] In this embodiment, the long-term prediction model expression is:

[0066]

[0067] in, This is a short-term range forecast, indicating the range over a given time period. Internally, based on historical driving behavior and predictions of future driving range trends from the external environment, It is a long-term prediction model that uses a Transformer architecture. It is the range record over the past k time steps, including historical range data and range based on short-term predictions; It contains vehicle status data over the past k time steps, including historical vehicle speed, SOC, and acceleration behavior; It contains external environmental data over the past k time steps, including weather changes, road conditions, and traffic flow. These are model parameters.

[0068] Long-term forecasting is used for trend modeling, analyzing driving patterns over past time intervals (1-12 hours) to predict driving range over longer periods. The long-term forecasting model uses a Transformer to capture long-term trends and changes in driving behavior through historical data. It can handle data over longer time periods and infer future driving range based on historical driving patterns and environmental conditions.

[0069] S300. Calculate adaptive weighting coefficients based on real-time driving behavior data and vehicle status data, and perform weighted fusion of short-term range prediction results and long-term range prediction results based on the weighting coefficients to obtain the final range prediction value.

[0070] In this embodiment, the calculation expression for the adaptive weighting coefficient is:

[0071]

[0072] It is a real-time adaptive weighting coefficient. For vehicle driving state function, This is the battery state function. For road and traffic state functions, Energy consumption function; weights , , , Dynamically adjust according to different driving situations.

[0073] In this embodiment, the vehicle driving state function It is acceleration, reflecting whether the vehicle accelerates or brakes suddenly. It is vehicle speed, reflecting the vehicle's driving status; It is the maximum threshold of acceleration. It is the maximum threshold of vehicle speed;

[0074] Battery State Function Change in battery state of charge It is the maximum change in battery SOC. Temperature affects battery efficiency. This is the battery's reference temperature. It is the maximum change in temperature;

[0075] Road and traffic state functions It's the road slope. Traffic flow That is the maximum slope. It represents the maximum traffic flow, the specific value of which depends on environmental conditions.

[0076] Energy consumption function Energy consumption This is the maximum energy consumption, which depends on the specific vehicle.

[0077] Specifically, the introduction of adaptive weighting is to intelligently adjust the proportion of short-term and long-term predictions under different driving scenarios. For driving situations with large dynamic changes (acceleration, deceleration), short-term predictions can better reflect real-time range changes; while under relatively stable driving conditions, long-term predictions can provide more stable range expectations.

[0078] In this embodiment, the weight ; The ; The weights w1, w2, w3, and w4 dynamically change based on real-time vehicle and environmental conditions. This dynamic adjustment of weights w1, w2, w3, and w4 makes the weighting coefficient more accurate. Based on the functions of the factors designed above and the dynamically adjusted weights, the final weighting coefficient α is automatically updated. This results in a more intelligent combination of short-term and long-term predictions, accurately predicting the driving range of hybrid vehicles.

[0079] In this embodiment, at preset intervals, the parameters of the short-term prediction model and the long-term prediction model are updated using the actual driving range data within that period. The gradient descent algorithm is used to adjust the model parameters to minimize the mean square error between the model prediction value and the actual driving range, thereby continuously optimizing the model performance.

[0080] This embodiment discloses a method for predicting the driving range of a hybrid electric vehicle. The method includes: collecting traditional internal data and non-traditional external data of the vehicle; preprocessing the data to obtain current vehicle status data and external environment data; constructing a short-term prediction model using a Transformer structure based on the preprocessed current vehicle status data and external environment data to predict the driving range in the short term; constructing a long-term prediction model using a Transformer structure based on preprocessed historical vehicle status data, historical external environment data, and historical driving range records to predict the driving range in the long term; calculating adaptive weight coefficients based on real-time driving behavior data and vehicle status data; and weighting and fusing the short-term and long-term driving range prediction results based on the weight coefficients to obtain the final driving range prediction value. This invention can significantly improve the accuracy, stability, and adaptability of driving range prediction, and enhance the driving experience and energy management efficiency.

[0081] Based on the same inventive concept, this embodiment of the invention also provides a hybrid electric vehicle range prediction system, employing the aforementioned range prediction method, as shown in Figure 2, including: a data acquisition and preprocessing module, a short-term and long-term range prediction module, and an adaptive weighted fusion module; wherein:

[0082] The data acquisition and preprocessing module is used to collect traditional internal data and non-traditional external data of the vehicle, and preprocess the data to obtain current vehicle status data and external environment data.

[0083] The short-term and long-term range prediction modules are used to build a short-term prediction model based on preprocessed current vehicle status data and external environment data, using a Transformer structure to predict the range in the short term; and to build a long-term prediction model based on preprocessed historical vehicle status data, historical external environment data and historical range records, using a Transformer structure to predict the range in the long term.

[0084] The adaptive weighted fusion module is used to calculate adaptive weight coefficients based on real-time driving behavior data and vehicle status data, and to perform weighted fusion of short-term range prediction results and long-term range prediction results based on the weight coefficients to obtain the final range prediction value.

[0085] The specific working methods of the data acquisition and preprocessing module, the short-term and long-term range prediction module, and the adaptive weighted fusion module have been described in detail in the above prediction method, and will not be repeated here in this embodiment.

[0086] Based on the same inventive concept, this invention also provides an electronic device. Figure 3 is a structural block diagram of an electronic device provided by an embodiment of this invention. As shown in Figure 3, the electronic device provided by this invention includes: one or more processors 101, a memory 102, and one or more I / O interfaces 103. The memory 102 stores one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement any of the prediction methods described in the above embodiments; the one or more I / O interfaces 103 are connected between the processor and the memory, configured to enable information interaction between the processor and the memory.

[0087] The processor 101 is a device with data processing capabilities, including but not limited to a central processing unit (CPU); the memory 102 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and flash memory (FLASH); the I / O interface (read / write interface) 103 is connected between the processor 101 and the memory 102, and can realize information interaction between the processor 101 and the memory 102, including but not limited to a data bus (Bus).

[0088] In some embodiments, the processor 101, memory 102, and I / O interface 103 are interconnected via bus 104, and thus connected to other components of the computing device.

[0089] In some embodiments, the one or more processors 101 include a field-programmable gate array.

[0090] This invention also provides a computer-readable medium. The computer-readable medium stores a computer program, which, when executed by a processor, implements the steps of any of the prediction methods described in the above embodiments. The computer-readable storage medium may be volatile or non-volatile.

[0091] This invention also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code, wherein when the computer-readable code is run in the processor of an electronic device, the processor in the electronic device executes the above-described prediction method.

[0092] Those skilled in the art will understand that all or some of the steps, systems, and apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable storage medium, which may include computer storage media (or non-transitory media) and communication media (or transient media).

[0093] As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable program instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technologies, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is known to those skilled in the art that communication media typically contain computer-readable program instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0094] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0095] The computer program instructions used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions. This electronic circuitry can execute the computer-readable program instructions to implement various aspects of the invention.

[0096] The computer program product described herein can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0097] Various aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0098] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0099] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0100] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown 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 the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may 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.

[0101] Example embodiments have been disclosed herein, and while specific terminology has been used, it is for illustrative purposes only and should be construed as such, and is not intended to be limiting. In some instances, it will be apparent to those skilled in the art that features, characteristics, and / or elements described in conjunction with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in conjunction with other embodiments, unless otherwise expressly indicated. Therefore, those skilled in the art will understand that various changes in form and detail may be made without departing from the scope of the invention as set forth in the appended claims.

Claims

1. A method for predicting the driving range of a hybrid electric vehicle, characterized in that, include: Collect traditional internal data and non-traditional external data of the vehicle, preprocess the data to obtain current vehicle status data and external environment data; Based on the preprocessed current vehicle status data and external environment data, a short-term prediction model is constructed using the Transformer structure to predict the driving range in the near future. Based on preprocessed historical vehicle status data, historical external environment data, and historical range records, a long-term prediction model is constructed using a Transformer structure to predict the driving range over a long period of time. Adaptive weighting coefficients are calculated based on real-time driving behavior data and vehicle status data. The short-term and long-term driving range prediction results are then weighted and fused based on these weighting coefficients to obtain the final driving range prediction value.

2. The driving range prediction method according to claim 1, characterized in that, The vehicle's conventional internal data includes state of charge, power battery voltage, power battery current, power battery temperature, vehicle speed, acceleration, wheel speed, instantaneous fuel consumption, engine power, motor power, engine temperature, and motor temperature; the vehicle's conventional external data includes GPS coordinates, road gradient, traffic flow density, traffic light status, temperature, humidity, wind speed, number of rapid accelerations, number of emergency brakings, and steering wheel angle.

3. The driving range prediction method according to claim 1, characterized in that, The data is preprocessed, specifically including time synchronization, outlier handling, feature extraction, and standardization of the collected data; the time synchronization uses an interpolation method to align the data at different sampling frequencies.

4. The driving range prediction method according to claim 1, characterized in that, The expression for the short-term prediction model is: in, This is a short-term range forecast, indicating the range at the current moment. The driving range is predicted based on real-time vehicle status and environmental conditions. It is a short-term forecasting model that uses a Transformer architecture. It is the traditional vehicle data of the current vehicle. This is current external environment data. That is, the training parameters of the short-term prediction model.

5. The driving range prediction method according to claim 1, characterized in that, The expression for the long-term prediction model is: in, This is a short-term range forecast, indicating the range over a given time period. Internally, based on historical driving behavior and predictions of future driving range trends from the external environment, It is a long-term prediction model that uses a Transformer architecture. It is the range record over the past k time steps, including historical range data and range based on short-term predictions; It contains vehicle status data over the past k time steps, including historical vehicle speed, SOC, and acceleration behavior; It contains external environmental data over the past k time steps, including weather changes, road conditions, and traffic flow. These are model parameters.

6. The driving range prediction method according to claim 1, characterized in that, The formula for calculating the adaptive weighting coefficient is as follows: It is a real-time adaptive weighting coefficient. For vehicle driving state function, This is the battery state function. For road and traffic state functions, Energy consumption function; weights 、 、 、 Dynamically adjust according to different driving situations.

7. The driving range prediction method according to claim 6, characterized in that, Vehicle driving state function It is acceleration, reflecting whether the vehicle accelerates or brakes suddenly. It is vehicle speed, reflecting the vehicle's driving status; It is the maximum threshold of acceleration. It is the maximum threshold of vehicle speed; battery state function Change in battery state of charge It is the maximum change in battery SOC. Temperature affects battery efficiency. This is the battery's reference temperature. It is the maximum change in temperature; road and traffic state function It's the road slope. Traffic flow That is the maximum slope. This represents the maximum traffic flow, the specific value of which depends on environmental conditions; energy consumption function. Energy consumption This is the maximum energy consumption, which depends on the specific vehicle.

8. The driving range prediction method according to claim 6, characterized in that, The weight ； The ； ； The weights w1, w2, w3, and w4 change dynamically based on the real-time vehicle and environmental conditions.

9. A hybrid electric vehicle range prediction system, employing the range prediction method described in any one of claims 1-8, characterized in that, include: The system comprises a data acquisition and preprocessing module, a short-term and long-term range prediction module, and an adaptive weighted fusion module. Specifically: the data acquisition and preprocessing module collects traditional internal vehicle data and non-traditional external data, preprocesses the data to obtain current vehicle status data and external environment data; the short-term and long-term range prediction module, based on the preprocessed current vehicle status data and external environment data, constructs a short-term prediction model using a Transformer structure to predict the range in the short term; and constructs a long-term prediction model using a Transformer structure based on preprocessed historical vehicle status data, historical external environment data, and historical range records to predict the range in the long term; the adaptive weighted fusion module calculates adaptive weight coefficients based on real-time driving behavior data and vehicle status data, and weights and fuses the short-term and long-term range prediction results based on these weight coefficients to obtain the final predicted range value.

10. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 8.

Images