Hybrid vehicle control method and device, hybrid vehicle and storage medium

Abstract

The invention relates to the technical field of vehicles, in particular to a hybrid power vehicle control method and device, a hybrid power vehicle and a storage medium, and the method comprises the steps that related data of a current vehicle are obtained, and the related data comprise at least one of working conditions, state data, surrounding environment data and driving behavior data of a driver; a control strategy of the vehicle is generated based on the related data and the target priority, the vehicle is controlled to execute the target action based on the control strategy, and the control strategy comprises at least one of an energy management strategy, an emission optimization strategy, a smoothness control strategy and a personalized driving strategy; after the vehicle executes the target action, feedback data of the vehicle are obtained, and a control strategy of the vehicle is corrected based on the feedback data. Therefore, the problems that in the prior art, a vehicle control strategy is difficult to meet adaptation of different complex driving environments, driving experience smoothness, low emission under extreme working conditions, individual requirements of drivers and the like are solved.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a hybrid vehicle control method, device, hybrid vehicle, and storage medium. Background Technology

[0002] Hybrid vehicles combine the advantages of internal combustion engines and electric motors, and through an intelligent management system, they can flexibly switch or work together according to driving conditions to achieve energy conservation and emission reduction.

[0003] Existing hybrid power systems typically employ rule-based energy management strategies, such as threshold control based on parameters like vehicle speed, engine speed, and battery charge, as well as control methods based on fuzzy logic or neural networks. While these methods achieve some degree of rational energy utilization and emission reduction, they still have significant shortcomings, including: energy management strategies rely on fixed rules or simple predictive models, making it difficult to simultaneously meet the needs of adapting to complex driving environments, ensuring smooth driving experience, achieving low emissions under extreme conditions, and meeting the personalized needs of drivers. Summary of the Invention

[0004] This application provides a hybrid vehicle control method, device, hybrid vehicle, and storage medium to solve the problems in related technologies where vehicle control strategies are difficult to meet the needs of different complex driving environments, driving experience smoothness, low emissions under extreme conditions, and personalized driver requirements.

[0005] The first aspect of this application provides a hybrid vehicle control method, comprising the following steps: acquiring relevant data of the current vehicle, wherein the relevant data includes at least one of operating conditions, status data, surrounding environment data, and driver driving behavior data; generating a vehicle control strategy based on the relevant data and target priorities, and controlling the vehicle to perform a target action based on the control strategy, wherein the control strategy includes at least one of energy management strategy, emission optimization strategy, ride comfort control strategy, and personalized driving strategy; and after the vehicle performs the target action, acquiring feedback data of the vehicle, and correcting the vehicle control strategy based on the feedback data.

[0006] Optionally, a vehicle control strategy is generated based on relevant data and target priorities, including: determining the core control objective of the current vehicle based on the operating conditions; determining the target execution module of the vehicle based on the core control objective and target priorities, wherein the target execution module includes at least one of an energy management module, an emission optimization module, a ride comfort control module, and a personalized driving module, and the target execution module outputs a corresponding control strategy based on relevant data; and generating the vehicle control strategy based on the core control objective, target priorities, and the control strategy output by the target execution module.

[0007] Optionally, after determining the vehicle's target execution module based on the core control objective and target priority, the method further includes: if the target execution module includes an energy management module and a ride comfort control module, then the vehicle's control strategy is modified based on a preset torque transition algorithm; if the target execution module includes an emission optimization module and a personalized driving module, then the vehicle's control strategy is modified based on an emission dynamic balance model.

[0008] Optionally, the energy management module includes: inputting relevant data into a target prediction model, and the target prediction model outputting the vehicle's energy management strategy, wherein the energy management strategy includes the operating status of the vehicle's energy equipment and the power output of the engine and electric motor.

[0009] Optionally, the ride comfort control module includes: determining a ride comfort control strategy for the vehicle based on relevant data and a target control algorithm, wherein the ride comfort control strategy includes torque compensation and torque fluctuation limitation for the engine and electric motor.

[0010] Optionally, the emission optimization module includes: determining the engine's operating conditions based on relevant data, and determining the vehicle's emission optimization strategy based on the engine's operating conditions and relevant data, wherein the emission optimization strategy includes control parameters of at least one of the vehicle's exhaust gas recirculation system, engine, and turbocharging system.

[0011] Optionally, the personalized driving module includes: determining the driver's driving habit data based on relevant data and target algorithms, and determining the vehicle's personalized driving strategy based on the driving habit data and environmental data, wherein the personalized driving strategy includes the power distribution between the engine and the electric motor, driving modes, and personalized settings.

[0012] A second aspect of this application provides a hybrid vehicle control device, comprising: an acquisition module for acquiring relevant data of the current vehicle, wherein the relevant data includes at least one of operating conditions, status data, surrounding environment data, and driver driving behavior data; a generation module for generating a vehicle control strategy based on the relevant data and target priorities, and controlling the vehicle to perform a target action based on the control strategy, wherein the control strategy includes at least one of energy management strategy, emission optimization strategy, ride comfort control strategy, and personalized driving strategy; and a correction module for acquiring feedback data of the vehicle after the vehicle performs the target action, and correcting the vehicle control strategy based on the feedback data.

[0013] Optionally, the generation module is further configured to: determine the core control objective of the current vehicle based on the operating conditions; determine the target execution module of the vehicle based on the core control objective and the target priority, wherein the target execution module includes at least one of an energy management module, an emission optimization module, a ride comfort control module, and a personalized driving module, and the target execution module outputs a corresponding control strategy based on relevant data; and generate the vehicle's control strategy based on the core control objective, the target priority, and the control strategy output by the target execution module.

[0014] Optionally, it further includes: a first correction module, used to correct the vehicle's control strategy based on a preset torque transition algorithm if the target execution module includes an energy management module and a ride comfort control module, after determining the vehicle's target execution module based on the core control target and target priority; and to correct the vehicle's control strategy based on an emission dynamic balance model if the target execution module includes an emission optimization module and a personalized driving module.

[0015] Optionally, the energy management module includes: inputting relevant data into a target prediction model, and the target prediction model outputting the vehicle's energy management strategy, wherein the energy management strategy includes the operating status of the vehicle's energy equipment and the power output of the engine and electric motor.

[0016] Optionally, the ride comfort control module includes: determining a ride comfort control strategy for the vehicle based on relevant data and a target control algorithm, wherein the ride comfort control strategy includes torque compensation and torque fluctuation limitation for the engine and electric motor.

[0017] Optionally, the emission optimization module includes: determining the engine's operating conditions based on relevant data, and determining the vehicle's emission optimization strategy based on the engine's operating conditions and relevant data, wherein the emission optimization strategy includes control parameters of at least one of the vehicle's exhaust gas recirculation system, engine, and turbocharging system.

[0018] Optionally, the personalized driving module includes: determining the driver's driving habit data based on relevant data and target algorithms, and determining the vehicle's personalized driving strategy based on the driving habit data and environmental data, wherein the personalized driving strategy includes the power distribution between the engine and the electric motor, driving modes, and personalized settings.

[0019] A third aspect of this application provides a hybrid vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to perform the hybrid vehicle control method as described in the above embodiments.

[0020] A fourth aspect of this application provides a computer-readable storage medium having a computer program or instructions stored thereon, which are executed by a processor to perform the hybrid vehicle control method as described above.

[0021] A fifth aspect of this application provides a computer program product, including a computer program or instructions, which, when executed, implement the hybrid vehicle control method as described in the above embodiments.

[0022] Therefore, this application has at least the following beneficial effects: This application's embodiments can generate a vehicle control strategy based on relevant data and priority settings of the hybrid vehicle, and control the vehicle to execute target actions based on the control strategy. By comprehensively considering various data and strategies, a unified control scheme for the vehicle is formed to adapt to complex scenarios, ensuring that the control strategy balances energy efficiency, smoothness, emissions, and personalization, thereby improving the vehicle's overall performance. After the vehicle executes the target action, feedback data is obtained from the vehicle, and the control strategy is corrected based on the feedback data to improve the adaptability of the control strategy. Thus, it solves the technical problems in related technologies such as adapting to complex driving environments, ensuring smooth driving experience, achieving low emissions under extreme conditions, and meeting the personalized needs of drivers.

[0023] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0024] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of a hybrid vehicle control method provided according to an embodiment of this application; Figure 2 This is an architecture diagram for a hybrid vehicle. Figure 3 This is a flowchart illustrating the execution of a personalized driving mode according to an embodiment of this application. Figure 4 This is an example diagram of a hybrid vehicle control device provided according to an embodiment of this application; Figure 5 This is a schematic diagram of the structure of a hybrid vehicle provided according to an embodiment of this application. Detailed Implementation

[0025] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0026] Existing hybrid power systems typically employ rule-based energy management strategies, such as threshold control based on parameters like vehicle speed, engine speed, and battery charge, as well as control methods based on fuzzy logic or neural networks. While these methods have achieved some degree of rational energy utilization and emission reduction, many challenges remain.

[0027] Existing problems (pain points): 1. Insufficiently intelligent energy management strategies: Existing hybrid power systems often rely on fixed rules or simple predictive models for energy management, making it difficult to adapt to complex and changing driving environments and habits. This results in inefficient power distribution between the engine and electric motor under certain operating conditions, leading to low energy utilization efficiency.

[0028] 2. Poor driving experience: Due to the less-than-smooth switching between the engine and electric motor, power interruptions or torque fluctuations may occur during driving, affecting driving comfort and safety. Furthermore, frequent mode switching may increase component wear and tear and the failure rate.

[0029] 3. Emissions performance needs improvement: Although hybrid vehicles have made significant improvements in emissions compared to traditional fuel vehicles, engine emissions may still exceed standards under certain extreme conditions, such as cold starts or rapid acceleration.

[0030] 4. Difficulty in meeting personalized needs: Different drivers have different driving habits and environmental conditions, but existing hybrid power systems often adopt a uniform control strategy, which makes it difficult to meet personalized needs.

[0031] Therefore, this application provides a hybrid vehicle control method to solve at least one of the above-mentioned technical problems.

[0032] Specifically, Figure 1 This is a flowchart illustrating a hybrid vehicle control method provided in an embodiment of this application. The architecture of the hybrid vehicle in this embodiment is as follows: Figure 2 As shown.

[0033] like Figure 1 As shown, the hybrid vehicle control method includes the following steps: In step S101, relevant data of the current vehicle are acquired, including at least one of operating conditions, status data, surrounding environment data, and driver driving behavior data.

[0034] The operating conditions include starting, acceleration, cruising, and braking. Status data includes battery charge, voltage, current, and temperature; engine speed, load, intake air temperature, and exhaust air temperature; surrounding environmental data includes road condition information (such as traffic congestion and speed limits) and weather information (such as temperature, humidity, and rainfall); driving behavior data includes accelerator pedal pressure, braking force, and steering wheel angle. The relevant data can be collected by sensors. Key parameters can be collected at a frequency of 100ms / time and non-key parameters at a frequency of 1min / time, which not only meets the needs of various solutions but also reduces hardware energy consumption.

[0035] The energy management module requires high-frequency data (100ms / time), while the personalized driving mode requires low-frequency long-term data (1min / time average). If high-frequency data is collected, it will increase the system load. Therefore, a layered data collection strategy is adopted. Key parameters (vehicle speed, torque demand) are collected at high frequency, while non-key parameters (driving habit statistics) are collected at low frequency and summarized in stages. This satisfies the needs of each solution and reduces hardware energy consumption.

[0036] In step S102, a vehicle control strategy is generated based on relevant data and target priorities, and the vehicle is controlled to perform target actions based on the control strategy. The control strategy includes at least one of energy management strategy, emission optimization strategy, ride comfort control strategy and personalized driving strategy.

[0037] The priority of the targets can be set according to the specific circumstances, such as safety > emissions > energy efficiency > individuality.

[0038] It is understood that the embodiments of this application can generate a vehicle control strategy based on relevant data and target priorities, and control the vehicle to perform target actions based on the control strategy. By comprehensively considering various data and strategies, a unified control scheme for the vehicle can be formed to adapt to complex scenarios, ensuring that the control strategy takes into account energy efficiency, smoothness, emissions and personalization, thereby improving the overall performance of the vehicle.

[0039] In this embodiment, a vehicle control strategy is generated based on relevant data and target priorities, including: determining the core control objective of the current vehicle based on the operating conditions; determining the target execution module of the vehicle based on the core control objective and target priorities, wherein the target execution module includes at least one of an energy management module, an emission optimization module, a ride comfort control module, and a personalized driving module, and the target execution module outputs a corresponding control strategy based on relevant data; and generating the vehicle control strategy based on the core control objective, target priorities, and the control strategy output by the target execution module.

[0040] Among them, the core control target and the target execution module can be obtained by querying based on the pre-set correspondence.

[0041] It is understood that the embodiments of this application can determine the core objective of the current vehicle based on the operating conditions, and determine the target execution module of the vehicle based on the core control objective and the target priority. The target execution module outputs the corresponding control strategy based on relevant data. The vehicle's control strategy is generated based on the core control objective, the target priority and the control strategy output by the target execution module, ensuring that the control strategy focuses on the core requirements and ensuring the rationality of multi-module collaboration.

[0042] For example, during cold start, the target execution modules include an emissions optimization module (EGR (Exhaust Gas Recirculation) system shutdown and three-way catalytic converter preheating) and an energy management module (electric motor priority drive to avoid low-load and inefficient engine operation); during rapid acceleration, the target execution modules include a smoothness control module (MPC (Model Predictive Control) algorithm predicts torque demand and coordinates the power superposition of the engine and electric motor) and a personalized driving module (adjusting the power response speed according to the driver's habits); during cruising, the target execution strategies include an energy management module (optimizing the power distribution between the engine and electric motor to keep the engine in its high-efficiency range) and an emissions optimization module (intelligently activating the EGR system to reduce NOx emissions).

[0043] In this embodiment, after determining the vehicle's target execution module based on the core control objective and target priority, the method further includes: if the target execution module includes an energy management module and a ride comfort control module, then the vehicle's control strategy is corrected based on a preset torque transition algorithm; if the target execution module includes an emission optimization module and a personalized driving module, then the vehicle's control strategy is corrected based on an emission dynamic balance model.

[0044] Since there may be instruction conflicts between the strategies output by different modules, the embodiments of this application can coordinate between different modules when conflicts occur in the instructions of the modules.

[0045] Specifically, the energy management module, in pursuit of energy efficiency, may require the engine to switch power rapidly; while smoothness control requires slow torque adjustments to avoid fluctuations. A torque transition algorithm is added to the HCU (Hybrid Control Unit). The target power distribution value output by the energy management system needs to be processed by the MPC algorithm of the smoothness control module to generate a "stepped torque change curve" (e.g., when the engine torque increases from 100Nm to 200Nm, it increases in 5 steps, with each step spaced 50ms apart). This satisfies energy efficiency requirements while avoiding power interruption. The emissions optimization module is adapted to the parameters of personalized driving. Aggressive driving mode requires high engine power output, which may lead to increased emissions; emissions optimization requires limiting engine load, which may affect power response. Establish an emissions-dynamic balance model and dynamically adjust it based on driver habit labels and real-time emissions data: for aggressive drivers, briefly relax the emissions threshold during rapid acceleration (but do not exceed the regulatory standards), and activate the emissions after-treatment system (such as the efficient operation of the three-way catalytic converter); for stable drivers, prioritize maintaining low emission conditions and optimize energy efficiency simultaneously.

[0046] In this embodiment of the application, the energy management module includes: inputting relevant data into a target prediction model, and the target prediction model outputting the vehicle's energy management strategy, wherein the energy management strategy includes the operating status of the vehicle's energy equipment and the power output of the engine and electric motor.

[0047] Specifically, the energy management module (also referred to as the energy management system) of this application aims to achieve efficient monitoring, management, and optimization of energy by integrating advanced sensors, data analysis algorithms, and intelligent control strategies. The specific implementation steps are as follows: 1. System architecture.

[0048] The energy management system consists of a data acquisition module, a data analysis module, an intelligent control module, and a user interface module.

[0049] Data acquisition module: Responsible for collecting real-time data from various energy devices and systems, including key parameters such as power consumption, voltage, current, and temperature. This data is collected through high-precision sensors and smart meters, and transmitted to the data analysis module via a communication network.

[0050] Data Analysis Module: This module processes and analyzes the collected data, including data cleaning, anomaly detection, and trend prediction. By employing big data analytics and machine learning algorithms, it can identify potential problems in the energy system, propose optimization suggestions, and predict future energy demand.

[0051] Intelligent Control Module: Based on the results of the data analysis module, the intelligent control module can automatically adjust the operating status of energy equipment and systems to maximize energy utilization and minimize emissions. It can intelligently schedule and control energy according to real-time energy demand and system performance.

[0052] User Interface Module: Provides users with an intuitive interface and visual reports, displaying the real-time status, historical data, and optimization suggestions of the energy system. Users can perform operations such as parameter settings, mode selection, and alarm viewing through the interface.

[0053] 2. Key technologies.

[0054] High-precision data acquisition technology: Employing advanced sensors and intelligent instruments, this technology enables high-precision data acquisition from energy equipment and systems. These sensors feature high precision, high reliability, and low power consumption, ensuring data accuracy and real-time performance.

[0055] Big data analytics and machine learning algorithms: These algorithms process and analyze collected data. They can discover patterns and trends in the data, predict future energy demand, propose optimization suggestions, and automatically adjust the operating status of energy equipment and systems.

[0056] Intelligent control strategies: Based on data analysis, intelligent control strategies are developed. These strategies can automatically adjust the operating status of energy equipment and systems according to real-time energy demand and system performance to maximize energy utilization and minimize emissions. Simultaneously, the strategies can also consider users' individual needs and changes in the external environment, ensuring the system's flexibility and adaptability.

[0057] 3. Functional features.

[0058] Real-time monitoring and early warning: The system can monitor the status of energy equipment and systems in real time, including key parameters such as power, voltage, and current. When an abnormality or fault occurs, the system will immediately issue an early warning signal and prompt the user to take appropriate measures.

[0059] Energy optimization and scheduling: Through big data analytics and machine learning algorithms, the system can identify potential problems in the energy system, propose optimization suggestions, and automatically adjust the operating status of energy equipment and systems. This helps to maximize energy utilization and minimize emissions.

[0060] User customization and optimization: The system supports user-defined parameters and modes to meet the personalized needs of different users. Furthermore, the system can automatically adjust optimization strategies based on user feedback and changes in the external environment, ensuring the system's flexibility and adaptability.

[0061] Visualized Reports and Data Analysis: The system provides users with intuitive visual reports and data analysis tools, displaying the real-time status, historical data, and optimization suggestions of the energy system. This helps users better understand the performance and optimization effects of the energy system.

[0062] During vehicle idling and acceleration, when the MCU detects that the engine is running and the high-voltage battery is discharging, the window displays: discharge capacity, available capacity, current battery discharge power, and discharge duration. When the MCU detects that the engine is not running and the high-voltage battery is charging, the display interface will show: capacity, amount to be charged, battery charging power, and charging duration.

[0063] ; Where W represents the charge or discharge amount, SOC1 represents the current battery level, and SOC... 下限 This indicates the lower limit of the power consumption, and K represents the unit power consumption.

[0064] ; Where T represents the charging or discharging duration, and P represents the charging or discharging power.

[0065] Sensor networks are used to collect vehicle status data, including vehicle speed, engine speed, and battery level.

[0066] By analyzing user behavior, we can identify and learn drivers' driving habits, such as acceleration and braking.

[0067] It integrates an environmental sensing module to monitor environmental conditions such as road conditions and temperature in real time.

[0068] Based on the above data, predictive algorithms and machine learning models are used to adjust the power output of the engine and electric motor in real time.

[0069] In this embodiment of the application, the ride comfort control module includes: determining a ride comfort control strategy for the vehicle based on relevant data and a target control algorithm, wherein the ride comfort control strategy includes torque compensation and torque fluctuation limitation for the engine and electric motor.

[0070] Specifically, the smoothness control module in this application employs advanced control algorithms, such as Model Predictive Control (MPC) or Sliding Mode Control (SMC), to accurately predict and coordinate the starting, stopping, and power adjustment of the engine and electric motor.

[0071] 1. Model Predictive Control (MPC).

[0072] (1) Working principle.

[0073] Model-based control (MPC) is a control strategy that uses a dynamic model of the system to predict future states and determines the optimal control input sequence through optimization algorithms. Within each control cycle, MPC calculates a set of control inputs based on the current state, the prediction model, and constraints, ensuring that the system's state over a future period is as close as possible to the desired state.

[0074] (2) Technical characteristics.

[0075] Predictability: MPC can predict the future state of a system and perform optimized control based on the prediction results.

[0076] Optimization: MPC uses optimization algorithms to determine the optimal control input sequence in order to achieve the control objective.

[0077] Constraint handling: MPC can handle various constraints, such as input constraints and state constraints, to ensure the safety and stability of the system.

[0078] (3) Implementation steps.

[0079] System modeling: Establishing a dynamic model of the system to describe the state transition relationships of the system.

[0080] Predictive model: Based on the system model, a predictive model is built to predict the future state of the system.

[0081] Optimization solution: Based on the prediction model and constraints, use optimization algorithms to solve for the optimal control input sequence.

[0082] Control input implementation: Apply the optimized first control input to the system to achieve real-time control.

[0083] Status feedback and update: The current state of the system is estimated in real time using sensor data, and the status information is fed back to the MPC controller for the next round of prediction and optimization.

[0084] 2. Sliding mode control (SMC).

[0085] (1) Working principle.

[0086] Sliding Mode Control (SMC) is a nonlinear control strategy that designs a sliding surface, allowing the system state to slide along the surface, thereby achieving system stability and desired dynamic performance. SMC achieves this by switching control laws, enabling the system state to rapidly approach the sliding surface from its initial state and maintain stable operation there.

[0087] (2) Technical characteristics.

[0088] Robustness: SMC is highly robust to system uncertainties and external disturbances, and can maintain system stability in the presence of model errors and disturbances.

[0089] Simplicity: SMC is relatively simple to implement and does not rely on precise system modeling, thus it has good adaptability in practical applications.

[0090] High-frequency switching issue: However, the sign function in SMC causes rapid switching of the control signal, resulting in high-frequency oscillations (i.e., "chickening"). This affects the control performance, and requires special handling, especially in practical applications.

[0091] (3) Implementation steps.

[0092] System modeling: Establishing an accurate mathematical model for the system to describe its dynamic behavior.

[0093] Selecting a sliding surface: Choose a suitable sliding surface based on system characteristics and control objectives.

[0094] Design a switching control law: Design a switching control law to make the system state quickly approach the sliding surface from the initial state.

[0095] Design a sliding mode control law: Once the system state enters the sliding surface, design a sliding mode control law to ensure that the system operates stably along the sliding surface.

[0096] Control Implementation: The designed SMC controller is applied to the system to achieve real-time control. Specific parameters in the HCU and ECU strategies vary depending on the vehicle model; therefore, modifications must be made based on the actual vehicle type and professional requirements such as NVH (Noise, Vibration, and Harshness).

[0097] Design a coordinated control strategy for the engine and electric motor to ensure smooth mode switching. Use control algorithms to predict and adjust the torque output of the engine and electric motor to reduce power interruption and torque fluctuation. Monitor and adjust control parameters in real time to adapt to the needs of different driving conditions.

[0098] In this embodiment of the application, the emission optimization module includes: determining the engine operating condition based on relevant data, and determining the vehicle emission optimization strategy based on the engine operating condition and relevant data, wherein the emission optimization strategy includes control parameters of at least one of the vehicle's exhaust gas recirculation system, engine, and turbocharging system.

[0099] Specifically, the emission optimization module in this application embodiment combines in-depth research on engine operating conditions and emission characteristics to propose targeted control strategies, utilizing technologies such as EGR and turbocharging to reduce emissions and improve engine efficiency.

[0100] 1. Targeted control strategies.

[0101] Engine operating status monitoring and analysis: Utilizing advanced sensor technology to monitor the engine's operating status in real time, including parameters such as speed, load, intake air temperature, and exhaust air temperature.

[0102] Data analysis identifies the emission characteristics of engines under different operating conditions. For example, gasoline engines mainly emit carbon monoxide (CO), hydrocarbons (HC), and nitrogen oxides (NOx), while diesel engines mainly emit particulate matter (PM) and NOx.

[0103] Emission control strategy development: Develop targeted emission control strategies based on engine emission characteristics and operating conditions. For example, in gasoline engines, technologies such as oxygen sensors and three-way catalytic converters can be used to reduce CO, HC, and NOx emissions.

[0104] In diesel engines, technologies such as high-pressure common rail fuel systems, particulate filters (DPF), and urea injection devices (for SCR systems) can be used to reduce PM and NOx emissions.

[0105] 2. Exhaust gas recirculation technology.

[0106] Working principle: EGR technology reintroduces a portion of the combusted exhaust gas into the intake system, mixes it with fresh air, and then re-enters the cylinder for combustion. This reduces the temperature in the combustion chamber, thereby decreasing NOx formation.

[0107] Technical features: An EGR system typically consists of an EGR valve, an EGR cooler, and a control system. The EGR valve controls the amount of exhaust gas recirculated, while the EGR cooler reduces the temperature of the exhaust gas to improve its recirculation efficiency.

[0108] EGR technology can significantly reduce NOx emissions while improving engine fuel economy. However, it should be noted that the EGR system will temporarily shut down under certain operating conditions such as engine start-up, idling, low temperature, or low speed to protect engine performance.

[0109] Implementation and Optimization: Implementing an EGR system requires precise control of the exhaust gas recirculation rate to avoid adverse effects on engine performance. This is typically achieved through intelligent adjustments by the electronic control unit based on engine operating conditions.

[0110] To further optimize the performance of the EGR system, adjustments and optimizations can be made to the opening degree of the EGR valve and the efficiency of the EGR cooler.

[0111] (2) Turbocharging technology.

[0112] How it works: Turbocharging technology uses the exhaust gases produced by an internal combustion engine to drive an air compressor (i.e., a turbine), thereby increasing the engine's intake air volume. This can improve engine power and torque, while optimizing fuel economy and reducing harmful emissions.

[0113] Technical characteristics: A turbocharging system typically consists of a turbocharger, an intercooler (used to reduce intake air temperature and increase intake air density), and a control system. The turbocharger consists of two parts: an exhaust gas turbine and a compressor, which are connected coaxially to convert exhaust gas energy into mechanical energy.

[0114] Turbocharging technology can significantly improve engine performance and reduce emissions to some extent. However, it should be noted that turbocharging increases engine complexity and weight, and also places higher demands on engine durability.

[0115] Implementation and optimization: The implementation of a turbocharger system requires consideration of matching with the engine, including the selection of the turbocharger and the optimization of the intake system.

[0116] To further optimize the performance of the turbocharger system, adjustments and optimizations can be made to the turbocharger's boost ratio and the intercooler's efficiency. Simultaneously, it is necessary to strengthen engine maintenance and upkeep to ensure its stable operation.

[0117] In summary, by finely tuning the engine, optimizing parameters such as fuel injection quantity and ignition advance angle, introducing exhaust gas recirculation technology to reduce nitrogen oxide emissions, and using turbocharging technology to improve engine intake efficiency, fuel consumption can be reduced.

[0118] In this embodiment of the application, the personalized driving module includes: determining the driver's driving habit data based on relevant data and a target algorithm, and determining the vehicle's personalized driving strategy based on the driving habit data and environmental data, wherein the personalized driving strategy includes the power distribution between the engine and the electric motor, driving mode, and personalized settings.

[0119] Specifically, the personalized driving module in this application embodiment is a system that intelligently adjusts and optimizes based on the driver's driving habits and environmental conditions using advanced technology to provide the best driving experience. The specific execution process is as follows: Figure 3 As shown.

[0120] 1. Overview of the technical solution.

[0121] The technical solution for personalized driving modes primarily utilizes machine learning algorithms to conduct in-depth analysis of driver habits and environmental conditions, thereby establishing personalized driving modes that meet the driver's needs. This mode can adaptively adjust parameters such as the power distribution between the engine and electric motor, and the driving mode, to achieve a more intelligent, comfortable, and energy-efficient driving experience.

[0122] 2. Analysis of driver's driving habits.

[0123] Data Acquisition: Real-time data on driver behavior, such as accelerator pedal pressure, braking force, and steering wheel rotation angle, is collected using onboard sensors, cameras, and other equipment.

[0124] At the same time, it records the driver's driving behavior at different times and under different road conditions to obtain comprehensive information on driving habits.

[0125] Machine learning algorithm analysis: This involves using machine learning algorithms to process and analyze collected driving behavior data to identify drivers' driving styles, preferences, and other characteristics. Through continuous learning and algorithm optimization, the accuracy and reliability of the analysis are improved.

[0126] 3. Environmental condition analysis.

[0127] Real-time traffic monitoring: Utilize in-vehicle navigation systems or external traffic information platforms to obtain real-time traffic information, such as road congestion and speed limits.

[0128] Weather condition analysis: Real-time weather information, such as temperature, humidity, and rainfall, is obtained through vehicle-mounted meteorological sensors or external weather information platforms.

[0129] 4. Personalized driving modes can be established.

[0130] Power distribution optimization: The power distribution between the engine and the electric motor is adaptively adjusted based on the driver's driving habits and environmental conditions. For example, on highways, the engine's power output can be increased to improve speed and acceleration performance; in congested urban areas, the electric motor can be relied upon more for energy saving and emission reduction.

[0131] Driving mode adjustment: The system intelligently adjusts the driving mode based on the driver's preferences and real-time road conditions. For example, drivers who prefer aggressive driving can choose Sport mode to improve acceleration response and power performance; drivers who prioritize fuel economy and comfort can choose Eco mode to reduce fuel consumption and noise.

[0132] Personalization settings: Drivers can personalize vehicle settings according to their preferences, such as seat position, steering wheel angle, and rearview mirror angle. They can also adjust parameters of the vehicle's suspension, steering, and braking systems to achieve optimal driving posture and handling performance.

[0133] 5. Technology implementation and optimization.

[0134] In-vehicle system upgrades: Regular upgrades and optimizations of the in-vehicle system are performed to improve the accuracy and reliability of personalized driving modes. Simultaneously, the connectivity and interaction capabilities between the in-vehicle system and external information platforms are enhanced to achieve more intelligent and convenient information acquisition and processing.

[0135] Driver Feedback Mechanism: Establish a driver feedback mechanism to collect drivers' opinions and suggestions on personalized driving modes. Continuously learn and improve the algorithm to optimize the performance and user experience of personalized driving modes.

[0136] Safety Measures: When implementing personalized driving modes, enhanced safety measures are implemented to ensure vehicle safety and stability. For example, when adjusting power distribution and driving modes, it is necessary to ensure that the vehicle's power performance and handling performance meet safety standards; when adjusting personalized settings, it is necessary to avoid adverse effects on the vehicle's safety performance.

[0137] In step S103, after the vehicle performs the target action, the vehicle's feedback data is acquired, and the vehicle's control strategy is corrected based on the feedback data.

[0138] The feedback data includes the engine's actual torque, torque fluctuation value, NOx emission concentration, and fuel consumption.

[0139] It is understood that, in the embodiments of this application, after the vehicle performs the target action, feedback data of the vehicle is obtained, and the control strategy of the vehicle is corrected based on the feedback data to improve the adaptability of the control strategy.

[0140] The hybrid vehicle control method of this application is described below through specific embodiments, which mainly involves four parts: energy management system, ride comfort control strategy, emission optimization technology and personalized driving mode system.

[0141] I. Energy Management System

[0142] 1. System Architecture: This system typically consists of multiple modules, including a data acquisition module, a data analysis module, an intelligent control module, and a user interface module. The data acquisition module is responsible for collecting various data during vehicle operation, such as vehicle speed, engine speed, and battery charge. The data analysis module processes and analyzes the collected data to formulate the optimal energy management strategy. Based on the results from the data analysis module, the intelligent control module automatically adjusts the operating status of the engine and electric motor to achieve optimal energy utilization. The user interface module provides an intuitive operating interface and visual reports, allowing the driver to understand the vehicle status and make corresponding adjustments.

[0143] 2. Working Principle: In pure electric mode, hybrid vehicles rely on the electric motor for propulsion, achieving zero-emission operation. In hybrid mode, the internal combustion engine and electric motor work together, intelligently adjusting power output based on driving conditions and battery status to improve fuel economy and performance. The intelligent energy management system optimizes the ratio of fuel to electricity through algorithms, ensuring the system always operates at its optimal state.

[0144] The intelligent energy management system for hybrid electric vehicles can significantly improve fuel economy and power performance. By optimizing energy distribution and reducing energy consumption, the system helps reduce the vehicle's environmental impact. At the same time, the system also enhances the driver's experience and comfort.

[0145] II. Smoothness control strategy.

[0146] This embodiment employs a control strategy that combines model predictive control (MPC) and sliding mode control (SMC) to accurately predict and coordinate the starting, shutting down, and power adjustment of the engine and electric motor.

[0147] 1. System Modeling and Predictive Model Construction: Establish an accurate mathematical model for the hybrid power system, including dynamic behavior descriptions of key components such as the engine, electric motor, transmission system, and battery. Based on the system model, construct a predictive model to predict the state changes of the engine and electric motor over a future period, including key parameters such as speed and torque.

[0148] 2. Optimization Solution and Control Input Implementation: Using the MPC algorithm, based on the prediction model and constraints (such as input constraints and state constraints), the optimal control input sequence is solved to make the system state as close as possible to the desired state over a future period. The first control input in the optimized control input sequence is applied to the system to achieve real-time control. Simultaneously, the current state of the system is estimated in real time using sensor data, and the state information is fed back to the MPC controller for the next round of prediction and optimization.

[0149] 3. Sliding Mode Control Strategy Design: Design a sliding surface to allow the system state to slide along it, achieving system stability and desired dynamic performance. Design switching control laws and sliding mode control laws to rapidly approach the sliding surface from the initial state and maintain stable operation there. Adjust control parameters to reduce the impact of chattering on the control effect.

[0150] 4. Cooperative Control Strategy Design: A cooperative control strategy for the engine and electric motor is designed to ensure a smooth transition during mode switching. Through precise prediction and coordinated control, power interruption and torque fluctuations are reduced, enhancing the driving experience.

[0151] After optimizing the smoothness control strategy in this embodiment, the smoothness of the hybrid passenger vehicle is significantly improved. During mode switching, power interruptions and torque fluctuations are significantly reduced, resulting in a more comfortable driving experience. Simultaneously, the system's stability and robustness are enhanced, enabling it to better adapt to different driving conditions.

[0152] III. Emission Optimization Technologies.

[0153] 1. Engine optimization.

[0154] Atkinson cycle engine: The Atkinson cycle engine with a high expansion ratio flexibly responds to different driving needs by adjusting the effective displacement, improving thermal efficiency and reducing fuel consumption.

[0155] Variable valve timing technology: Utilizing variable valve timing technology to precisely control the opening and closing of intake and exhaust valves, ensuring that the engine can achieve optimal operating conditions under various operating conditions, and further reducing emissions.

[0156] 2. Exhaust gas recirculation technology.

[0157] EGR system design: Installing an EGR valve and EGR cooler allows some of the exhaust gas after combustion to be reintroduced into the intake system, mixed with fresh air, and then re-entered into the cylinder for combustion, thereby reducing the combustion chamber temperature and NOx generation.

[0158] Intelligent adjustment: The electronic control unit intelligently adjusts the EGR rate according to the engine operating conditions to ensure that emissions are reduced without affecting engine performance.

[0159] 3. Three-way catalytic converter and oxygen sensor.

[0160] Three-way catalytic converter: A three-way catalytic converter is installed in the exhaust system to use a precious metal catalyst to convert CO, HC and NOx in the exhaust gas into harmless nitrogen, carbon dioxide and water vapor.

[0161] Oxygen sensor: Oxygen sensors are installed before and after the catalytic converter to monitor the oxygen content in the exhaust in real time and provide feedback signals to the ECU so as to accurately control the air-fuel ratio and ensure the efficient operation of the catalytic converter.

[0162] 4. Energy recovery system.

[0163] Braking energy recovery: Integrating a braking energy recovery system into a hybrid system converts the energy generated during vehicle braking into electrical energy and stores it for subsequent driving or auxiliary driving, thereby improving energy utilization efficiency.

[0164] 5. Emission after-treatment system.

[0165] Particulate Filter (DPF) (for diesel hybrid vehicles): Installing a DPF in the exhaust system captures and oxidizes particulate matter in the exhaust gas, reducing PM emissions. Urea Injection System (for SCR systems): For vehicles requiring further NOx emission reductions, a urea injection system can be installed, injecting urea solution into the exhaust system to react with NOx and produce harmless nitrogen and water vapor.

[0166] Through the implementation of the aforementioned emission optimization technologies, the emission performance of hybrid passenger vehicles has been significantly improved. Emissions of harmful substances such as CO, HC, and NOx have been substantially reduced, meeting or even exceeding current environmental regulations. Simultaneously, engine thermal efficiency and fuel economy have also been improved, providing consumers with better fuel economy and driving experience.

[0167] IV. Personalized driving mode system.

[0168] 1. System Components: Data Acquisition Module: Responsible for collecting driver behavior data, including acceleration, braking, and steering operation information, as well as vehicle status data such as speed, RPM, and fuel consumption; Data Analysis Module: Utilizes machine learning algorithms to process and analyze the collected data, identifying the driver's driving habits and preferences; Pattern Generation Module: Based on the analysis results, generates personalized driving modes, including engine and electric motor power distribution strategies and driving mode selection; Execution Control Module: Applyes the generated personalized driving modes to the vehicle control system, adjusting the vehicle status in real time to meet the driver's needs.

[0169] 2. Workflow: The data acquisition module collects driver behavior data and vehicle status data in real time; the data analysis module processes and analyzes the collected data to identify the driver's driving habits and preferences; the mode generation module generates a personalized driving mode that meets the driver's needs based on the analysis results; the execution control module applies the generated driving mode to the vehicle control system to adjust the vehicle status in real time, such as engine power, electric motor output, and driving mode.

[0170] 3. Technical Features: Personalization: Generates personalized driving modes based on the driver's driving habits and preferences; Real-time: Capable of collecting and analyzing data in real time and adjusting vehicle status based on the analysis results; Intelligence: Utilizes machine learning algorithms for data analysis to continuously optimize and improve personalized driving modes.

[0171] It can improve driver comfort and satisfaction; reduce vehicle energy consumption and emissions, improving environmental performance; and enhance vehicle safety and stability.

[0172] Taking a high-end electric vehicle as an example, this car is equipped with a personalized driving mode system. Drivers can personalize settings according to their preferences and needs via the in-vehicle touchscreen or a mobile app. For example, drivers can choose "Sport Mode" for faster acceleration and more responsive handling; or choose "Eco Mode" to reduce energy consumption and extend driving range. In addition, drivers can also customize the vehicle's seat position, steering wheel angle, and rearview mirror angle to ensure optimal driving posture and visibility.

[0173] Based on the above four parts, centralized scheduling is achieved through a central control unit, avoiding command conflicts caused by independent control of multiple systems (e.g., when emission optimization requires adjusting the engine fuel injection quantity, the energy management system must be simultaneously informed of the appropriate electric motor power). The underlying logic can be summarized as follows: using the data acquisition module as the information entry point, the central control unit as the scheduling core, and the four major technical solutions as execution branches, ultimately outputting a comprehensive control effect that is efficient, smooth, low-emission, and personalized. The specific unified scheduling steps are as follows: Step 1: Establish a data sharing hub and connect data links between solutions. Unified data acquisition module: Integrates sensors such as vehicle speed sensor, engine speed sensor, driver operation sensor, and ambient temperature sensor into one, and sets the data acquisition frequency (e.g., 100ms / time for key parameters, 1s / time for auxiliary parameters) and format (e.g., using CAN bus standard protocol) to ensure that data is transmitted to the central hub in real time and consistently. Establish a data classification and storage repository: Store data in categories such as vehicle status (vehicle speed, battery level), driving behavior (acceleration force, braking frequency), environmental data (road conditions, temperature), and control feedback data (engine torque, emission concentration), so that the four major solutions can call them as needed (for example, when emission optimization technology needs engine speed data, it can be obtained directly from the vehicle status database without repeated collection).

[0174] For example, personalized driving modes can use machine learning to analyze the driver's level of aggression (such as "high aggression" or "smoothness") and synchronize this information to the energy management system in real time. For highly aggressive drivers, the energy management system can reserve instantaneous power from the electric motor in advance to avoid a sudden increase in engine load during rapid acceleration. At the same time, it can be synchronized with the smoothness control strategy to optimize the torque switching rate and reduce power fluctuations.

[0175] Step 2: Formulate scheduling rules based on the central control unit (HCU).

[0176] The execution of the four schemes requires unified coordination through the HCU to avoid control conflicts, and three types of scheduling logic need to be clearly defined: Priority scheduling: When multiple options conflict, they are ordered in the order of "safety > emissions > energy efficiency > personalization" (e.g., during cold start, emission optimization technology needs to prioritize adjusting the engine fuel injection quantity and EGR rate. At this time, the energy management system needs to temporarily adapt to emission requirements and reduce the electric motor intervention ratio. Energy efficiency optimization will be restored after emissions meet the standards). Operating condition-based scheduling: Triggering corresponding scheme combinations based on the actual operating conditions of the vehicle (such as starting, accelerating, cruising, and braking). Cold start condition: Emission optimization technology (EGR system off, three-way catalytic converter preheating) + energy management system (electric motor priority drive to avoid low-load and inefficient engine operation); Rapid acceleration conditions: Smoothness control strategy (MPC algorithm predicts torque demand and coordinates the superposition of engine and electric motor power) + energy management system (instantaneous battery discharge assistance) + personalized mode (adjusts power response speed according to driver habits). Cruise mode: Energy management system (optimizes the power distribution between the engine and the electric motor to keep the engine in the high-efficiency range) + emission optimization technology (intelligent activation of the EGR system to reduce NOx emissions). Feedback adjustment and scheduling: The feedback data output after each scheme is executed (such as the torque fluctuation value after smoothness control and the NOx concentration after emission optimization) needs to be sent back to the HCU, so that the HCU can dynamically correct the parameters of other schemes (for example, if NOx is detected to exceed the emission standard, the HCU can instruct the energy management system to appropriately increase the participation of the electric motor, reduce the engine load, and adjust the emission-optimized EGR rate at the same time).

[0177] Step 3: Technical interface conflicts between solutions.

[0178] Torque coordination between energy management and smoothness control: Conflict point: In pursuit of energy efficiency, the energy management system may require the engine to switch power quickly; while smoothness control needs to adjust torque slowly to avoid fluctuations.

[0179] Integrated solution: Add a "torque transition algorithm" to the HCU. The target power distribution value output by the energy management system needs to be processed by the MPC algorithm of the smoothness control module to generate a "stepped torque change curve" (e.g., when the engine torque increases from 100Nm to 200Nm, it increases in 5 steps with an interval of 50ms between each step), which satisfies the energy efficiency requirements and avoids power interruption. Matching parameters for emissions optimization and personalized driving: Conflict point: Aggressive driving mode requires high engine power output, which may lead to increased emissions; emissions optimization requires limiting engine load, which may affect power response.

[0180] Integrated Solution: Establish an "emissions-power balance model" that dynamically adjusts based on driver habit labels and real-time emissions data: For aggressive drivers, briefly relax emission thresholds during rapid acceleration (but not exceeding regulatory standards), while simultaneously activating the emissions aftertreatment system (such as efficient operation of the three-way catalytic converter); for stable drivers, prioritize maintaining low emission conditions and simultaneously optimize energy efficiency. Unified data acquisition frequency: Conflict point: The energy management system requires high-frequency data (100ms / time), while the personalized driving mode requires low-frequency long-term data (1min / time average). Acquiring data at a high frequency will increase the system load.

[0181] Integrated solution: Adopting a "layered data collection strategy", key parameters (vehicle speed, torque requirements) are collected at high frequency, while non-key parameters (driving habit statistics) are collected at low frequency and summarized in stages, which not only meets the needs of each solution, but also reduces hardware energy consumption.

[0182] Step 4: Ensure integration effectiveness through scenario-based verification After integration, the solutions need to be validated in typical scenarios to ensure that they work synergistically.

[0183] 1. Urban traffic congestion scenario.

[0184] Verification objectives: Improved energy efficiency + smoothness + low emissions; Integration logic: Data center collects road condition data of "frequent start-stop and low-speed driving" → HCU schedules energy management system (motor drives first, engine only starts when battery SOC is below 20%) + smoothness control (SMC algorithm suppresses torque fluctuations during start-stop) + emission optimization (automatic activation of three-way catalytic converter preheating when engine starts). Verification indicators: Fuel consumption rate reduced by 15% (compared to the original plan), torque fluctuation value <5Nm, NOx emissions <50mg / km; 2. Highway cruising scenario.

[0185] Verification objectives: Efficient cruise control + personalization; Integration logic: The data center collects data on "constant speed of 100km / h and smooth driving by the driver" → HCU dispatches the energy management system (the engine maintains the high-efficiency range of 2000rpm, and the electric motor assists in compensating for load fluctuations) + personalized mode (adjusts steering assist and power response according to the driver's habits) + emission optimization (EGR rate is adjusted to 15% to reduce NOx); Verification indicators: Engine thermal efficiency > 38%, driver operation satisfaction improved by 20%.

[0186] In summary, this application, through intelligent energy management strategies, effectively reduces fuel consumption and improves energy efficiency in hybrid vehicles, aligning with the environmental trend of energy conservation and emission reduction, and significantly improving energy efficiency; it enhances the driving experience, reduces discomfort during driving, and improves passenger comfort, thus enhancing the user's driving experience; the optimized engine operation strategy and control method significantly reduce the emission of harmful gases, contributing to improved air quality and environmental protection; through precise control and optimized management, this invention significantly improves the vehicle's power, economy, and reliability, enhancing vehicle performance and strengthening the market competitiveness of hybrid vehicles.

[0187] Specifically, this application may: Enhancing the intelligence of energy management strategies: This application employs advanced predictive algorithms and machine learning technology to monitor and analyze vehicle status, driving habits, and environmental conditions in real time, dynamically adjusting the power distribution between the engine and electric motor to maximize energy utilization.

[0188] Enhanced driving smoothness: By accurately predicting and coordinating the start-up, shutdown, and power adjustment of the engine and electric motor, this application reduces power interruption and torque fluctuations during mode switching, thereby improving driving smoothness and comfort.

[0189] Optimizing emission performance: Based on in-depth research on engine operating conditions and emission characteristics, this application proposes targeted control strategies that effectively reduce emissions under extreme conditions such as cold starts and rapid acceleration.

[0190] Meeting personalized needs: By using machine learning algorithms to analyze drivers' driving habits and environmental conditions, this application can adaptively adjust the control strategy to better meet personalized needs and improve user experience.

[0191] According to the hybrid vehicle control method proposed in the embodiments of this application, a vehicle control strategy can be generated based on relevant data and priority of the hybrid vehicle, and the vehicle can be controlled to perform target actions based on the control strategy. By comprehensively considering multiple data and strategies, a unified control scheme for the vehicle can be formed to adapt to complex scenarios, ensuring that the control strategy takes into account energy efficiency, smoothness, emissions and personalization, thereby improving the overall performance of the vehicle. After the vehicle performs the target action, feedback data of the vehicle is obtained, and the vehicle control strategy is corrected based on the feedback data to improve the adaptability of the control strategy.

[0192] Next, a hybrid vehicle control device according to an embodiment of this application is described with reference to the accompanying drawings.

[0193] Figure 4 This is a block diagram of a hybrid vehicle control device according to an embodiment of this application.

[0194] like Figure 4 As shown, the hybrid vehicle control device 10 includes: an acquisition module 100, a generation module 200, and a correction module 300.

[0195] The acquisition module 100 is used to acquire relevant data of the current vehicle, including at least one of operating conditions, status data, surrounding environment data, and driver driving behavior data; the generation module 200 is used to generate a vehicle control strategy based on the relevant data and target priority, and control the vehicle to perform target actions based on the control strategy, including at least one of energy management strategy, emission optimization strategy, ride comfort control strategy, and personalized driving strategy; the correction module 300 is used to acquire feedback data of the vehicle after the vehicle performs the target action, and correct the vehicle control strategy based on the feedback data.

[0196] In this embodiment, the generation module 200 is further configured to: determine the core control objective of the current vehicle based on the operating conditions; determine the target execution module of the vehicle based on the core control objective and the target priority, wherein the target execution module includes at least one of an energy management module, an emission optimization module, a ride comfort control module, and a personalized driving module, and the target execution module outputs a corresponding control strategy based on relevant data; and generate the vehicle's control strategy based on the core control objective, the target priority, and the control strategy output by the target execution module.

[0197] In this embodiment of the application, the apparatus further includes a first correction module.

[0198] The first correction module is used to correct the vehicle's control strategy based on a preset torque transition algorithm after determining the vehicle's target execution module based on the core control target and target priority. If the target execution module includes an energy management module and a ride comfort control module, the correction module corrects the vehicle's control strategy based on an emission dynamic balance model.

[0199] In this embodiment of the application, the energy management module includes: inputting relevant data into a target prediction model, and the target prediction model outputting the vehicle's energy management strategy, wherein the energy management strategy includes the operating status of the vehicle's energy equipment and the power output of the engine and electric motor.

[0200] In this embodiment of the application, the ride comfort control module includes: determining a ride comfort control strategy for the vehicle based on relevant data and a target control algorithm, wherein the ride comfort control strategy includes torque compensation and torque fluctuation limitation for the engine and electric motor.

[0201] In this embodiment of the application, the emission optimization module includes: determining the engine operating condition based on relevant data, and determining the vehicle emission optimization strategy based on the engine operating condition and relevant data, wherein the emission optimization strategy includes control parameters of at least one of the vehicle's exhaust gas recirculation system, engine, and turbocharging system.

[0202] In this embodiment of the application, the personalized driving module includes: determining the driver's driving habit data based on relevant data and a target algorithm, and determining the vehicle's personalized driving strategy based on the driving habit data and environmental data, wherein the personalized driving strategy includes the power distribution between the engine and the electric motor, driving mode, and personalized settings.

[0203] It should be noted that the foregoing explanation of the hybrid vehicle control method embodiment also applies to the hybrid vehicle control device of this embodiment, and will not be repeated here.

[0204] The hybrid vehicle control device proposed in the embodiments of this application can generate a vehicle control strategy based on relevant data and priority of the hybrid vehicle, and control the vehicle to perform target actions based on the control strategy. By comprehensively considering multiple data and strategies, a unified control scheme for the vehicle is formed to adapt to complex scenarios, ensuring that the control strategy takes into account energy efficiency, smoothness, emissions and personalization, thereby improving the overall performance of the vehicle. After the vehicle performs the target action, feedback data of the vehicle is obtained, and the vehicle control strategy is corrected based on the feedback data to improve the adaptability of the control strategy.

[0205] Figure 5 A schematic diagram of a hybrid vehicle provided in an embodiment of this application. The hybrid vehicle may include: The memory 501, the processor 502, and the computer program stored on the memory 501 and capable of running on the processor 502.

[0206] When processor 502 executes the program, it implements the hybrid vehicle control method provided in the above embodiments.

[0207] Furthermore, hybrid vehicles also include: Communication interface 503 is used for communication between memory 501 and processor 502.

[0208] The memory 501 is used to store computer programs that can run on the processor 502.

[0209] Memory 501 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0210] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0211] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.

[0212] Processor 502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0213] This application also provides a computer-readable storage medium storing a computer program or instructions thereon, which, when executed by a processor, implements the hybrid vehicle control method described above.

[0214] This application also provides a computer program product, including a computer program or instructions, which, when executed, implement the hybrid vehicle control method described above.

[0215] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0216] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0217] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0218] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0219] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

Claims

1. A hybrid vehicle control method, characterized in that, Includes the following steps: Acquire relevant data of the current vehicle, wherein the relevant data includes at least one of operating condition data, status data, surrounding environment data, and driver driving behavior data; The vehicle control strategy is generated based on the relevant data and target priorities, and the vehicle is controlled to perform target actions based on the control strategy. The control strategy includes at least one of energy management strategy, emission optimization strategy, ride comfort control strategy and personalized driving strategy. After the vehicle performs the target action, feedback data of the vehicle is acquired, and the control strategy of the vehicle is corrected based on the feedback data.

2. The hybrid vehicle control method according to claim 1, characterized in that, The process of generating the vehicle's control strategy based on the relevant data and target priority includes: Determine the core control objective of the current vehicle based on the described operating conditions; The target execution module of the vehicle is determined based on the core control objective and the target priority. The target execution module includes at least one of an energy management module, an emission optimization module, a ride comfort control module, and a personalized driving module. The target execution module outputs a corresponding control strategy based on the relevant data. The vehicle control strategy is generated based on the core control objective, the objective priority, and the control strategy output by the objective execution module.

3. The hybrid vehicle control method according to claim 2, characterized in that, After determining the target execution module of the vehicle based on the core control objective and the target priority, the system further includes: If the target execution module includes an energy management module and a ride comfort control module, the vehicle control strategy is modified based on a preset torque transition algorithm. If the target execution module includes an emissions optimization module and a personalized driving module, then the vehicle's control strategy is modified based on the emissions dynamic balance model.

4. The hybrid vehicle control method according to claim 2, characterized in that, The energy management module includes: inputting the relevant data into a target prediction model, and the target prediction model outputting the energy management strategy of the vehicle, wherein the energy management strategy includes the operating status of the vehicle's energy equipment and the power output of the engine and electric motor.

5. The hybrid vehicle control method according to claim 2, characterized in that, The ride comfort control module includes: determining the ride comfort control strategy of the vehicle based on the relevant data and the target control algorithm, wherein the ride comfort control strategy includes torque compensation and torque fluctuation limitation of the engine and electric motor.

6. The hybrid vehicle control method according to claim 2, characterized in that, The emission optimization module includes: determining the engine's operating condition based on the relevant data, and determining the vehicle's emission optimization strategy based on the engine's operating condition and the relevant data, wherein the emission optimization strategy includes control parameters of at least one of the vehicle's exhaust gas recirculation system, engine, and turbocharging system.

7. The hybrid vehicle control method according to claim 2, characterized in that, The personalized driving module includes: determining the driver's driving habit data based on the relevant data and the target algorithm; and determining the vehicle's personalized driving strategy based on the driving habit data and the environmental data. The personalized driving strategy includes the power distribution between the engine and the electric motor, driving modes, and personalized settings.

8. A hybrid vehicle control device, characterized in that, include: The acquisition module is used to acquire relevant data of the current vehicle, wherein the relevant data includes at least one of operating condition data, status data, surrounding environment data, and driver driving behavior data; A generation module is used to generate a control strategy for the vehicle based on the relevant data and target priority, and to control the vehicle to perform target actions based on the control strategy, wherein the control strategy includes at least one of an energy management strategy, an emission optimization strategy, a ride comfort control strategy, and a personalized driving strategy; The correction module is used to acquire feedback data of the vehicle after the vehicle performs the target action, and correct the control strategy of the vehicle based on the feedback data.

9. A hybrid vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the hybrid vehicle control method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, The computer program or instructions are executed by a processor to implement the hybrid vehicle control method as described in any one of claims 1-7.

Images