A vehicle energy management method fusing user portrait and intersection signal coordination

Abstract

The application discloses a kind of fusion user portrait and intersection signal synergic vehicle energy management method, it is related to vehicle control technical field, the method includes: obtaining the navigation path of target vehicle and the signal light phase time sequence information of each intersection along the way;With the lowest total energy consumption as optimization goal, determine constraint condition based on signal light phase time sequence information and vehicle dynamics characteristics, construct global optimization objective function, and obtain global energy reference trajectory by solving;Obtain the style factor for quantitatively characterizing the driving preference of driver;Collect the driving data of target vehicle and traffic flow information on navigation path, dynamically correct global energy reference trajectory;Based on the result after correction, generate instantaneous control instruction at each time, and perform predicted performance energy recovery and driving according to instantaneous optimal control instruction.The application considers global optimality and real-time road condition adaptation flexibility under the condition of on-board limited computing power, thereby significantly reducing the fuel consumption and electricity consumption of the whole vehicle.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a vehicle energy management method that integrates user profiles and intersection signal coordination. Background Technology

[0002] Hybrid vehicle energy management strategies are directly related to fuel economy and emissions levels. With the development of intelligent connected vehicle and vehicle-road cooperative technologies, predictive energy management based on traffic information can achieve global optimization of energy management by integrating prior information such as navigation routes, road gradients, and traffic light timings.

[0003] Existing technologies can combine navigation routes with traffic light information at single intersections to generate recommended speeds, guiding vehicles to utilize green waves at single intersections, reducing idling and sudden acceleration / deceleration, and achieving localized energy savings. However, this approach has significant drawbacks: First, limited by multi-intersection collaborative processing, existing solutions primarily focus on short-sightedness optimization at single intersections, lacking comprehensive planning for the timing of consecutive intersections along long paths. This results in vehicles encountering red lights at subsequent intersections after passing the first intersection, leading to frequent idling and sudden acceleration / deceleration, which actually increases journey energy consumption. Second, existing strategies do not differentiate between autonomous and manual driving conditions, nor do they consider individual driver preferences. In manual driving scenarios, when energy-saving speeds conflict with driver habits, drivers often actively intervene or ignore suggestions, causing the strategy to fail.

[0004] Existing technologies struggle to achieve multi-intersection signal coordination and global energy consumption optimization, facing numerous core technological barriers. First, the cycles and phases of traffic lights at urban intersections are configured independently, with traffic sequences mutually constraining and highly coupled. When performing comprehensive optimization for long-path, continuous intersections, the feasible vehicle speed solution space expands exponentially, significantly increasing algorithm computational complexity. Second, various minor disturbances during vehicle movement cause small speed deviations, which accumulate and amplify along the travel path, disrupting the green wave passage windows at subsequent intersections and rendering global optimization ineffective. Third, existing technologies lack a complete journey-level global energy consumption evaluation system, focusing only on optimizing single-intersection traffic flow, failing to scientifically weigh comprehensive energy consumption losses across the entire journey. Furthermore, onboard controllers have limited computing resources, and the computational load for multi-intersection global collaborative optimization is substantial, making it difficult to meet the real-time control requirements during vehicle movement, severely hindering the practical application of energy management technologies for energy-efficient vehicles.

[0005] Therefore, there is currently a lack of a vehicle energy management method that can integrate user profiles with intersection signal coordination. Summary of the Invention

[0006] This application provides a vehicle energy management method that integrates user profiling and intersection signal coordination to address the shortcomings of the aforementioned related technologies. By constructing a two-layer optimization model of "global energy corridor" and "personalized real-time correction," it improves the personalized driving experience and user compliance with system strategies while ensuring optimal journey-level energy efficiency. The technical solution is as follows: Firstly, this application provides a vehicle energy management method that integrates user profiles and intersection signal coordination, including: Obtain the navigation path of the target vehicle, determine multiple consecutive intersections along the route based on the navigation path, and extract the traffic light phase timing information of each intersection. With the goal of minimizing total energy consumption throughout the journey, constraints are determined based on the traffic light phase timing information and vehicle dynamics characteristics. A global optimization objective function is then constructed, and the global energy reference trajectory of the target vehicle is obtained by solving the problem. Obtain style factors constructed based on drivers' historical driving behavior data to quantitatively characterize drivers' driving preferences; Real-time acquisition of target vehicle driving data and traffic flow information on the navigation path; dynamic rolling time-domain correction of the global energy reference trajectory based on the style factor, driving data and traffic flow information. Instantaneous control commands are generated for each moment based on the corrected global energy reference trajectory, and predictive energy recovery and drive are executed according to the instantaneous optimal control commands at the corresponding moment.

[0007] In one alternative embodiment of the first aspect, obtaining the navigation path of the target vehicle, determining multiple consecutive intersections along the route based on the navigation path, and extracting the traffic light phase timing information of each intersection specifically includes: The coordinates, number of lanes, and road speed limit information of each intersection on the navigation path are extracted based on the map database. The traffic light cycle parameters for each intersection are obtained based on a cloud-based traffic management platform. The direction of travel of the target vehicle at each intersection is determined based on the navigation path, and the traffic lights at each intersection whose lane direction is consistent with the direction of travel are determined. The current phase, remaining countdown, and phase switching time of the traffic lights with the same direction are extracted from the traffic light period parameters to obtain the traffic light phase timing information.

[0008] In one alternative of the first aspect, the optimization objective is to minimize the total energy consumption over the entire journey. Based on the traffic light phase timing information and vehicle dynamics characteristics, constraints are determined, and a global optimization objective function is constructed, including: A global optimization objective function is established with the goal of minimizing total energy consumption throughout the entire journey; wherein, the total energy consumption throughout the entire journey includes fuel consumption and power loss of the power battery. Determine vehicle dynamics constraints; the vehicle dynamics constraints include real-time vehicle speed constraints, acceleration constraints, motor torque constraints, and battery state of charge constraints. Based on the traffic light phase timing information of each intersection, the green light passage time interval of the corresponding intersection is determined, the predicted arrival time of the target vehicle at the recommended speed to the corresponding intersection is determined, and the predicted arrival time is constrained to fall within the green light passage time interval, thus constructing the intersection time window constraint. If the predicted arrival time corresponding to any recommended vehicle speed cannot fall within the green light passage time interval of the corresponding intersection, then minimizing the red light waiting time of the target vehicle at that intersection is taken as the secondary optimization objective and incorporated into the global optimization objective function. Based on the vehicle dynamics constraints and the intersection time window constraints, the model predictive control algorithm is used to solve the global optimization objective function, resulting in a global energy reference trajectory with travel time as the horizontal axis and recommended vehicle speed and instantaneous total energy consumption as the vertical axis.

[0009] In one alternative approach to the first aspect, the process of extracting the driver's style factors specifically includes the following steps: Collect drivers' historical driving behavior data, which includes long-term average acceleration, frequency of rapid acceleration and deceleration per unit distance, average following distance, and frequency of following the recommended speed for green wave traffic. The historical driving behavior data are subjected to min-max normalization to map each data point to a uniform numerical range, resulting in a normalized feature vector. The normalized feature vector is input into a preset style factor output model to obtain style factors with values ​​between 0 and 1.

[0010] In one alternative embodiment of the first aspect, the dynamic correction of the global energy reference trajectory in the rolling time domain based on the driving data and the traffic flow information includes: Establish a rolling optimization time domain window and collect traffic flow information on the navigation path within the rolling optimization time domain window in real time; Based on the traffic flow information, the estimated intersection delay time for the target vehicle to arrive at each intersection is determined, and a time efficiency cost is constructed based on the estimated intersection delay time. By comparing the actual vehicle speed of the target vehicle at each moment in the rolling optimization time domain window with the recommended vehicle speed at the corresponding moment in the global energy reference trajectory, the vehicle speed deviation at the corresponding moment is calculated, and a comfort cost is constructed based on the vehicle speed deviation. Determine the total energy consumption rate of the target vehicle at each moment within the rolling optimization time window, and construct the energy consumption cost based on the total energy consumption rate; An instantaneous cost function is constructed based on time efficiency cost, comfort cost, and energy consumption cost; wherein, the weight of each cost term in the instantaneous cost function is dynamically adjusted based on the style factor; The instantaneous cost function is solved within the rolling optimization time-domain window. Based on the solution results, the recommended vehicle speed and instantaneous total energy consumption at each moment in the global energy reference trajectory are corrected to obtain the corrected global energy reference trajectory.

[0011] In one alternative to the first aspect, the process of dynamically adjusting the weight of each cost term in the instantaneous cost function based on the style factor specifically includes the following steps: When the style factor is greater than the style factor determination threshold, the weight of time efficiency cost is increased, and the weight of energy consumption cost and comfort cost are decreased. When the style factor is less than the style factor determination threshold, the weight of time efficiency cost is reduced, while the weight of energy consumption cost and comfort cost are increased.

[0012] In one alternative to the first aspect, the instantaneous optimal control command includes the target vehicle speed, target drive torque, and regenerative braking intensity at the corresponding moment; The execution of predictive energy recovery and drive based on the instantaneous optimal control command at the corresponding moment includes: The instantaneous optimal control command is sent to the vehicle controller. The instantaneous optimal control command includes the target vehicle speed, the target drive torque, and the regenerative braking intensity. The vehicle controller performs power distribution based on the instantaneous optimal control command to ensure that the actual vehicle speed reaches the target vehicle speed at the corresponding moment, including: Under driving conditions, the vehicle controller allocates the output power of the engine and the drive motor according to the target driving torque, combined with the state of charge of the power battery, battery temperature and the maximum output torque limit of the drive motor. During coasting or braking, the vehicle controller performs coasting energy recovery or braking energy recovery based on the braking energy recovery intensity.

[0013] Secondly, this application also provides a vehicle energy management device that integrates user profiles and intersection signal coordination, comprising: The data acquisition unit is used to acquire the navigation path of the target vehicle, determine multiple consecutive intersections along the route based on the navigation path, and extract the traffic light phase timing information of each intersection. The trajectory prediction unit is used to determine the constraints based on the traffic light phase timing information and vehicle dynamics characteristics with the goal of minimizing the total energy consumption throughout the journey, construct a global optimization objective function, and solve for the global energy reference trajectory of the target vehicle. The data acquisition unit is also used to acquire a style factor constructed based on the driver's historical driving behavior data to quantitatively characterize the driver's driving preferences; The dynamic correction unit is used to collect the driving data of the target vehicle and the traffic flow information on the navigation path in real time, and to perform rolling time-domain dynamic correction of the global energy reference trajectory based on the driving data and the traffic flow information. The vehicle control unit is used to generate instantaneous control commands for each moment based on the corrected global energy reference trajectory, and to execute predictive energy recovery and drive according to the instantaneous optimal control command at the corresponding moment.

[0014] Thirdly, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method provided by the first aspect of this application or any implementation thereof.

[0015] Fourthly, this application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method provided by the first aspect of this application or any implementation thereof.

[0016] The beneficial effects of the technical solution provided in this application include at least the following: This application overcomes the shortcomings of existing technologies, such as short-sighted optimization at single intersections, poor energy consumption control over long paths, and inability to adapt to drivers' personalized driving styles. By integrating the phase and timing information of traffic lights at multiple intersections with vehicle dynamics characteristics to construct a global optimization objective function, it achieves optimal global energy consumption planning at the long-distance journey level. This effectively avoids the energy waste caused by frequent idling and rapid acceleration / deceleration during red light waiting at subsequent intersections after green wave passage at the first intersection.

[0017] This application introduces a driver style factor to quantitatively represent driving preferences, deeply embedding personalized driving preferences into the energy management closed loop. This allows energy management strategies to adapt to different driver habits, solving the failure problem caused by the conflict between strategies and driving behaviors, and significantly improving user acceptance and strategy compliance.

[0018] Meanwhile, this application relies on a two-layer optimization architecture that combines global planning with rolling time-domain dynamic correction. The upper layer ensures the global optimality of macro energy consumption, while the lower layer performs rolling time-domain dynamic correction based on real-time driving data and traffic flow information. This not only alleviates the computational complexity pressure caused by the exponential expansion of the solution space of multi-intersection collaborative optimization, but also effectively suppresses the chain reaction of the green wave passage window caused by the cumulative amplification of vehicle speed deviation along the path during driving. Under the condition of limited on-board computing power, it takes into account both global optimality and flexibility in adapting to real-time road conditions, thereby significantly reducing the vehicle's fuel consumption and electricity consumption. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating a vehicle energy management method that integrates user profiles and intersection signal coordination, as provided in an embodiment of this application. Figure 2 This is a schematic diagram of a vehicle energy management device that integrates user profiles and intersection signal coordination, provided in an embodiment of this application. Figure 3 The present application provides a schematic diagram of the structure of an electronic device. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or modules is not limited to the steps or modules listed, but may optionally include steps or modules not listed, or may optionally include other steps or modules inherent to such process, method, product, or apparatus.

[0023] It should be noted that the terms "first" and "second" used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects. It is understood that "first" and "second" can be interchanged in a specific order or sequence where permitted. It should be understood that the objects distinguished by "first" and "second" can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in an order other than those described or illustrated herein.

[0024] The present application will now be described in detail with reference to specific embodiments.

[0025] Next, combine Figure 1 This application introduces a vehicle energy management method that integrates user profiling and intersection signal coordination, as provided in its embodiments. For details, please refer to... Figure 1 , Figure 1 This illustration shows a flowchart of a vehicle energy management method integrating user profiles and intersection signal coordination, provided in an embodiment of this application. Figure 1 The method includes the following steps: S101, Obtain the navigation path of the target vehicle, determine multiple consecutive intersections along the route based on the navigation path, and extract the traffic light phase timing information of each intersection.

[0026] Specifically, the target vehicle can set a navigation route before or during driving, which is a recommended navigation route from the user-specified starting point to the destination. The coordinates of each intersection, the number of lanes, and the road speed limit information on the navigation route can be extracted from the built-in map database of the vehicle navigation host.

[0027] Specifically, the traffic light cycle parameters for each intersection can be obtained from the cloud-based traffic management platform through the in-vehicle navigation host. The direction of travel of the target vehicle at each intersection can be determined through the navigation path, and the traffic lights at each intersection whose lane direction is consistent with the direction of travel can be identified.

[0028] Furthermore, the current phase, remaining countdown, and phase switching time of the traffic lights with the same direction are extracted from the traffic light period parameters to obtain the traffic light phase timing information.

[0029] For example, if the target vehicle needs to turn left at intersection A, it is necessary to determine the left-turn signal light corresponding to the left-turn lane at intersection A, and then extract the current phase (red, yellow, or green light), the remaining countdown of the current phase, and the switching time when the current phase switches to the next phase.

[0030] S102, with the goal of minimizing total energy consumption throughout the journey, constraints are determined based on the traffic light phase timing information and vehicle dynamics characteristics, a global optimization objective function is constructed, and the global energy reference trajectory of the target vehicle is obtained by solving the problem.

[0031] Specifically, a global optimization objective function is established with the goal of minimizing total energy consumption throughout the entire journey. This total energy consumption includes fuel consumption and power loss from the battery. An example of the formula for the global optimization objective function is as follows: ; in, This represents the real-time speed of the target vehicle at time t. This represents the real-time output power of the target vehicle's battery at time t. This represents the predicted total time for the target vehicle to travel along the navigation path to its destination. This represents the instantaneous fuel consumption rate at time t. It represents the power loss of the power battery at time t (including the charging power generated by kinetic energy recovery and the discharging power generated by the output power). The weight representing the instantaneous fuel consumption rate, This indicates the weight of the power loss of the power battery.

[0032] The vehicle dynamics constraints are determined, specifically including real-time vehicle speed constraints, acceleration constraints, motor torque constraints, and battery state of charge constraints, expressed by the following formula: ; ; ; ; in, This represents the minimum speed of the vehicle. The speed limit information can be obtained from the cloud-based traffic management platform via the vehicle's navigation system. This represents the acceleration of the vehicle at time t. This represents the minimum value of vehicle acceleration. This indicates the maximum value of the vehicle's acceleration. This represents the motor torque of the vehicle at time t. This represents the minimum motor torque of the vehicle at time t. This represents the maximum motor torque of the vehicle at time t; This represents the battery state of charge of the vehicle at time t. This represents the minimum state of charge of the vehicle's battery at time t. This represents the maximum state of charge of the vehicle's battery at time t.

[0033] For intersection time window constraints, the green light time interval for each intersection can first be determined based on the traffic light phase timing information of each intersection. The green light time interval for the i-th intersection is represented as: ; in, This indicates the start time of the green light window at the i-th intersection. This indicates the end time of the green light window at the i-th intersection.

[0034] The predicted arrival time of the target vehicle at the i-th intersection when traveling at the recommended speed is determined as follows: .

[0035] The constraint is to ensure that the predicted arrival time falls within the green light time interval, thus constructing the intersection time window constraint. Specifically, the predicted arrival time must satisfy the following conditions: ; It should be noted that if the predicted arrival time corresponding to any recommended vehicle speed cannot fall within the green light time interval of the corresponding intersection, then minimizing the red light waiting time of the target vehicle at that intersection is used as a secondary optimization objective and incorporated into the global optimization objective function.

[0036] Subsequently, based on the vehicle dynamics constraints and the intersection time window constraints, the global optimization objective function can be solved using a model predictive control algorithm to obtain a global energy reference trajectory with travel time as the horizontal axis and recommended vehicle speed and instantaneous total energy consumption as the vertical axis.

[0037] It should be noted that the curve of the global energy reference trajectory is not a two-dimensional curve with vehicle speed on the horizontal axis and energy consumption on the vertical axis. Instead, it can be uniformly divided into two sub-graphs with travel time t as the horizontal axis and two sets of vertical axes. Figure 1 Output the optimal recommended speed ,son Figure 2 Output corresponding instantaneous total energy consumption Battery charging and discharging power The curve is bound to the arrival time constraints of each intersection throughout the entire process. Each time node corresponds to a unique recommended vehicle speed and energy allocation strategy, which simultaneously takes into account the traffic sequence and the optimal energy consumption throughout the entire process.

[0038] S103, Obtain style factors constructed based on the driver's historical driving behavior data to quantify the driver's driving preferences.

[0039] Specifically, the style factors stored in the vehicle's infotainment system can be directly accessed. Drivers can select the corresponding profile after starting the vehicle and before beginning their journey. Driving profiles can be created for each driver, thereby saving driving data for different drivers.

[0040] The process of extracting the driver's style factors includes the following steps: S1031, Collect the driver's historical driving behavior data, which includes long-term average acceleration, frequency of rapid acceleration and deceleration per unit mileage, average following distance, and frequency of following the recommended speed for green wave traffic. The frequency of rapid acceleration / deceleration can be understood as the frequency at which the absolute value of acceleration is greater than the acceleration threshold within a unit distance. It can be calculated based on the duration of acceleration or the continuous distance. This application does not limit this.

[0041] The calculation method for the frequency of compliance with the recommended speed for green wave traffic can include: System distribution within the statistical period The frequency of compliance with the green wave energy-saving vehicle speed command is calculated using the following formula: ; in, Indicates the frequency of user compliance. Indicates that the user is The number of times a user follows the recommended speed after the green wave energy-saving speed command is issued. Following the recommended speed can be understood as the difference between the user's actual speed and the recommended speed within 10 seconds after the green wave energy-saving speed command is issued being ≤ ±5km / h, and the accelerator and brake pedal travel being less than the corresponding thresholds.

[0042] S1032, perform min-max normalization on the historical driving behavior data to map each data item to a uniform numerical range and obtain a normalized feature vector.

[0043] Specifically, the original feature set corresponding to historical driving behavior data can be represented as:

[0044] in, This represents the user's average acceleration over a historical period. This indicates the frequency of rapid acceleration / deceleration per unit of time for the user. This indicates the average following distance between the user and the vehicle in front while driving.

[0045] The formula for min-max normalization is expressed as: ; In this way, historical driving behavior data can be processed into normalized feature vectors, thereby eliminating dimensional differences and unifying the feature value range.

[0046] S1033, the normalized feature vector is input into a preset style factor output model to obtain a style factor with a value between 0 and 1.

[0047] In some embodiments, a lightweight lookup table mapping model can be selected as the style factor output model. Through this lookup table mapping model, multiple sets of multidimensional feature threshold intervals can be preset to establish a piecewise linear mapping table of "normalized features-style factors". After inputting the feature vector, the continuous style factor s of 0~1 is output through interpolation. This method has extremely low computational power consumption and is suitable for low-end vehicle controllers.

[0048] In some embodiments, a pre-trained BP neural network model can also be selected. An input layer can be set to receive four normalized features, a single hidden layer can be set with six neurons, and the output layer can output a unique value s∈[0,1]. The activation function can be Sigmoid, which naturally constrains the output range. After the model training is completed offline, the network weights are solidified to the vehicle terminal.

[0049] It should be noted that the user's driving type can be determined based on the value of the style factor. A style factor s value of 0 represents an extremely economical and conservative type, while a value of 1 represents an extremely aggressive and efficient type.

[0050] S104, Real-time acquisition of target vehicle driving data and traffic flow information on the navigation path; dynamic rolling time-domain correction of the global energy reference trajectory based on the style factor, driving data, and traffic flow information, specifically including: S1041, Establish a rolling optimization time domain window and collect traffic flow information on the navigation path within the rolling optimization time domain window in real time.

[0051] The length of the rolling optimization time-domain window can be expressed as: .

[0052] Specifically, traffic flow information includes, but is not limited to, the speed of the vehicle in front, the level of road congestion, and the traffic volume of the road segment. The vehicle dynamics constraints in S102 can be corrected through traffic flow information.

[0053] S1042, based on the traffic flow information, determine the estimated intersection delay time for the target vehicle to reach each intersection, and construct a time efficiency cost based on the estimated intersection delay time, expressed as: .

[0054] S1043, compare the actual vehicle speed of the target vehicle at each moment in the rolling optimization time domain window with the recommended vehicle speed at the corresponding moment in the global energy reference trajectory, calculate the vehicle speed deviation at the corresponding moment, and construct the comfort cost based on the vehicle speed deviation, expressed by the formula: ; in, This represents the actual vehicle speed at time t. This represents the recommended vehicle speed at time t. This indicates a deviation in vehicle speed.

[0055] S1044, determine the total energy consumption rate of the target vehicle at each moment within the rolling optimization time-domain window, and construct the energy consumption cost based on the total energy consumption rate, expressed as... .

[0056] S1045, an instantaneous cost function is constructed based on time efficiency cost, comfort cost, and energy consumption cost; wherein, the weight of each cost term in the instantaneous cost function is dynamically adjusted based on the style factor.

[0057] The instantaneous cost function is expressed as follows: ; in, Indicates time efficiency weight. Indicates energy consumption weight. Indicates the weight of comfort. represents the braking energy recovery interval constraint term, and s represents the style factor.

[0058] In some embodiments, the process of dynamically adjusting the weight of each cost term in the instantaneous cost function based on the style factor specifically includes the following steps: When the style factor is greater than the style factor determination threshold, the weight of time efficiency cost is increased, and the weight of energy consumption cost and comfort cost are decreased. When the style factor is less than the style factor determination threshold, the weight of time efficiency cost is reduced, while the weight of energy consumption cost and comfort cost are increased.

[0059] For example, a style factor decision threshold can be set. Preset weight benchmark value =1、 =1、 =1, , , The preset adjustment coefficient; For aggressive drivers, style factor s> The adjustment process is illustrated in the following example: ; ; ; Amplify time efficiency weight Reduce energy consumption weight Comfort weight Simultaneously shrink the coasting recovery zone.

[0060] For economically conservative drivers, the style factor s < The adjustment process is illustrated in the following example: ; ; ; Amplify energy consumption weight Comfort weight Reduce the weight of time efficiency This triggers smooth gliding in advance and widens the energy recovery range.

[0061] It should be noted that the coasting recovery range specifically refers to the speed range within which the vehicle releases the accelerator, outputs no power, coasts relying on inertia, and engages regenerative braking. This range is represented as follows: For style factor s> Aggressive drivers can raise the lower limit. Energy recovery is permitted only at medium to high speeds, while power output is maintained at low speeds to reduce coasting time; for style factor s < For economically conservative drivers, the lower limit can be lowered. It enters the coasting recovery phase at low speed in advance to maximize energy recovery.

[0062] It should be noted that smooth coasting can be controlled through acceleration threshold constraints. For example, for economically conservative drivers, the motor drive torque can be released 2-3 seconds in advance, limiting the maximum negative acceleration during the coasting phase to a certain value. ∈[-0.5, 0]m / s², it is forbidden to release the accelerator suddenly to produce strong drag and deceleration, and a small braking energy recovery intensity command is issued simultaneously to avoid a sudden drop in vehicle speed.

[0063] S1046, Solve the instantaneous cost function within the rolling optimization time-domain window, and correct the recommended vehicle speed and instantaneous total energy consumption corresponding to each moment in the global energy reference trajectory based on the solution results, to obtain the corrected global energy reference trajectory.

[0064] S105 generates instantaneous control commands for each moment based on the corrected global energy reference trajectory, and executes predictive energy recovery and drive according to the instantaneous optimal control commands at the corresponding moment.

[0065] Specifically, the calculated instantaneous control commands include the target vehicle speed, the target drive torque, and the intensity of regenerative braking.

[0066] Specifically, the instantaneous optimal control command can be sent to the vehicle controller, and the instantaneous optimal control command includes the target vehicle speed, the target drive torque, and the braking energy recovery intensity; The vehicle controller performs power distribution based on the instantaneous optimal control command to ensure that the actual vehicle speed reaches the target vehicle speed at the corresponding moment, including: Under driving conditions, the vehicle controller allocates the output power of the engine and the drive motor according to the target driving torque, combined with the state of charge of the power battery, battery temperature and the maximum output torque limit of the drive motor. During coasting or braking, the vehicle controller performs coasting energy recovery or braking energy recovery based on the braking energy recovery intensity.

[0067] The following are apparatus embodiments of this application, which can be used to execute the method embodiments of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the method embodiments of this application.

[0068] Please see below. Figure 2 The image below is a schematic diagram of a vehicle energy management device that integrates user profiles and intersection signal coordination, provided as an exemplary embodiment of this application. The device includes: The data acquisition unit is used to acquire the navigation path of the target vehicle, determine multiple consecutive intersections along the route based on the navigation path, and extract the traffic light phase timing information of each intersection. The trajectory prediction unit is used to determine the constraints based on the traffic light phase timing information and vehicle dynamics characteristics with the goal of minimizing the total energy consumption throughout the journey, construct a global optimization objective function, and solve for the global energy reference trajectory of the target vehicle. The data acquisition unit is also used to acquire a style factor constructed based on the driver's historical driving behavior data to quantitatively characterize the driver's driving preferences; The dynamic correction unit is used to collect the driving data of the target vehicle and the traffic flow information on the navigation path in real time, and to perform rolling time-domain dynamic correction of the global energy reference trajectory based on the driving data and the traffic flow information. The vehicle control unit is used to generate instantaneous control commands for each moment based on the corrected global energy reference trajectory, and to execute predictive energy recovery and drive according to the instantaneous optimal control command at the corresponding moment.

[0069] It should be noted that the device provided in the above embodiments, when executing a vehicle energy management method that integrates user profiles and intersection signal coordination, is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments belong to the same concept, and the implementation process is detailed in the method embodiments, which will not be repeated here.

[0070] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of any of the methods described above.

[0071] Please see Figure 3 This is a structural block diagram of an electronic device provided in an embodiment of this application.

[0072] like Figure 3 As shown, the electronic device includes a processor and a memory.

[0073] In this embodiment, the processor is the control center of the computer system, and can be a processor of a physical machine or a processor of a virtual machine. The processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor can be implemented using at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), or PLA (Programmable Logic Array).

[0074] A processor can also include a main processor and a coprocessor. The main processor is used to process data in the wake-up state and is also called the CPU (Central Processing Unit). The coprocessor is a low-power processor used to process data in the standby state.

[0075] The memory may include one or more computer-readable storage media, which may be non-transitory. The memory may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments of this application, the non-transitory computer-readable storage media in the memory are used to store at least one instruction, which is executed by a processor to implement the methods in the embodiments of this application.

[0076] In some embodiments, the electronic device further includes a peripheral device interface and at least one peripheral device. The processor, memory, and peripheral device interface are connected via a bus or signal line. Each peripheral device is connected to the peripheral device interface via a bus, signal line, or circuit board. Specifically, the peripheral device includes: a display screen, a camera, and audio circuitry. The peripheral device interface can be used to connect at least one I / O (Input / Output) related peripheral device to the processor and memory.

[0077] In some embodiments of this application, the processor, memory, and peripheral device interfaces are integrated on the same chip or circuit board; in other embodiments of this application, any one or two of the processor, memory, and peripheral device interfaces can be implemented on separate chips or circuit boards. This application does not specifically limit the implementation in this regard.

[0078] The electronic device structural block diagrams shown in the embodiments of this application do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0079] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the methods in any of the foregoing embodiments. The computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives, as well as magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0080] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of software products. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A vehicle energy management method integrating user profiling and intersection signal coordination, characterized in that, include: Obtain the navigation path of the target vehicle, determine multiple consecutive intersections along the route based on the navigation path, and extract the traffic light phase timing information of each intersection. With the goal of minimizing total energy consumption throughout the journey, constraints are determined based on the traffic light phase timing information and vehicle dynamics characteristics. A global optimization objective function is then constructed, and the global energy reference trajectory of the target vehicle is obtained by solving the problem. Obtain style factors constructed based on drivers' historical driving behavior data to quantitatively characterize drivers' driving preferences; Real-time acquisition of target vehicle driving data and traffic flow information on the navigation path; dynamic rolling time-domain correction of the global energy reference trajectory based on the style factor, driving data and traffic flow information. Instantaneous control commands are generated for each moment based on the corrected global energy reference trajectory, and predictive energy recovery and drive are executed according to the instantaneous optimal control commands at the corresponding moment.

2. The vehicle energy management method integrating user profiles and intersection signal coordination according to claim 1, characterized in that, The process of obtaining the navigation path of the target vehicle, determining multiple consecutive intersections along the route based on the navigation path, and extracting the traffic light phase timing information for each intersection specifically includes: The coordinates, number of lanes, and road speed limit information of each intersection on the navigation path are extracted based on the map database. The traffic light cycle parameters for each intersection are obtained based on a cloud-based traffic management platform. The direction of travel of the target vehicle at each intersection is determined based on the navigation path, and the traffic lights at each intersection whose lane direction is consistent with the direction of travel are determined. The current phase, remaining countdown, and phase switching time of the traffic lights with the same direction are extracted from the traffic light period parameters to obtain the traffic light phase timing information.

3. The vehicle energy management method integrating user profiles and intersection signal coordination according to claim 2, characterized in that, The optimization objective is to minimize the total energy consumption throughout the entire process. Based on the traffic light phase timing information and vehicle dynamics characteristics, constraints are determined, and a global optimization objective function is constructed, including: A global optimization objective function is established with the goal of minimizing total energy consumption throughout the entire journey; wherein, the total energy consumption throughout the entire journey includes fuel consumption and power loss of the power battery. Determine vehicle dynamics constraints; the vehicle dynamics constraints include real-time vehicle speed constraints, acceleration constraints, motor torque constraints, and battery state of charge constraints. Based on the traffic light phase timing information of each intersection, the green light passage time interval of the corresponding intersection is determined, the predicted arrival time of the target vehicle at the recommended speed to the corresponding intersection is determined, and the predicted arrival time is constrained to fall within the green light passage time interval, thus constructing the intersection time window constraint. If the predicted arrival time corresponding to any recommended vehicle speed cannot fall within the green light passage time interval of the corresponding intersection, then minimizing the red light waiting time of the target vehicle at that intersection is taken as the secondary optimization objective and incorporated into the global optimization objective function. Based on the vehicle dynamics constraints and the intersection time window constraints, the model predictive control algorithm is used to solve the global optimization objective function, resulting in a global energy reference trajectory with travel time as the horizontal axis and recommended vehicle speed and instantaneous total energy consumption as the vertical axis.

4. The vehicle energy management method integrating user profiles and intersection signal coordination according to claim 1, characterized in that, The process of extracting the driver's style factors includes the following steps: Collect drivers' historical driving behavior data, which includes long-term average acceleration, frequency of rapid acceleration and deceleration per unit distance, average following distance, and frequency of following the recommended speed for green wave traffic. The historical driving behavior data are subjected to min-max normalization to map each data point to a uniform numerical range, resulting in a normalized feature vector. The normalized feature vector is input into a preset style factor output model to obtain style factors with values ​​between 0 and 1.

5. The vehicle energy management method integrating user profiles and intersection signal coordination according to claim 1, characterized in that, The dynamic correction of the global energy reference trajectory in the rolling time domain based on the driving data and the traffic flow information includes: Establish a rolling optimization time domain window and collect traffic flow information on the navigation path within the rolling optimization time domain window in real time; Based on the traffic flow information, the estimated intersection delay time for the target vehicle to arrive at each intersection is determined, and a time efficiency cost is constructed based on the estimated intersection delay time. By comparing the actual vehicle speed of the target vehicle at each moment in the rolling optimization time domain window with the recommended vehicle speed at the corresponding moment in the global energy reference trajectory, the vehicle speed deviation at the corresponding moment is calculated, and a comfort cost is constructed based on the vehicle speed deviation. Determine the total energy consumption rate of the target vehicle at each moment within the rolling optimization time window, and construct the energy consumption cost based on the total energy consumption rate; An instantaneous cost function is constructed based on time efficiency cost, comfort cost, and energy consumption cost; wherein, the weight of each cost term in the instantaneous cost function is dynamically adjusted based on the style factor; The instantaneous cost function is solved within the rolling optimization time-domain window. Based on the solution results, the recommended vehicle speed and instantaneous total energy consumption at each moment in the global energy reference trajectory are corrected to obtain the corrected global energy reference trajectory.

6. The vehicle energy management method integrating user profiles and intersection signal coordination according to claim 5, characterized in that, The process of dynamically adjusting the weight of each cost term in the instantaneous cost function based on the style factor specifically includes the following steps: When the style factor is greater than the style factor determination threshold, the weight of time efficiency cost is increased, and the weight of energy consumption cost and comfort cost are decreased. When the style factor is less than the style factor determination threshold, the weight of time efficiency cost is reduced, while the weight of energy consumption cost and comfort cost are increased.

7. The vehicle energy management method integrating user profiles and intersection signal coordination according to claim 1, characterized in that, The instantaneous optimal control command includes the target vehicle speed, target drive torque, and regenerative braking intensity at the corresponding moment. The execution of predictive energy recovery and drive based on the instantaneous optimal control command at the corresponding moment includes: The instantaneous optimal control command is sent to the vehicle controller. The instantaneous optimal control command includes the target vehicle speed, the target drive torque, and the regenerative braking intensity. The vehicle controller performs power distribution based on the instantaneous optimal control command to ensure that the actual vehicle speed reaches the target vehicle speed at the corresponding moment, including: Under driving conditions, the vehicle controller allocates the output power of the engine and the drive motor according to the target driving torque, combined with the state of charge of the power battery, battery temperature and the maximum output torque limit of the drive motor. During coasting or braking, the vehicle controller performs coasting energy recovery or braking energy recovery based on the braking energy recovery intensity.

8. A vehicle energy management device integrating user profiling and intersection signal coordination, characterized in that, include: The data acquisition unit is used to acquire the navigation path of the target vehicle, determine multiple consecutive intersections along the route based on the navigation path, and extract the traffic light phase timing information of each intersection. The trajectory prediction unit is used to determine the constraints based on the traffic light phase timing information and vehicle dynamics characteristics with the goal of minimizing the total energy consumption throughout the journey, construct a global optimization objective function, and solve for the global energy reference trajectory of the target vehicle. The data acquisition unit is also used to acquire a style factor constructed based on the driver's historical driving behavior data to quantitatively characterize the driver's driving preferences; The dynamic correction unit is used to collect the driving data of the target vehicle and the traffic flow information on the navigation path in real time, and to perform rolling time-domain dynamic correction of the global energy reference trajectory based on the driving data and the traffic flow information. The vehicle control unit is used to generate instantaneous control commands for each moment based on the corrected global energy reference trajectory, and to execute predictive energy recovery and drive according to the instantaneous optimal control command at the corresponding moment.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images