Hierarchical predictive control method, device and equipment for hybrid vehicle and storage medium

Abstract

The invention discloses a hierarchical predictive control method, device and equipment for a hybrid vehicle and a storage medium. The method comprises the following steps: determining a predicted speed sequence through a speed prediction layer according to current driving data, current traffic complexity and historical speed data; determining a transmission adjustment parameter sequence through a speed prediction layer according to the prediction speed sequence and the current traffic data; a transmission prediction layer determines a predicted engine power sequence and a predicted gear sequence according to a predicted speed sequence, a transmission adjustment parameter sequence and current transmission data obtained from a transmission control layer in real time; an engine power instruction and a target gear are determined through a transmission prediction layer based on a transmission control time period according to a predicted engine power sequence and a predicted gear sequence; and the transmission control layer controls the gearbox, the engine and the motor controller according to the engine power instruction and the target gear. According to the scheme, the real-time performance and reliability of predictive control of the hybrid vehicle can be improved.

Description

Technical Field

[0001] This application relates to the field of automotive engineering technology, and more particularly to the field of vehicle dynamics technology, specifically to a hierarchical predictive control method, device, equipment, and storage medium for hybrid vehicles. Background Technology

[0002] The energy management strategy of hybrid electric vehicles is closely related to the vehicle's real-time speed. Traditional hierarchical control typically decouples speed planning (upper layer) and energy management (lower layer). The upper layer plans a desired speed, and the lower-level energy management system (EMS) performs instantaneous optimization at that speed.

[0003] However, this method has obvious limitations: the upper-level speed planning (such as economic cruising speed) does not fully consider the efficiency characteristics of the lower-level powertrain under different operating conditions, resulting in the planned "optimal" speed curve not being truly optimal in terms of overall energy flow; the lower-level EMS is unaware of future traffic information (such as traffic lights) and cannot perform forward-looking energy buffering (such as coasting to recover energy before a green light or using battery energy to help pass through an intersection), thus missing fuel-saving opportunities; the dynamic processes of traffic information perception, speed planning, energy distribution, and torque response exist on different time scales from minutes to milliseconds, and traditional methods are difficult to coordinate these dynamic processes at different scales. Summary of the Invention

[0004] This application provides a hierarchical predictive control method, apparatus, device, and storage medium for hybrid vehicles to improve the real-time performance and reliability of predictive control for hybrid vehicles.

[0005] According to one aspect of this application, a hierarchical predictive control method for hybrid vehicles is provided, which is applied to a vehicle hierarchical management and control system; the vehicle hierarchical management and control system includes a speed prediction layer, a transmission prediction layer, and a transmission control layer; the transmission prediction layer is communicatively connected to the speed prediction layer and the transmission control layer, respectively; the method includes:

[0006] The speed prediction layer determines the current traffic complexity of the target hybrid vehicle based on the speed prediction time period and the current driving data of the target hybrid vehicle; wherein the speed prediction time period is dynamically adjusted based on the current road data and current traffic data of the target hybrid vehicle.

[0007] The speed prediction layer predicts the speed of the target hybrid vehicle based on the current driving data, the current traffic complexity, and the historical speed data of the target hybrid vehicle, thereby obtaining the predicted speed sequence of the target hybrid vehicle in the speed prediction time window.

[0008] The speed prediction layer determines the transmission adjustment parameter sequence of the target hybrid vehicle based on the predicted speed sequence and the current traffic data, and sends the predicted speed sequence and the transmission adjustment parameter sequence to the transmission prediction layer.

[0009] Based on a preset transmission prediction time period, the transmission prediction layer determines the predicted engine power sequence and predicted gear sequence of the target hybrid vehicle according to the predicted speed sequence, the transmission adjustment parameter sequence, and the current transmission data obtained in real time from the transmission control layer; wherein the transmission prediction time period is less than or equal to the speed prediction time period.

[0010] Based on a preset transmission control time period, the transmission prediction layer determines the engine power command and target gear according to the predicted engine power sequence and the predicted gear sequence, and sends the engine power command and the target gear to the transmission control layer; wherein, the transmission control time period is shorter than the transmission prediction time period;

[0011] The transmission control layer controls the gearbox, engine, and motor controller of the target hybrid vehicle according to the engine power command and the target gear.

[0012] According to another aspect of this application, a hybrid vehicle hierarchical predictive control device is provided, which is configured in a vehicle hierarchical management and control system; the vehicle hierarchical management and control system includes a speed prediction layer, a transmission prediction layer, and a transmission control layer; the transmission prediction layer is communicatively connected to the speed prediction layer and the transmission control layer, respectively; the device includes:

[0013] The traffic assessment module is used to determine the current traffic complexity of the target hybrid vehicle based on the speed prediction time period and the current driving data of the target hybrid vehicle through the speed prediction layer; wherein, the speed prediction time period is dynamically adjusted according to the current road data and current traffic data of the target hybrid vehicle.

[0014] The speed prediction module is used to predict the speed of the target hybrid vehicle through the speed prediction layer based on the current driving data, the current traffic complexity and the historical speed data of the target hybrid vehicle, so as to obtain the predicted speed sequence of the target hybrid vehicle in the speed prediction time window.

[0015] The adjustment parameter determination module is used to determine the transmission adjustment parameter sequence of the target hybrid vehicle through the speed prediction layer based on the predicted speed sequence and the current traffic data, and send the predicted speed sequence and the transmission adjustment parameter sequence to the transmission prediction layer;

[0016] The transmission data prediction module is used to determine the predicted engine power sequence and predicted gear sequence of the target hybrid vehicle based on the predicted speed sequence, the transmission adjustment parameter sequence, and the current transmission data obtained in real time from the transmission control layer, using the transmission prediction layer based on a preset transmission prediction time period; wherein the transmission prediction time period is less than or equal to the speed prediction time period.

[0017] The instruction generation module is used to determine the engine power instruction and the target gear based on the predicted engine power sequence and the predicted gear sequence through the transmission prediction layer based on a preset transmission control time period, and send the engine power instruction and the target gear to the transmission control layer; wherein the transmission control time period is shorter than the transmission prediction time period;

[0018] The transmission control module is used to control the transmission, engine, and motor controller of the target hybrid vehicle through the transmission control layer according to the engine power command and the target gear.

[0019] According to another aspect of this application, an electronic device is provided, the electronic device comprising:

[0020] One or more processors;

[0021] Memory, used to store one or more programs;

[0022] When the one or more programs are executed by the one or more processors, the one or more processors implement any of the hybrid vehicle hierarchical predictive control methods provided in the embodiments of this application.

[0023] According to another aspect of this application, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements any of the hybrid vehicle hierarchical predictive control methods provided in the embodiments of this application.

[0024] According to another aspect of this application, a computer program product is provided, including a computer program that, when executed by a processor, implements any of the hybrid vehicle hierarchical predictive control methods provided in the embodiments of this application.

[0025] This application uses a speed prediction layer to determine the current traffic complexity of the target hybrid vehicle based on its current driving data and a speed prediction time period. The speed prediction time period is dynamically adjusted based on the target hybrid vehicle's current road and traffic data. The speed prediction layer predicts the target hybrid vehicle's speed based on current driving data, current traffic complexity, and historical speed data, obtaining a predicted speed sequence for the target hybrid vehicle within the predicted time window. The speed prediction layer then determines the transmission adjustment parameter sequence of the target hybrid vehicle based on the predicted speed sequence and current traffic data, and sends both the predicted speed sequence and transmission adjustment parameter sequence to the transmission prediction layer. The transmission prediction layer then... Within a preset transmission prediction time period, based on the predicted speed sequence, transmission adjustment parameter sequence, and current transmission data obtained in real time from the transmission control layer, the predicted engine power sequence and predicted gear sequence of the target hybrid vehicle are determined. The transmission prediction time period is less than or equal to the speed prediction time period. Based on a preset transmission control time period, the transmission prediction layer determines the engine power command and target gear according to the predicted engine power sequence and predicted gear sequence, and sends the engine power command and target gear to the transmission control layer. The transmission control time period is less than the transmission prediction time period. The transmission control layer controls the transmission, engine, and motor controllers of the target hybrid vehicle according to the engine power command and target gear. This technical solution, by performing hierarchical collaborative optimization of three control problems at different time scales—long-term ecological driving speed planning, mid-term energy management and gear decision-making, and engine and motor control—within a unified framework, breaks the old pattern of separation between speed and energy management in traditional methods, thus helping to improve the real-time performance and reliability of predictive control for hybrid vehicles. Attached Figure Description

[0026] Figure 1 This is a flowchart of a hierarchical predictive control method for hybrid vehicles according to Embodiment 1 of this application;

[0027] Figure 2 This is a flowchart of a hierarchical predictive control method for hybrid vehicles according to Embodiment 2 of this application;

[0028] Figure 3 This is a schematic diagram of the structure of a hybrid vehicle layered predictive control device according to Embodiment 3 of this application;

[0029] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the hierarchical predictive control method for hybrid vehicles according to Embodiment 4 of this application. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] Furthermore, it should be noted that the collection, storage, use, processing, transmission, provision, and disclosure of relevant data such as speed prediction time periods and current driving data involved in the technical solution of this application all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0033] Example 1

[0034] Figure 1 This is a flowchart of a hybrid vehicle hierarchical predictive control method according to Embodiment 1 of this application. This embodiment is applicable to situations where hybrid vehicles achieve global energy management in complex connected traffic environments. It can be executed by a hybrid vehicle hierarchical predictive control device, which can be implemented in hardware and / or software. This device can be configured in a computer device, such as a vehicle hierarchical management system. The vehicle hierarchical management system includes a speed prediction layer, a transmission prediction layer, and a transmission control layer. The transmission prediction layer is communicatively connected to both the speed prediction layer and the transmission control layer. Figure 1 As shown, the method includes:

[0035] S110. Based on the speed prediction time period, the current traffic complexity of the target hybrid vehicle is determined by the speed prediction layer according to the current driving data of the target hybrid vehicle; wherein, the speed prediction time period is dynamically adjusted according to the current road data and current traffic data of the target hybrid vehicle.

[0036] The speed prediction layer is a layer within the system primarily responsible for predicting vehicle speeds over a future period based on current road and traffic information and vehicle driving conditions. The speed prediction time period refers to the time range or time segment used for speed prediction; the length of this period is dynamically adjusted, depending on current road and traffic conditions. The target hybrid vehicle refers to a vehicle equipped with both an internal combustion engine and an electric motor, requiring global energy management. Current driving data refers to the real-time driving information of the hybrid vehicle, including speed, acceleration, and direction, which, along with traffic data and road conditions, influences the vehicle's driving state. Current traffic complexity refers to the complexity of the current traffic situation, typically a result of the combined influence of factors such as traffic density, traffic flow, and traffic signals; higher traffic complexity means the vehicle needs to adjust its speed and driving strategy more frequently. Current road data refers to real-time information about the road where the hybrid vehicle is located, including road type, road surface conditions, slope information, traffic signs, and traffic lights. Current traffic data refers to the real-time traffic conditions of the environment in which the hybrid vehicle is located, including traffic flow, traffic density, traffic accidents or obstacles, traffic signal status, and traffic regulations.

[0037] For example, the current traffic complexity can be determined by the following formula:

[0038] ;

[0039] CI stands for CI. , and It is determined through extensive experimentation and pre-set based on actual conditions or empirical values. B refers to the speed variance of the target hybrid vehicle, reflecting the degree of speed fluctuation. C refers to the distance variation coefficient of the target hybrid vehicle, which is the ratio of the distance standard deviation to the mean, reflecting following stability. D refers to the lane-changing frequency of the target hybrid vehicle, the number of lane changes per unit time, reflecting the degree of driving aggression.

[0040] S120. Based on the current driving data, current traffic complexity, and historical speed data of the target hybrid vehicle, the speed prediction layer predicts the speed of the target hybrid vehicle and obtains the predicted speed sequence of the target hybrid vehicle within the speed prediction time window.

[0041] Historical speed data refers to the driving speed data of hybrid vehicles over a past period. Predicted speed sequence refers to the list of expected speed changes of vehicles over a future period, calculated by the speed prediction layer.

[0042] In one optional implementation, after obtaining the predicted speed sequence of the target hybrid vehicle within the speed prediction time window through the speed prediction layer, the speed prediction layer can further optimize the predicted speed sequence based on the current fuel consumption data of the target hybrid vehicle, constrained by the vehicle dynamics model, to obtain an optimized predicted speed sequence; wherein, the vehicle dynamics model is predetermined based on the powertrain architecture of the target hybrid vehicle.

[0043] The vehicle dynamics model is a mathematical model used to describe the dynamic behavior of a vehicle under different operating conditions; it considers the vehicle's powertrain (such as engine, electric motor, and transmission) and the vehicle's physical characteristics (such as mass, tire friction, and air resistance). Current fuel consumption data refers to the amount of fuel consumed by the vehicle under specific conditions (such as specific speed, driving mode, and road conditions). The powertrain architecture refers to the vehicle's drive mode (such as hybrid, pure electric, or gasoline-powered) and the coordination between its various systems.

[0044] Specifically, the vehicle dynamics model can be used as a constraint, and an objective function can be set for the optimization of the predicted speed sequence based on the current fuel consumption data of the target hybrid vehicle. The predicted speed sequence can be optimized by minimizing the objective function to obtain the optimized predicted speed sequence.

[0045] For example, a vehicle dynamics model can be represented by the following formula:

[0046] ;

[0047] Where m is the vehicle's curb weight, and v is the vehicle's speed. It refers to the driving force, provided by the powertrain, and is a control variable in the speed prediction sequence optimization process. It refers to braking force. This refers to the rolling resistance coefficient. It refers to gravitational acceleration. It refers to the road slope angle. It refers to air density. This refers to the drag coefficient. A refers to the vehicle's frontal area.

[0048] For example, the objective function can be minimized by the following formula:

[0049] ;

[0050] in, This refers to the objective function value, used to represent the time window from time t to... The system calculates the overall performance score by minimizing this function to optimize the vehicle's energy efficiency, speed control accuracy, and performance at traffic lights. , and These are weighting parameters used to balance the relative importance of different parts of the objective function. This refers to fuel consumption rate. This refers to the desired speed, which is usually the speed limit on the road or the target speed set according to driving strategy. This refers to the traffic light communication penalty function, used to penalize vehicles for sudden acceleration or deceleration during red lights, encouraging vehicles to pass smoothly through the intersection during green lights. 's' refers to the traffic signal status at the intersection (e.g., red or green light).

[0051] It should be noted that, This means that the powertrain (engine, motor, battery, transmission system) is regarded as a "black box", and its overall average fuel consumption is directly proportional to the driving power required by the vehicle or there is a non-linear mapping relationship. This mapping relationship can be obtained by fitting the historical data of the whole vehicle under typical operating conditions. Its purpose is to quickly and roughly assess the energy consumption corresponding to different speed curves at the strategic level, without involving complex component details.

[0052] Furthermore, the traffic light communication penalty function can be expressed by the following formula:

[0053] ;

[0054] in, and It is a very large positive penalty weight, and the values ​​of both are determined through simulation and expert experience.

[0055] It's understandable that predicting a vehicle will reach the stop line during a red light is a non-ideal traffic situation. In this case, the vehicle might need to come to a complete stop and wait for the light to end, wasting time and increasing energy consumption due to sudden braking and subsequent acceleration. Even if the vehicle hasn't reached the stop line but is predicted to stop at a red light, the final result is still a stop, but it differs from the situation where the light is red when the vehicle has already reached the stop line. In this case, there might be room for adjustment, such as adjusting the speed to stop at a suitable location. The involvement of speed demonstrates that the negative impact of stopping at higher speeds is greater because sudden braking at high speeds increases energy consumption and reduces safety. Sudden braking significantly increases fuel or electrical energy consumption, and during sudden braking and subsequent acceleration, the engine deviates from its economic operating range, increasing emissions. Simultaneously, stopping itself increases energy consumption, and frequent occurrences can affect passenger comfort, negatively impacting both driving economy and comfort. Introducing a traffic light penalty function into the speed prediction optimization process can help improve the reliability of speed prediction, making it more closely reflect actual road conditions, and further improving passenger comfort while ensuring the real-time nature and accuracy of speed prediction.

[0056] S130. Based on the predicted speed sequence and current traffic data, the speed prediction layer determines the transmission adjustment parameter sequence of the target hybrid vehicle and sends the predicted speed sequence and transmission adjustment parameter sequence to the transmission prediction layer.

[0057] The transmission adjustment parameter sequence refers to a series of parameters calculated based on speed prediction results and traffic data, used to guide the prediction of the transmission system. The transmission prediction layer is a layer of the system that mainly provides necessary operating parameters to the control layer by predicting the operating state of the vehicle's transmission system, such as engine power and gear position.

[0058] Optionally, the speed prediction layer determines the motion state prediction sequence of the target hybrid vehicle based on the predicted speed sequence and current traffic data; the speed prediction layer determines the transmission adjustment parameter sequence of the target hybrid vehicle based on the correspondence between candidate motion states and candidate transmission adjustment parameters and the motion state prediction sequence.

[0059] The motion state prediction sequence refers to the sequence of motion states of the target hybrid vehicle over a future period, generated by the speed prediction layer; these motion states can include information such as position, speed, acceleration, and direction. Candidate motion states refer to multiple possible motion states considered by the system during optimization based on vehicle operating conditions, traffic environment, and expected goals; these states can encompass different combinations of speed, acceleration, and position. Candidate transmission adjustment parameters refer to multiple possible transmission system adjustment parameters that the system can select under different driving scenarios and motion states.

[0060] For example, the correspondence between candidate motion states and candidate transmission adjustment parameters can be expressed by the following formula:

[0061] ;

[0062] in, This refers to the candidate transmission adjustment parameters.

[0063] S140. Based on a preset transmission prediction time period, the transmission prediction layer determines the predicted engine power sequence and predicted gear sequence of the target hybrid vehicle according to the predicted speed sequence, transmission adjustment parameter sequence, and current transmission data obtained in real time from the transmission control layer; wherein, the transmission prediction time period is less than or equal to the speed prediction time period.

[0064] The transmission prediction time period refers to the time range or period used for transmission prediction, which is usually less than or equal to the speed prediction time period. Current transmission data refers to real-time information in the vehicle's transmission system, including parameters such as engine speed, power output, and the vehicle's current gear. The predicted engine power sequence refers to the engine power output sequence for a future period calculated at the transmission prediction layer based on the predicted speed, transmission adjustment parameters, and current transmission data. The predicted gear sequence refers to the gear shifting sequence calculated at the transmission prediction layer based on the predicted speed and engine power sequence.

[0065] Optionally, the transmission prediction layer, based on a preset transmission prediction time period, employs a model predictive control algorithm, constrained by the hybrid power model of the target hybrid vehicle, to determine the predicted transmission data sequence of the target hybrid vehicle according to the predicted speed sequence and the current transmission data obtained in real time from the transmission control layer; wherein, the hybrid power model is predetermined based on the transmission system architecture of the target hybrid vehicle; and the transmission prediction layer, based on the Pontryagin minimum principle, determines the predicted engine power sequence and predicted gear sequence of the target hybrid vehicle according to the predicted transmission data sequence and the transmission adjustment parameter sequence.

[0066] The hybrid power model is a mathematical model describing the working mechanism of the powertrain system (including components such as the engine, electric motor, and battery) of a hybrid vehicle. This model considers the coordination and switching between different power sources, such as the combined operation of the engine and electric motor, and energy flow. Predictive transmission data sequence refers to a series of future transmission system data generated through the transmission prediction layer, including parameters such as engine speed, power output, electric motor power, and transmission gear. The vehicle energy management model is an energy management algorithm model constructed based on historical transmission data of hybrid vehicles, combined with the vehicle's energy consumption and storage characteristics. It typically includes modules for energy prediction, optimized scheduling, and power allocation, enabling dynamic adjustment of the vehicle's energy usage and optimization of fuel efficiency. Model predictive control (MPC) is an algorithm that uses a mathematical model of the system to predict the system's behavior over a future period and optimizes the control strategy based on the prediction results. In hybrid vehicles, MPC is commonly used to optimize the control of the transmission system. Pontryagin's minimum principle is a mathematical optimization method widely used in the optimal control problem of dynamic systems. In hybrid vehicles, it is often used to optimize energy management strategies. This principle helps to determine the optimal control strategy by optimizing vehicle energy consumption, emissions, and other objectives, ensuring the efficient operation of the hybrid system under different driving conditions.

[0067] For example, within each preset transmission prediction time period, the transmission prediction layer uses the current state (vehicle speed, displacement, battery state of charge, engine speed, etc.) as the initial value, and predicts the transmission data sequence based on the hybrid power model and the predicted speed sequence. The predicted transmission data sequence is a sequence containing all state variables (vehicle speed, displacement, battery state of charge, etc.) in the prediction time domain. For each state point in the predicted transmission data sequence, the optimal power allocation problem is constructed as a Pontryagin minimum principle problem and solved quickly. The boundary value problem between the two points is solved online using numerical methods (such as the target shooting method) (i.e., given the starting state and the ending constraint, the change process of the intermediate control variables and state variables is solved), to obtain the optimal engine power sequence and gear sequence.

[0068] In one alternative implementation, before making predictions using the transmission adjustment parameter sequence, the transmission adjustment parameter sequence needs to be dynamically updated, as shown in the following formula:

[0069] ;

[0070] in, It refers to the dynamically updated sequence of transmission adjustment parameters. This refers to the fundamental costate variables, which are obtained offline through a traditional battery state-of-charge balancing strategy. This refers to the adjustment coefficient, which has a value range of [0.1, 0.3] and is predetermined through simulation optimization. This refers to the sequence of transmission adjustment parameters before the update.

[0071] Furthermore, the Pontryagin minimum principle problem can be expressed by the following formula:

[0072] ;

[0073] In this embodiment, x refers to the state variable; where, s refers to vehicle displacement, v refers to vehicle speed, and SOC refers to battery state of charge. This refers to control variables; among them, , "Gear" refers to the engine power, and "Gear" refers to the gearbox gears. This refers to costate variables, which in a physical sense represent the marginal cost of the corresponding state variable, i.e., the degree of impact of the state change on the overall objective function (fuel consumption); among them, , It refers to the costate variable of vehicle displacement. This refers to the costate variable of vehicle speed. It refers to the co-state variable of the battery's state of charge. This refers to engine speed. This refers to fuel consumption rate. It refers to vehicle acceleration. This refers to the change in the state of the battery.

[0074] S150. Based on a preset transmission control time period, the transmission prediction layer determines the engine power command and target gear according to the predicted engine power sequence and predicted gear sequence, and sends the engine power command and target gear to the transmission control layer; wherein, the transmission control time period is shorter than the transmission prediction time period.

[0075] The transmission control time cycle refers to the time interval between control actions performed by the transmission control layer. This time cycle is shorter than the transmission prediction time cycle, indicating that the control layer will make more frequent adjustments within a shorter period to adapt to the dynamic driving environment. The engine power command is a control command given based on the engine power sequence, indicating how much power should be provided to drive the engine. The target gear refers to the target gear setting command given by the transmission prediction layer.

[0076] Specifically, based on a preset transmission control time period, the transmission prediction layer sequentially generates engine power commands and target gears from the predicted engine power sequence and predicted gear sequence, and then sends the engine power commands and target gears to the transmission control layer.

[0077] For example, when the transmission prediction layer sends the engine power command and target gear to the transmission control layer for the first time based on the preset transmission control time period, the first engine power element and gear element in the predicted engine power sequence and predicted gear sequence are sent to the execution layer.

[0078] S160: The transmission control layer controls the gearbox, engine, and motor controller of the target hybrid vehicle according to the engine power command and the target gear.

[0079] The transmission control layer refers to a layer primarily used to control the transmission hardware devices of the target hybrid vehicle, such as the engine and motor, based on received transmission control commands. Engine and motor controllers are hardware devices in the vehicle used to regulate the operating states of the engine and motor; they adjust the engine's power output and the motor's operating mode according to the commands from the transmission control layer, thereby optimizing the vehicle's powertrain operation.

[0080] For example, when the transmission control layer detects that the target gear is inconsistent with the current gear of the target hybrid vehicle, it sends a shift request to the transmission control unit of the target hybrid vehicle. The transmission control unit performs a safety check based on preset shift rules (ensuring the engine operates in the high-efficiency range and avoiding frequent shifts) and the current vehicle status (such as vehicle speed and throttle opening), and then executes a series of hydraulic or electric actions such as disengaging, selecting, and engaging the gear. The transmission control layer determines the engine torque based on the engine power command and engine speed. The transmission control layer determines the motor compensation torque based on the engine torque and the vehicle's required torque. The transmission control layer controls the engine based on the engine torque and controls the motor controller based on the motor compensation torque.

[0081] Engine torque refers to the rotational torque output by the engine, typically generated by the engine's combustion process or an electric motor, controlling the vehicle's power output. Vehicle torque demand refers to the total torque required by the vehicle based on driving needs and current driving conditions (such as acceleration, deceleration, or constant speed), representing the power output required by the vehicle at a specific moment. Motor compensation torque refers to the torque calculated by the electric motor to compensate for the difference between engine torque and vehicle torque demand. It ensures that the torque output of the engine and electric motor are coordinated under different driving conditions, thereby guaranteeing the overall performance of the vehicle.

[0082] For example, engine torque can be determined by the following formula:

[0083] ;

[0084] in, This refers to engine torque. This refers to the engine power required by the engine power command. This refers to the current engine speed.

[0085] For example, the required torque for the entire vehicle can be determined by the following formula:

[0086] ;

[0087] in, This refers to the torque required by the entire vehicle. This refers to the wheel radius. This refers to the gearbox ratio.

[0088] For example, the motor compensation torque can be determined by the following formula:

[0089] ;

[0090] in, This refers to the motor's compensation torque.

[0091] In one alternative implementation, the transmission control layer can feed back the actual state of the engine and motor controllers of the target hybrid vehicle after execution to the transmission prediction layer, so as to update the algorithm and model parameters of the transmission prediction layer.

[0092] This application embodiment uses a speed prediction layer to determine the current traffic complexity of the target hybrid vehicle based on the speed prediction time period and the current driving data of the target hybrid vehicle. The speed prediction time period is dynamically adjusted based on the current road data and current traffic data of the target hybrid vehicle. The speed prediction layer predicts the speed of the target hybrid vehicle based on the current driving data, current traffic complexity, and historical speed data of the target hybrid vehicle, obtaining a predicted speed sequence for the target hybrid vehicle within the speed prediction time window. The speed prediction layer then determines the transmission adjustment parameter sequence of the target hybrid vehicle based on the predicted speed sequence and current traffic data, and sends the predicted speed sequence and transmission adjustment parameter sequence to the transmission prediction layer. The transmission prediction... The transmission prediction layer, based on a preset transmission prediction time period, determines the predicted engine power sequence and predicted gear sequence of the target hybrid vehicle according to the predicted speed sequence, transmission adjustment parameter sequence, and current transmission data obtained in real time from the transmission control layer. The transmission prediction time period is less than or equal to the speed prediction time period. Based on a preset transmission control time period, the transmission prediction layer determines the engine power command and target gear according to the predicted engine power sequence and predicted gear sequence, and sends the engine power command and target gear to the transmission control layer. The transmission control time period is less than the transmission prediction time period. The transmission control layer controls the transmission, engine, and motor controllers of the target hybrid vehicle according to the engine power command and target gear. This technical solution, by performing layered collaborative optimization of three control problems at different time scales—long-term ecological driving speed planning, mid-term energy management and gear decision-making, and engine and motor control—within a unified framework, breaks the old pattern of separation between speed and energy management in traditional methods, and helps improve the real-time performance and reliability of predictive control for hybrid vehicles.

[0093] Example 2

[0094] Figure 2This is a flowchart of a hierarchical predictive control method for hybrid vehicles according to Embodiment 2 of this application. Based on the technical solutions of the above embodiments, this embodiment refines the process of "predicting the speed of the target hybrid vehicle based on current driving data, current traffic complexity, and historical speed data of the target hybrid vehicle through a speed prediction layer, obtaining a predicted speed sequence of the target hybrid vehicle within the speed prediction time window" into "determining the target speed prediction model of the target hybrid vehicle based on the correspondence between candidate traffic complexity and candidate speed prediction models, according to the current traffic complexity; wherein, the candidate speed prediction models include a steady traffic flow prediction model and a dynamic traffic flow prediction model; and predicting the speed of the target hybrid vehicle based on the target speed prediction model, according to current driving data and historical speed data of the target hybrid vehicle, obtaining a predicted speed sequence of the target hybrid vehicle within the speed prediction time window." It should be noted that for parts not detailed in this embodiment, please refer to the relevant descriptions in other embodiments. Figure 2 As shown, the method includes:

[0095] S210. Based on the speed prediction time period, the current traffic complexity of the target hybrid vehicle is determined by the speed prediction layer according to the current driving data of the target hybrid vehicle.

[0096] S220. Based on the correspondence between candidate traffic complexity and candidate speed prediction models, the target speed prediction model for the target hybrid vehicle is determined according to the current traffic complexity through the speed prediction layer; wherein, the candidate speed prediction models include a steady traffic flow prediction model and a dynamic traffic flow prediction model.

[0097] The correspondence between candidate traffic complexity and candidate speed prediction models refers to the relationship or matching rule between traffic complexity and prediction models. Based on different traffic complexities (such as smooth flow, congestion, etc.), the system selects different speed prediction models for prediction. The target speed prediction model is a mathematical or algorithmic model that predicts the future speed changes of a target hybrid vehicle based on traffic complexity and other relevant factors. A smooth traffic flow prediction model is suitable for scenarios with relatively stable traffic flow, large distances between vehicles, and relatively smooth traffic conditions. This model typically assumes low traffic volume, minimal traffic signal fluctuations, and relatively constant vehicle speeds. A dynamic traffic flow prediction model is suitable for scenarios with dense traffic flow and significant speed variations. This model typically considers factors such as traffic signal changes, sudden traffic events, and traffic accidents, and the prediction results may change frequently.

[0098] For example, the current traffic complexity is compared with the upper and lower thresholds of the complexity classification threshold; if the current traffic complexity is less than the lower threshold, the steady traffic flow prediction model is determined as the target speed prediction model; if the current traffic complexity is greater than or equal to the lower threshold and less than or equal to the upper threshold, both the steady traffic flow prediction model and the dynamic traffic flow prediction model are determined as the target speed prediction model; if the current traffic complexity is greater than the upper threshold, the dynamic traffic flow prediction model is determined as the target speed prediction model.

[0099] S230. Based on the target speed prediction model, the speed prediction layer predicts the speed of the target hybrid vehicle according to the current driving data and the historical speed data of the target hybrid vehicle, and obtains the predicted speed sequence of the target hybrid vehicle in the speed prediction time window.

[0100] Optionally, if the target speed prediction model includes both a steady traffic flow prediction model and a dynamic traffic flow prediction model, then the speed prediction layer determines the model weight ratio between the steady traffic flow prediction model and the dynamic traffic flow prediction model based on traffic complexity and a preset complexity threshold. The speed prediction layer then predicts the speed of the target hybrid vehicle based on the steady traffic flow prediction model and its historical speed data, obtaining a first candidate speed sequence for the target hybrid vehicle within the speed prediction time window. The steady traffic flow prediction model is trained on an autoregressive integral moving average model based on the historical speed sequence of the target hybrid vehicle. The speed prediction layer then predicts the speed of the target hybrid vehicle based on the dynamic traffic flow prediction model and its current driving data, obtaining a second candidate speed sequence for the target hybrid vehicle within the speed prediction time window. The dynamic traffic flow prediction model is trained on a hidden Markov model based on the historical driving data and historical speed sequence of the target hybrid vehicle. Finally, the speed prediction layer weights and sums the first and second candidate speed sequences according to the model weight ratio to obtain the predicted speed sequence of the target hybrid vehicle within the speed prediction time window.

[0101] The complexity threshold is pre-set based on actual conditions or experience. This threshold can include at least one of a lower complexity threshold and an upper complexity threshold, with the lower threshold being lower than the upper threshold. The model weight ratio refers to the proportion of weights assigned to each model among multiple prediction models based on different traffic complexities and preset thresholds; different weight ratios reflect the reliability of model predictions under different traffic environments. The autoregressive integral moving average model is a time series prediction model commonly used to predict stationary time series data. It combines autoregression, differencing, and moving average components, making it suitable for scenarios with relatively stable historical data. The hidden Markov model is a statistical model used to describe the stochastic process of a system in a hidden state. It is typically used to process and predict data containing uncertainty or hidden structures, particularly in dynamic systems and time series prediction. Historical speed sequences refer to the driving speed records of the target hybrid vehicle over a past period. This data provides the model with a time series of vehicle speeds, providing a foundation for training the prediction model. Historical driving data refers to the driving records of the target hybrid vehicle over a period of time, including speed, acceleration, driving route, and traffic conditions. It provides data support for dynamic traffic flow prediction models. The first candidate speed sequence is a speed sequence predicted using the historical speed data of the target hybrid vehicle based on a stationary traffic flow prediction model. This sequence represents the possible driving speed of the target hybrid vehicle under stable traffic conditions, serving as a candidate result for speed prediction. The second candidate speed sequence is a speed sequence predicted using the historical driving data of the target hybrid vehicle based on a dynamic traffic flow prediction model. This sequence represents the possible driving speed of the target hybrid vehicle under complex or unstable traffic conditions.

[0102] For example, the weights of the stationary traffic flow prediction model in the model weight ratio can be determined by the following formula:

[0103] ;

[0104] in, This refers to the weights in the steady-state traffic flow prediction model. CI refers to the current traffic complexity. This refers to the threshold value under the preset complexity division. This refers to the preset threshold for complexity classification.

[0105] Correspondingly, the weight of the dynamic traffic flow prediction model in the model weight ratio can be 1-β.

[0106] For example, a steady traffic flow prediction model can be implemented using the following formula:

[0107] ;

[0108] in, This refers to the predicted velocity value at the current time t. This refers to the coefficient of the autoregressive term. This coefficient is a parameter of the autoregressive part in the model and reflects the impact of the speed at past p times on the current predicted speed. It is obtained through offline training using historical smooth driving data. This refers to the vehicle speed at a historical moment. It refers to the prediction error at the current moment, which is the difference between the predicted velocity and the actual observed velocity. This refers to the prediction error at past moments. This refers to the moving average coefficient, which represents the impact of past prediction errors on current speed predictions. It is obtained through offline training using historical smooth driving data.

[0109] For example, a dynamic traffic flow prediction model can be implemented using the following formula:

[0110] ;

[0111] in, Refers to the current speed and transportation modes Predict vehicle speed in the next moment The probability of traffic patterns can include at least one of the following modes, lane changing modes, rapid acceleration modes, and rapid deceleration modes. It refers to the probability that the hidden state is i at the initial moment. It represents the probability that the traffic scenario is in a certain hidden state when the model starts. This parameter reflects the initial distribution of traffic patterns and is usually estimated through historical data. This refers to the observation matrix, which represents the predicted vehicle speed at the next moment based on observations in hidden state i. The probability of a vehicle speed distribution under a specific traffic mode (such as following mode, lane changing mode, etc.) can be obtained through historical data statistics and can reflect the typical variation pattern of vehicle speed under different traffic modes. It refers to the state transition matrix, which represents the probability of transitioning from the hidden state i at the current time to the hidden state j at the next time. This probability is usually obtained by training with a large amount of natural driving data and reflects the transition patterns between different traffic modes, such as the transition probability from following mode to rapid acceleration mode, and from lane changing mode to rapid deceleration mode.

[0112] Optionally, if the target speed prediction model is a steady traffic flow prediction model, then the speed prediction layer is based on the steady traffic flow prediction model and uses the historical speed data of the target hybrid vehicle to predict the speed of the target hybrid vehicle, thereby obtaining the predicted speed sequence of the target hybrid vehicle within the speed prediction time window.

[0113] Optionally, if the target speed prediction model is a dynamic traffic flow prediction model, then the speed prediction layer is based on the dynamic traffic flow prediction model and the current driving data to predict the speed of the target hybrid vehicle, thereby obtaining the predicted speed sequence of the target hybrid vehicle within the speed prediction time window.

[0114] S240. Based on the predicted speed sequence and current traffic data, the speed prediction layer determines the transmission adjustment parameter sequence of the target hybrid vehicle and sends the predicted speed sequence and transmission adjustment parameter sequence to the transmission prediction layer.

[0115] S250: Based on a preset transmission prediction time period, the transmission prediction layer determines the predicted engine power sequence and predicted gear sequence of the target hybrid vehicle according to the predicted speed sequence, transmission adjustment parameter sequence, and current transmission data obtained in real time from the transmission control layer.

[0116] S260. Based on a preset transmission control time period, the transmission prediction layer determines the engine power command and target gear according to the predicted engine power sequence and predicted gear sequence, and sends the engine power command and target gear to the transmission control layer.

[0117] S270 controls the transmission, engine, and motor controllers of the target hybrid vehicle through the transmission control layer based on the engine power command and target gear.

[0118] This application embodiment determines the current traffic complexity of the target hybrid vehicle based on the current driving data of the target hybrid vehicle through a speed prediction layer using a speed prediction time period. It then determines the target speed prediction model for the target hybrid vehicle based on the correspondence between candidate traffic complexities and candidate speed prediction models, according to the current traffic complexity. The candidate speed prediction models include a steady traffic flow prediction model and a dynamic traffic flow prediction model. Based on the target speed prediction model, the speed prediction layer predicts the speed of the target hybrid vehicle using current driving data and historical speed data, obtaining a predicted speed sequence for the target hybrid vehicle within the speed prediction time window. Finally, the speed prediction layer calculates the predicted speed sequence based on the current traffic data. The system determines the transmission adjustment parameter sequence of the target hybrid vehicle and sends the predicted speed sequence and transmission adjustment parameter sequence to the transmission prediction layer. Based on a preset transmission prediction time period, the transmission prediction layer determines the predicted engine power sequence and predicted gear sequence of the target hybrid vehicle according to the predicted speed sequence, transmission adjustment parameter sequence, and current transmission data obtained in real time from the transmission control layer. Based on a preset transmission control time period, the transmission prediction layer determines the engine power command and target gear according to the predicted engine power sequence and predicted gear sequence, and sends the engine power command and target gear to the transmission control layer. The transmission control layer controls the transmission, engine, and motor controllers of the target hybrid vehicle according to the engine power command and target gear. This technical solution, by selecting different speed prediction models according to different traffic complexities, can effectively improve the accuracy and reliability of speed prediction in complex connected traffic environments.

[0119] Example 3

[0120] Figure 3 This is a schematic diagram of a hybrid vehicle hierarchical predictive control device according to Embodiment 3 of this application. It is applicable to situations where hybrid vehicles achieve global energy management in complex connected traffic environments. This hybrid vehicle hierarchical predictive control device can be implemented in hardware and / or software and can be configured in computer equipment, such as a vehicle hierarchical management system. The vehicle hierarchical management system includes a speed prediction layer, a transmission prediction layer, and a transmission control layer. The transmission prediction layer is communicatively connected to both the speed prediction layer and the transmission control layer. Figure 3 As shown, the device includes:

[0121] The traffic assessment module 310 is used to determine the current traffic complexity of the target hybrid vehicle based on the speed prediction time period and the current driving data of the target hybrid vehicle through the speed prediction layer; wherein, the speed prediction time period is dynamically adjusted according to the current road data and current traffic data of the target hybrid vehicle.

[0122] The speed prediction module 320 is used to predict the speed of the target hybrid vehicle by using the speed prediction layer based on the current driving data, the current traffic complexity and the historical speed data of the target hybrid vehicle, so as to obtain the predicted speed sequence of the target hybrid vehicle in the speed prediction time window.

[0123] The adjustment parameter determination module 330 is used to determine the transmission adjustment parameter sequence of the target hybrid vehicle based on the predicted speed sequence and current traffic data through the speed prediction layer, and send the predicted speed sequence and transmission adjustment parameter sequence to the transmission prediction layer.

[0124] The transmission data prediction module 340 is used to determine the predicted engine power sequence and predicted gear sequence of the target hybrid vehicle based on the transmission prediction layer and a preset transmission prediction time period, according to the predicted speed sequence, transmission adjustment parameter sequence and current transmission data obtained in real time from the transmission control layer; wherein, the transmission prediction time period is less than or equal to the speed prediction time period.

[0125] The instruction generation module 350 is used to determine the engine power instruction and the target gear based on the predicted engine power sequence and the predicted gear sequence through the transmission prediction layer based on the preset transmission control time period, and send the engine power instruction and the target gear to the transmission control layer; wherein, the transmission control time period is shorter than the transmission prediction time period.

[0126] The transmission control module 360 ​​is used to control the transmission, engine, and motor controllers of the target hybrid vehicle through the transmission control layer based on the engine power command and the target gear.

[0127] This application embodiment uses a speed prediction layer to determine the current traffic complexity of the target hybrid vehicle based on the speed prediction time period and the current driving data of the target hybrid vehicle. The speed prediction time period is dynamically adjusted based on the current road data and current traffic data of the target hybrid vehicle. The speed prediction layer predicts the speed of the target hybrid vehicle based on the current driving data, current traffic complexity, current transmission data, and historical speed data, obtaining a predicted speed sequence for the target hybrid vehicle within the speed prediction time window. The speed prediction layer then determines the transmission adjustment parameter sequence of the target hybrid vehicle based on the predicted speed sequence and current traffic data, and sends the predicted speed sequence and transmission adjustment parameter sequence to the transmission prediction layer. The dynamic prediction layer, based on a preset transmission prediction time period, determines the predicted engine power sequence and predicted gear sequence of the target hybrid vehicle according to the predicted speed sequence, transmission adjustment parameter sequence, and current transmission data obtained in real time from the transmission control layer. The transmission prediction time period is less than or equal to the speed prediction time period. The transmission prediction layer, based on a preset transmission control time period, determines the engine power command and target gear according to the predicted engine power sequence and predicted gear sequence, and sends the engine power command and target gear to the transmission control layer. The transmission control time period is less than the transmission prediction time period. The transmission control layer controls the transmission, engine, and motor controllers of the target hybrid vehicle according to the engine power command and target gear. This technical solution, by performing hierarchical collaborative optimization of three control problems at different time scales—long-term ecological driving speed planning, mid-term energy management and gear decision-making, and engine and motor control—within a unified framework, breaks the old pattern of separation between speed and energy management in traditional methods, and helps improve the real-time performance and reliability of predictive control for hybrid vehicles.

[0128] Optionally, the speed prediction module 320 includes:

[0129] The model determination unit is used to determine the target speed prediction model of the target hybrid vehicle based on the correspondence between candidate traffic complexity and candidate speed prediction models through the speed prediction layer, according to the current traffic complexity; wherein, the candidate speed prediction models include a steady traffic flow prediction model and a dynamic traffic flow prediction model;

[0130] The speed prediction unit is used to predict the speed of the target hybrid vehicle based on the target speed prediction model through the speed prediction layer, according to the current driving data and the historical speed data of the target hybrid vehicle, and obtain the predicted speed sequence of the target hybrid vehicle within the speed prediction time window.

[0131] Optional, velocity prediction unit, specifically used for:

[0132] If the target speed prediction model includes both a steady traffic flow prediction model and a dynamic traffic flow prediction model, then the speed prediction layer determines the model weight ratio between the steady traffic flow prediction model and the dynamic traffic flow prediction model based on traffic complexity and a preset complexity threshold.

[0133] The speed prediction layer, based on a steady-state traffic flow prediction model, predicts the speed of the target hybrid vehicle using historical speed data, thus obtaining the first candidate speed sequence of the target hybrid vehicle within the speed prediction time window. The steady-state traffic flow prediction model is trained on an autoregressive integral moving average model based on the historical speed sequence of the target hybrid vehicle.

[0134] Based on the dynamic traffic flow prediction model, the speed prediction layer predicts the speed of the target hybrid vehicle according to the current driving data, and obtains the second candidate speed sequence of the target hybrid vehicle in the speed prediction time window; the dynamic traffic flow prediction model is trained on the hidden Markov model based on the historical driving data and historical speed sequence of the target hybrid vehicle.

[0135] The speed prediction layer uses the model weight ratio to perform a weighted summation of the first and second candidate speed sequences to obtain the predicted speed sequence of the target hybrid vehicle within the speed prediction time window.

[0136] Optionally, the speed prediction module 320 is also used for:

[0137] After obtaining the predicted speed sequence of the target hybrid vehicle within the speed prediction time window through the speed prediction layer, the predicted speed sequence is optimized based on the current fuel consumption data of the target hybrid vehicle, constrained by the vehicle dynamics model, to obtain the optimized predicted speed sequence; wherein, the vehicle dynamics model is predetermined based on the powertrain architecture of the target hybrid vehicle.

[0138] Optionally, the parameter determination module 330 is used for:

[0139] The speed prediction layer determines the motion state prediction sequence of the target hybrid vehicle based on the predicted speed sequence and current traffic data.

[0140] Based on the correspondence between candidate motion states and candidate transmission adjustment parameters, the speed prediction layer determines the transmission adjustment parameter sequence of the target hybrid vehicle according to the motion state prediction sequence.

[0141] Optional, the transmission data prediction module 340 is specifically used for:

[0142] Based on a preset transmission prediction time period, the transmission prediction layer employs a model predictive control algorithm, constrained by the hybrid power model of the target hybrid vehicle, and determines the predicted transmission data sequence of the target hybrid vehicle according to the predicted speed sequence and the current transmission data obtained in real time from the transmission control layer; wherein, the hybrid power model is predetermined based on the transmission system architecture of the target hybrid vehicle.

[0143] Based on the Pontryagin minimum principle, the transmission prediction layer determines the predicted engine power sequence and predicted gear sequence of the target hybrid vehicle according to the predicted transmission data sequence and the transmission adjustment parameter sequence.

[0144] The hybrid vehicle hierarchical predictive control device provided in this application embodiment can execute the hybrid vehicle hierarchical predictive control method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects for executing each hybrid vehicle hierarchical predictive control method.

[0145] According to embodiments of this application, this application also provides an electronic device, a readable storage medium, and a computer program product.

[0146] Example 4

[0147] Figure 4 This is a schematic diagram of the structure of an electronic device 410 implementing the hybrid vehicle hierarchical predictive control method according to embodiments of this application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present application described and / or claimed herein.

[0148] like Figure 4As shown, the electronic device 410 includes at least one processor 411 and a memory, such as a read-only memory (ROM) 412 or a random access memory (RAM) 413, communicatively connected to the at least one processor 411. The memory stores computer programs executable by the at least one processor. The processor 411 can perform various appropriate actions and processes based on the computer program stored in the ROM 412 or loaded from storage unit 418 into the RAM 413. The RAM 413 may also store various programs and data required for the operation of the electronic device 410. The processor 411, ROM 412, and RAM 413 are interconnected via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0149] Multiple components in electronic device 410 are connected to I / O interface 415, including: input unit 416, such as keyboard, mouse, etc.; output unit 417, such as various types of displays, speakers, etc.; storage unit 418, such as disk, optical disk, etc.; and communication unit 419, such as network card, modem, wireless transceiver, etc. Communication unit 419 allows electronic device 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0150] Processor 411 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 411 performs the various methods and processes described above, such as the hierarchical predictive control method for hybrid vehicles.

[0151] In some embodiments, the hybrid vehicle hierarchical predictive control method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 418. In some embodiments, part or all of the computer program may be loaded into and / or installed on electronic device 410 via ROM 412 and / or communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the hybrid vehicle hierarchical predictive control method described above may be performed. Alternatively, in other embodiments, processor 411 may be configured as the hybrid vehicle hierarchical predictive control method by any other suitable means (e.g., by means of firmware).

[0152] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0153] Computer programs used to implement the methods of this application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable hybrid vehicle hierarchical predictive control device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0154] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0155] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0156] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0157] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0158] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this application can be achieved, and this is not limited herein.

[0159] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A hierarchical predictive control method for hybrid vehicles, characterized in that, The method is applied to a vehicle hierarchical management system; the vehicle hierarchical management system includes a speed prediction layer, a transmission prediction layer, and a transmission control layer; the transmission prediction layer is communicatively connected to the speed prediction layer and the transmission control layer, respectively; the method includes: The speed prediction layer determines the current traffic complexity of the target hybrid vehicle based on the speed prediction time period and the current driving data of the target hybrid vehicle; wherein the speed prediction time period is dynamically adjusted based on the current road data and current traffic data of the target hybrid vehicle. The speed prediction layer predicts the speed of the target hybrid vehicle based on the current driving data, the current traffic complexity, and the historical speed data of the target hybrid vehicle, thereby obtaining the predicted speed sequence of the target hybrid vehicle in the speed prediction time window. The speed prediction layer determines the transmission adjustment parameter sequence of the target hybrid vehicle based on the predicted speed sequence and the current traffic data, and sends the predicted speed sequence and the transmission adjustment parameter sequence to the transmission prediction layer. Based on a preset transmission prediction time period, the transmission prediction layer determines the predicted engine power sequence and predicted gear sequence of the target hybrid vehicle according to the predicted speed sequence, the transmission adjustment parameter sequence, and the current transmission data obtained in real time from the transmission control layer; wherein the transmission prediction time period is less than or equal to the speed prediction time period. Based on a preset transmission control time period, the transmission prediction layer determines the engine power command and target gear according to the predicted engine power sequence and the predicted gear sequence, and sends the engine power command and the target gear to the transmission control layer; wherein, the transmission control time period is shorter than the transmission prediction time period; The transmission control layer controls the gearbox, engine, and motor controller of the target hybrid vehicle according to the engine power command and the target gear.

2. The method according to claim 1, characterized in that, The step of using the speed prediction layer to predict the speed of the target hybrid vehicle based on the current driving data, the current traffic complexity, and the historical speed data of the target hybrid vehicle, to obtain the predicted speed sequence of the target hybrid vehicle within the speed prediction time window, includes: Based on the correspondence between candidate traffic complexity and candidate speed prediction models, the speed prediction layer determines the target speed prediction model for the target hybrid vehicle according to the current traffic complexity; wherein, the candidate speed prediction model includes a steady traffic flow prediction model and a dynamic traffic flow prediction model. Based on the target speed prediction model, the speed prediction layer predicts the speed of the target hybrid vehicle according to the current driving data and the historical speed data of the target hybrid vehicle, thereby obtaining the predicted speed sequence of the target hybrid vehicle in the speed prediction time window.

3. The method according to claim 2, characterized in that, The step of using the speed prediction layer based on the target speed prediction model, according to the current driving data and the historical speed data of the target hybrid vehicle, to predict the speed of the target hybrid vehicle and obtain the predicted speed sequence of the target hybrid vehicle in the speed prediction time window includes: If the target speed prediction model includes both the steady traffic flow prediction model and the dynamic traffic flow prediction model, then the speed prediction layer determines the model weight ratio between the steady traffic flow prediction model and the dynamic traffic flow prediction model based on the traffic complexity and a preset complexity division threshold. Based on the steady traffic flow prediction model, the speed prediction layer predicts the speed of the target hybrid vehicle according to its historical speed data, thereby obtaining the first candidate speed sequence of the target hybrid vehicle within the speed prediction time window; wherein, the steady traffic flow prediction model is trained on an autoregressive integral moving average model based on the historical speed sequence of the target hybrid vehicle. Based on the dynamic traffic flow prediction model, the speed prediction layer predicts the speed of the target hybrid vehicle according to the current driving data, thereby obtaining a second candidate speed sequence of the target hybrid vehicle in the speed prediction time window; wherein, the dynamic traffic flow prediction model is trained on a hidden Markov model based on the historical driving data and historical speed sequence of the target hybrid vehicle. The speed prediction layer calculates a weighted sum of the first candidate speed sequence and the second candidate speed sequence based on the model weight ratio to obtain the predicted speed sequence of the target hybrid vehicle within the speed prediction time window.

4. The method according to claim 1, characterized in that, After obtaining the predicted speed sequence of the target hybrid vehicle within the speed prediction time window through the speed prediction layer, the method further includes: The speed prediction layer, constrained by the vehicle dynamics model, optimizes the predicted speed sequence based on the current fuel consumption data of the target hybrid vehicle to obtain an optimized predicted speed sequence; wherein, the vehicle dynamics model is predetermined based on the powertrain architecture of the target hybrid vehicle.

5. The method according to claim 1, characterized in that, The speed prediction layer determines the transmission adjustment parameter sequence of the target hybrid vehicle based on the predicted speed sequence and the current traffic data, including: The speed prediction layer determines the motion state prediction sequence of the target hybrid vehicle based on the predicted speed sequence and the current traffic data. Based on the correspondence between candidate motion states and candidate transmission adjustment parameters, the speed prediction layer determines the transmission adjustment parameter sequence of the target hybrid vehicle according to the motion state prediction sequence.

6. The method according to claim 1, characterized in that, Based on a preset transmission prediction time period, the transmission prediction layer determines the predicted engine power sequence and predicted gear sequence of the target hybrid vehicle according to the predicted speed sequence, the transmission adjustment parameter sequence, and the current transmission data obtained in real time from the transmission control layer, including: Based on a preset transmission prediction time period, the transmission prediction layer employs a model predictive control algorithm, constrained by the hybrid power model of the target hybrid vehicle, and determines the predicted transmission data sequence of the target hybrid vehicle according to the predicted speed sequence and the current transmission data obtained in real time from the transmission control layer; wherein, the hybrid power model is predetermined based on the transmission system architecture of the target hybrid vehicle. Based on the Pontryagin minimum principle, the transmission prediction layer determines the predicted engine power sequence and predicted gear sequence of the target hybrid vehicle according to the predicted transmission data sequence and the transmission adjustment parameter sequence.

7. A stratified predictive control device for hybrid vehicles, characterized in that, Configured in a vehicle hierarchical management system; the vehicle hierarchical management system includes a speed prediction layer, a transmission prediction layer, and a transmission control layer; the transmission prediction layer is communicatively connected to the speed prediction layer and the transmission control layer, respectively; the device includes: The traffic assessment module is used to determine the current traffic complexity of the target hybrid vehicle based on the speed prediction time period and the current driving data of the target hybrid vehicle through the speed prediction layer; wherein, the speed prediction time period is dynamically adjusted according to the current road data and current traffic data of the target hybrid vehicle. The speed prediction module is used to predict the speed of the target hybrid vehicle through the speed prediction layer based on the current driving data, the current traffic complexity and the historical speed data of the target hybrid vehicle, so as to obtain the predicted speed sequence of the target hybrid vehicle in the speed prediction time window. The adjustment parameter determination module is used to determine the transmission adjustment parameter sequence of the target hybrid vehicle through the speed prediction layer based on the predicted speed sequence and the current traffic data, and send the predicted speed sequence and the transmission adjustment parameter sequence to the transmission prediction layer; The transmission data prediction module is used to determine the predicted engine power sequence and predicted gear sequence of the target hybrid vehicle based on the predicted speed sequence, the transmission adjustment parameter sequence, and the current transmission data obtained in real time from the transmission control layer, using the transmission prediction layer based on a preset transmission prediction time period; wherein the transmission prediction time period is less than or equal to the speed prediction time period. The instruction generation module is used to determine the engine power instruction and the target gear based on the predicted engine power sequence and the predicted gear sequence through the transmission prediction layer based on a preset transmission control time period, and send the engine power instruction and the target gear to the transmission control layer; wherein the transmission control time period is shorter than the transmission prediction time period; The transmission control module is used to control the transmission, engine, and motor controller of the target hybrid vehicle through the transmission control layer according to the engine power command and the target gear.

8. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the hybrid vehicle hierarchical predictive control method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the hierarchical predictive control method for hybrid vehicles as described in any one of claims 1-6.

10. A computer program product comprising a computer program that, when executed by a processor, implements the hybrid vehicle hierarchical predictive control method according to any one of claims 1-6.

Images