Energy control method and system for a hybrid vehicle

Abstract

The application discloses an energy control method and system for a hybrid vehicle, wherein the method obtains a trained vehicle speed prediction model and a preset torque control rule, and obtains driving speed data and residual power data of a target vehicle; the driving speed data is input into the trained vehicle speed prediction model for vehicle speed prediction, so that predicted vehicle speed data is obtained; driving working modes of the target vehicle are obtained according to driving demand torque of the residual power data and the driving speed data; and energy control is performed on the target vehicle according to the driving working modes. The method can effectively reduce the required computing resources for energy control of the hybrid vehicle, and improve the efficiency and effect of energy control. The application relates to the technical field of vehicles.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicles, and particularly relates to an energy control method and system of a hybrid vehicle. BACKGROUND

[0002] The hybrid vehicle refers to a vehicle capable of driving under the cooperation of an electric motor and an engine. Optimal energy control of the hybrid vehicle under various driving conditions is one of the important contents of industry concern.

[0003] At present, the existing technology usually realizes energy control of the hybrid vehicle in the mode of model predictive control (MPC). Specifically, the model predicts the vehicle speed in a certain time range in the future to realize energy control of the hybrid vehicle. The mode requires more computing resources and has large computing load, and the efficiency and effect of energy control are not satisfactory.

[0004] Therefore, the problems of the existing technology still need to be solved and optimized. SUMMARY

[0005] The present application aims to at least partly solve one of the problems in the related art.

[0006] To this end, one purpose of the embodiments of the present application is to provide an energy control method and system of a hybrid vehicle, wherein the method can effectively reduce the computing resources required for energy control of the hybrid vehicle and improve the efficiency and effect of energy control.

[0007] In order to achieve the above technical purpose, the technical solutions adopted by the embodiments of the present application include:

[0008] In a first aspect, the embodiments of the present application provide an energy control method of a hybrid vehicle, comprising:

[0009] obtaining a trained vehicle speed prediction model and a preset torque control rule, and driving speed data and residual power data of a target vehicle;

[0010] inputting the driving speed data into the trained vehicle speed prediction model for vehicle speed prediction to obtain predicted speed data;

[0011] obtaining a driving working mode of the target vehicle according to the driving demand torque of the residual power data and the driving speed data, the driving working mode including a regular working mode and an irregular working mode;

[0012] If the driving working mode is the regular working mode, the target vehicle is controlled according to the torque control rule; or if the driving working mode is the irregular working mode, the target vehicle speed demand torque is allocated according to the driving speed data and the residual power data, to obtain an engine torque control sequence and a motor torque control sequence, and the target vehicle is jointly controlled according to the engine torque control sequence and the motor torque control sequence.

[0013] In addition, the method according to the above-mentioned embodiments of the present application can further have the following additional technical features:

[0014] Further, in an embodiment of the present application, the driving working mode of the target vehicle is obtained according to the driving demand torque and the residual power data, comprising:

[0015] obtaining a minimum power threshold, a maximum power threshold, a starting torque threshold and an optimal torque threshold;

[0016] comparing the residual power data according to the minimum power threshold and the maximum power threshold, to obtain a power comparison result;

[0017] comparing the driving demand torque according to the starting torque threshold and the optimal torque threshold, to obtain a torque comparison result;

[0018] obtaining the driving working mode of the target vehicle according to the power comparison result and the torque comparison result.

[0019] Further, in an embodiment of the present application, the target vehicle speed demand torque is allocated according to the driving speed data and the residual power data, to obtain an engine torque control sequence and a motor torque control sequence, comprising:

[0020] obtaining a vehicle engine torque and a vehicle motor torque of the target vehicle, and an input shaft speed corresponding to the driving speed data and a power equivalent factor corresponding to the residual power data;

[0021] constructing a torque constraint problem according to the power equivalent factor, the input shaft speed, the target vehicle speed demand torque, the vehicle engine torque and the vehicle motor torque;

[0022] constraint solving the torque constraint problem, to obtain the engine torque control sequence and the motor torque control sequence.

[0023] Further, in an embodiment of the present application, the constraint solving of the torque constraint problem to obtain the engine torque control sequence and the motor torque control sequence comprises:

[0024] obtaining a target torque function and a torque constraint condition of the torque constraint problem;

[0025] constructing a first quadratic programming sub-problem corresponding to the torque constraint problem according to the target torque function and the torque constraint condition;

[0026] performing sub-problem optimization on the first quadratic programming sub-problem to obtain the engine torque control sequence and the motor torque control sequence.

[0027] Further, in an embodiment of the present application, the constraint solving of the torque constraint problem to obtain the engine torque control sequence and the motor torque control sequence comprises:

[0028] obtaining a preset optimization precision condition;

[0029] obtaining a first control sequence, a first optimization point and a first quadratic programming sub-problem corresponding to the first optimization point;

[0030] performing gradient analysis on the target torque function according to the first optimization point to obtain a target torque gradient, and performing constraint condition analysis on the torque constraint condition according to the first optimization point to obtain a torque constraint matrix;

[0031] performing sub-problem solving on the first quadratic programming sub-problem according to the target torque gradient and the torque constraint matrix to obtain a target optimal solution;

[0032] optimizing and updating the first optimization point according to the target optimal solution to obtain a second optimization point;

[0033] performing first condition verification on the optimization precision condition according to the first optimization point and the second optimization point to obtain a first condition verification result;

[0034] if the first condition verification result is that the optimization precision condition is satisfied, updating the first control sequence according to the target optimal solution to obtain a second control sequence, and obtaining the engine torque control sequence and the motor torque control sequence according to the second control sequence; or, if the first condition verification result is that the optimization precision condition is not satisfied, updating the first control sequence according to the target optimal solution, and updating the first optimization point according to the second optimization point, and then returning to the step of obtaining the first control sequence, the first optimization point and the first quadratic programming sub-problem corresponding to the first optimization point.

[0035] Further, in an embodiment of the present application, the sub-problem solving of the first quadratic programming sub-problem according to the target torque gradient and the torque constraint matrix to obtain the target optimal solution comprises:

[0036] conditionally solving the first quadratic programming sub-problem according to the target torque gradient and the torque constraint matrix to obtain an intermediate optimal solution;

[0037] correcting the intermediate optimal solution to obtain the target optimal solution.

[0038] Further, in an embodiment of the present application, the conditionally solving the first quadratic programming sub-problem according to the target torque gradient and the torque constraint matrix to obtain an intermediate optimal solution comprises:

[0039] problem solution verification of the first quadratic programming sub-problem according to the target torque gradient and the torque constraint matrix to obtain a problem solution verification result, the problem solution verification result being used to represent whether the first quadratic programming sub-problem has a problem solution;

[0040] if the problem solution verification result is that the first quadratic programming sub-problem has a problem solution, then performing original solving of the first quadratic programming sub-problem according to the target torque gradient and the torque constraint matrix to obtain the intermediate optimal solution; or, if the problem solution verification result is that the first quadratic programming sub-problem has a problem solution, then obtaining a second quadratic programming sub-problem corresponding to the first quadratic programming sub-problem, and performing replacement solving of the second quadratic programming sub-problem according to the target torque gradient and the torque constraint matrix to obtain the intermediate optimal solution.

[0041] Further, in an embodiment of the present application, the correcting the intermediate optimal solution to obtain the target optimal solution comprises:

[0042] obtaining a preset effect condition;

[0043] performing second condition verification of the effect condition according to the intermediate optimal solution to obtain a second condition verification result;

[0044] if the second condition verification result is that the effect condition is satisfied, then performing search direction correction of the intermediate optimal solution to obtain the target optimal solution; or, if the second condition verification result is that the effect condition is not satisfied, then determining the intermediate optimal solution as the target optimal solution.

[0045] Further, in an embodiment of the present application, the updating the first optimization point according to the target optimal solution to obtain a second optimization point comprises:

[0046] obtaining a penalty factor corresponding to the target optimal solution and a benefit function corresponding to the target optimal solution;

[0047] solving the benefit function according to the penalty factor to obtain a benefit step corresponding to the target optimal solution;

[0048] updating the first optimization point according to the benefit step and the target optimal solution to obtain the second optimization point.

[0049] In a second aspect, an embodiment of the present application provides an energy control system of a hybrid vehicle, comprising:

[0050] a first processing unit configured to obtain a trained vehicle speed prediction model and a preset torque control rule, and obtain driving speed data and residual power data of a target vehicle;

[0051] a second processing unit configured to input the driving speed data into the trained vehicle speed prediction model to perform vehicle speed prediction and obtain predicted driving speed data;

[0052] a third processing unit configured to obtain a driving working mode of the target vehicle according to driving demand torque of the residual power data and the driving speed data, the driving working mode comprising a regular working mode and an irregular working mode;

[0053] a fourth processing unit configured to perform energy control on the target vehicle according to the torque control rule if the driving working mode is the regular working mode, or perform torque distribution on the target vehicle demand torque according to the driving speed data and the residual power data if the driving working mode is the irregular working mode, to obtain an engine torque control sequence and a motor torque control sequence, and perform energy joint control on the target vehicle according to the engine torque control sequence and the motor torque control sequence.

[0054] In a third aspect, an embodiment of the present application further provides an electronic device, comprising:

[0055] at least one processor;

[0056] at least one memory configured to store at least one program;

[0057] when the at least one program is executed by the at least one processor, the at least one processor is caused to implement the method in the first aspect.

[0058] In a fourth aspect, the embodiments of the present application further provide a computer readable storage medium, which stores a processor executable program. The processor executable program, when executed by a processor, is configured to implement the method of the first aspect.

[0059] The advantages and beneficial effects of the present application will be partially given in the following description, partially will become obvious from the following description, or will be learned by the practice of the present application:

[0060] The energy control method and system of the hybrid vehicle disclosed by the embodiments of the present application, wherein the method obtains a trained vehicle speed prediction model and a preset torque control rule, and driving speed data and residual power data of a target vehicle; the driving speed data is input into the trained vehicle speed prediction model for vehicle speed prediction to obtain predicted driving speed data; according to the driving demand torque of the residual power data and the driving speed data, the driving working mode of the target vehicle is obtained, and the driving working mode includes a regular working mode and an irregular working mode; if the driving working mode is the regular working mode, the energy control of the target vehicle is performed according to the torque control rule; or, if the driving working mode is the irregular working mode, the torque distribution of the target speed demand torque is performed according to the driving speed data and the residual power data, to obtain an engine torque control sequence and a motor torque control sequence, and the energy joint control of the target vehicle is performed according to the engine torque control sequence and the motor torque control sequence. The method predicts the predicted driving speed data of the target vehicle in the future based on the vehicle speed prediction model to determine the target speed demand torque, and then determines the driving working mode of the target vehicle based on the residual power data and the target speed demand torque, and performs energy control based on the driving working mode, which can effectively reduce the calculation resources required for energy control of the hybrid vehicle and improve the efficiency and effect of energy control. BRIEF DESCRIPTION OF DRAWINGS

[0061] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the following introduces the drawings of the related technical solutions in the embodiments of the present application or the prior art. It should be understood that the drawings in the following introduction are only for the convenience of expressing part of the embodiments of the technical solutions of the present application, and for those skilled in the art, other drawings can be obtained without creative labor on the premise of the drawings.

[0062] Figure 1 A flowchart of the energy control method of the hybrid vehicle provided by the embodiments of the present application is shown in the figure;

[0063] Figure 2 A frame diagram of the energy control system of the hybrid vehicle provided by the embodiments of the present application is shown in the figure;

[0064] Figure 3 A structural schematic diagram of an electronic device is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0065] Embodiments of the present application are described in detail below with reference to examples shown in the attached drawings, wherein the same or similar reference numerals represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and are only used to explain the present application and cannot be understood as a limitation of the present application. For the step numbers in the following embodiments, they are only set for the convenience of explanation and description, and the order between the steps is not limited in any way, and the execution order of each step in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0066] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0067] At present, the existing technology usually realizes the energy control of the hybrid vehicle in the mode of model predictive control (MPC), which specifically realizes the energy control of the hybrid vehicle by predicting the vehicle speed in a certain time range in the future. However, since this mode usually controls the energy of all driving conditions of the target vehicle, the control performance of MPC is more dependent on the solving efficiency of the solver, the required computing resources of this mode are more, the computing load is larger, the timeliness of energy control is not good, and the efficiency is not satisfactory. In addition, the control performance of MPC also depends on the predicted vehicle speed provided by the model, and in the complex driving conditions of the target vehicle, the accuracy of the predicted vehicle speed provided by this mode is not good, and the effect of energy control is not satisfactory.

[0068] Therefore, the embodiment of the present application provides an energy control method and system for a hybrid vehicle, wherein the method predicts target vehicle speed demand torque based on a vehicle speed prediction model, then determines the driving working mode of the target vehicle based on residual power data and the target vehicle speed demand torque, and performs energy control based on the driving working mode, specifically, uses torque control rules to perform energy control on the target vehicle in a regular working mode, and uses engine torque control sequences and motor torque control sequences to perform energy control on the target vehicle in a non-regular working mode, which can effectively reduce the calculation resources required for energy control of the target vehicle, reduce calculation compliance, improve the timeliness of energy control, and thus improve the energy control efficiency; in addition, the method performs torque distribution on the target vehicle speed demand torque based on driving speed data and residual power data, specifically, solves the torque constraint problem corresponding to the target vehicle speed demand torque by constraint, which can reduce the dependence on the predicted speed provided by the model while ensuring energy control of the target vehicle, and improve the energy control effect of the target vehicle in complex driving conditions.

[0069] Reference Figure 1 In the embodiment of the present application, an energy control method for a hybrid vehicle comprises:

[0070] Step 110, obtaining a trained vehicle speed prediction model and a preset torque control rule, and driving speed data and residual power data of a target vehicle;

[0071] In the embodiment of the present application, the target vehicle can be a hybrid vehicle; the vehicle speed prediction model can be a long short-term memory neural network (LSTM) model, and the trained vehicle speed prediction model can be obtained by collecting historical vehicle speed data set of the target vehicle; then, the vehicle speed data of the target vehicle in a historical period is extracted and a sliding window is formed, and the sliding window and the predicted speed are input into the model for training, so as to obtain the trained vehicle speed prediction model.

[0072] It can be understood that the torque control rule is used to realize energy control of the target vehicle in a regular working mode, and the torque control includes no torque output, only motor output positive torque, only engine output positive torque, only motor output negative torque, etc. The driving speed data of the target vehicle can be the vehicle speed data of the target vehicle at the current time; the residual power data can be the SOC (State of Charge) value of the power battery of the target vehicle.

[0073] Step 120, inputting the driving speed data into the trained vehicle speed prediction model for vehicle speed prediction to obtain predicted speed data;

[0074] In the embodiment of the present application, the driving vehicle data of the target vehicle can be input into the trained vehicle speed prediction model, and the driving speed data is predicted by the trained vehicle speed prediction model to obtain the predicted vehicle speed data of the target vehicle in the future. The predicted vehicle speed data can be the vehicle speed data of the target vehicle at a certain time in the future, or the vehicle speed data of the target vehicle within a certain period in the future.

[0075] It can be understood that after obtaining the predicted vehicle speed data of the target vehicle in the future, the corresponding target speed demand torque can be calculated based on the predicted vehicle speed data. The target speed demand torque can be represented as:

[0076] T dem =r·(mgfcosα+0.5A f C d ρ air v 2 +ma+mg sinα) / i t

[0077] Wherein, T dem is the target speed demand torque; r is the tire radius of the target vehicle; m is the total vehicle mass of the target vehicle; g is the acceleration of gravity; f is the rolling resistance coefficient; a is the road slope angle; A f is the target vehicle's frontal area; C d is the air resistance coefficient; p air is the air density; v represents the vehicle speed; a is the longitudinal acceleration of the target vehicle; i t is the transmission ratio of the target vehicle.

[0078] Step 130, obtaining the driving working mode of the target vehicle according to the driving demand torque of the remaining power data and the driving speed data, the driving working mode including regular working mode and irregular working mode;

[0079] In the embodiment of the present application, the driving demand torque is the current demand torque of the target vehicle, and step 130 can obtain the driving working mode of the target vehicle based on the remaining power data of the target vehicle and the driving demand torque corresponding to the driving speed data. The driving working mode includes regular working mode and irregular working mode. The regular working mode includes idle parking mode, pure motor drive mode, pure engine drive mode and regenerative braking mode. The irregular working mode includes driving charging mode and hybrid drive mode.

[0080] In some embodiments, the step 130, obtaining the driving working mode of the target vehicle according to the driving demand torque of the remaining power data and the driving speed data, includes:

[0081] A1, obtaining a minimum power threshold, a maximum power threshold, a start torque threshold and an optimal torque threshold;

[0082] A2, performing a power comparison on the residual power data according to the minimum power threshold and the maximum power threshold, to obtain a power comparison result;

[0083] A3, performing a torque comparison on the driving demand torque according to the start torque threshold and the optimal torque threshold, to obtain a torque comparison result;

[0084] A4, obtaining a driving working mode of the target vehicle according to the power comparison result and the torque comparison result.

[0085] In the embodiments of the present application, the start torque threshold can be an engine start torque of an engine of the target vehicle at a specific engine speed, and the optimal torque threshold can be an engine optimal torque of the engine of the target vehicle at the specific engine speed, wherein the start torque threshold and the optimal torque threshold change with the change of the engine speed, and the optimal torque threshold is greater than the start torque threshold. Specifically, for a certain engine speed, firstly, a size relationship between the minimum power threshold and the residual power data can be compared to obtain the power comparison result; then, a size relationship between the peak torque threshold and the driving demand torque, and a size relationship between the optimal torque threshold and the driving demand torque can be compared to obtain the torque comparison result.

[0086] It can be understood that, if the power comparison result is that the residual power data is greater than or equal to the minimum power threshold and the torque comparison result is that the driving demand torque is greater than or equal to the optimal torque threshold, the driving working mode of the target vehicle is the hybrid drive mode in the irregular working mode; or, if the power comparison result is that the residual power data is less than the minimum power threshold and the torque comparison result is that the driving demand torque is greater than or equal to the optimal torque threshold, the driving working mode of the target vehicle is the pure engine drive mode in the regular working mode.

[0087] If the power comparison result is that the residual power data is less than the maximum power threshold, the torque comparison result is that the driving demand torque is greater than or equal to the start torque threshold, and the driving demand torque is less than the optimal torque threshold, the driving working mode of the target vehicle is the driving charging mode in the irregular working mode; or, if the power comparison result is that the residual power data is greater than or equal to the maximum power threshold, the torque comparison result is that the driving demand torque is greater than or equal to the start torque threshold, and the driving demand torque is less than the optimal torque threshold, the driving working mode of the target vehicle is the pure motor drive mode in the regular working mode.

[0088] If the comparison result of the electric quantity is that the residual electric quantity data is greater than or equal to the minimum electric quantity threshold value, and the comparison result of the torque is that the driving demand torque is less than the starting torque threshold value, the driving working mode of the target vehicle is the pure motor driving mode in the regular working mode; or, if the comparison result of the electric quantity is that the residual electric quantity data is less than the minimum electric quantity threshold value, and the comparison result of the torque is that the driving demand torque is less than the starting torque threshold value, the driving working mode of the target vehicle is the pure engine driving mode in the regular working mode.

[0089] In step 140, if the driving working mode is the regular working mode, the energy control is performed on the target vehicle according to the torque control rule.

[0090] In the embodiment of the present application, step 140 can be to perform the energy control on the target vehicle based on the torque control rule corresponding to the regular working mode. Specifically, if the regular working mode is the idle stop mode, the energy control on the target vehicle can be that the engine and the motor do not output torque; or, if the regular working mode is the pure motor driving mode, the energy control on the target vehicle can be based on that only the motor outputs positive torque; or, if the regular working mode is the pure engine driving mode, the energy control on the target vehicle can be based on that only the engine outputs positive torque; or, if the regular working mode is the regenerative braking mode, the energy control on the target vehicle can be based on that only the motor outputs negative torque.

[0091] Alternatively, in step 150, if the driving working mode is the irregular working mode, the target speed demand torque is torque distributed according to the driving speed data and the residual electric quantity data, to obtain an engine torque control sequence and a motor torque control sequence, and the energy joint control is performed on the target vehicle according to the engine torque control sequence and the motor torque control sequence.

[0092] In the embodiment of the present application, if the driving working mode is the irregular working mode, the target speed demand torque can be torque distributed according to the driving speed data and the residual electric quantity data based on the principle of minimum equivalent fuel consumption, to obtain the engine torque control sequence corresponding to the engine and the motor torque control sequence corresponding to the motor, so that the engine performs the energy control on the target vehicle based on the engine torque control sequence, and the motor performs the energy control on the target vehicle based on the motor torque control sequence.

[0093] In some embodiments, step 150 of torque distributing the target speed demand torque according to the driving speed data and the residual electric quantity data to obtain the engine torque control sequence and the motor torque control sequence comprises:

[0094] B1, obtaining a vehicle engine torque and a vehicle motor torque of the target vehicle, and an input shaft speed corresponding to the driving speed data and an electric quantity equivalent factor corresponding to the residual electric quantity data;

[0095] B2, constructing a torque constraint problem according to the electric quantity equivalent factor, the input shaft speed, the target speed demand torque, the vehicle engine torque and the vehicle motor torque;

[0096] In the embodiment of the present application, the vehicle engine torque can be the current engine torque of the target vehicle, the vehicle motor torque is the current motor torque of the target vehicle, the input shaft speed is the speed of the input shaft of the gearbox converted from the driving speed data of the target vehicle, and the electric quantity equivalent factor is a dimensionless value corresponding to the residual electric quantity data, and the function form of the electric quantity equivalent factor can be represented as:

[0097]

[0098] Wherein, s(SOC) is the function form of the electric quantity equivalent factor, and SOC is the residual electric quantity data.

[0099] It can be understood that step B2 can be based on the principle of minimum equivalent fuel consumption, and the torque constraint problem is constructed according to the electric quantity equivalent factor, the input shaft speed, the target speed demand data, the vehicle engine torque and the vehicle motor torque.

[0100] B3, constraint solving the torque constraint problem to obtain the engine torque control sequence and the motor torque control sequence.

[0101] Further, the step B3, constraint solving the torque constraint problem to obtain the engine torque control sequence and the motor torque control sequence, comprises:

[0102] B31, obtaining a target torque function and a torque constraint condition of the torque constraint problem;

[0103] B32, constructing a first quadratic programming sub-problem corresponding to the torque constraint problem according to the target torque function and the torque constraint condition;

[0104] In the embodiment of the present application, if the driving working mode is the driving charging mode in the irregular working mode, the target torque function can be represented as:

[0105]

[0106] Wherein, f(x) is the target torque function, min() is the minimum function, f fuek(x1, ω) is a function of fuel consumption with respect to engine torque x1 and input shaft speed x1; s is an electric quantity equivalent factor; x1 is engine torque; ω is input shaft speed; x2 is motor torque; Q L is low heat value of diesel; f eff (x2, ω) is a function of motor efficiency with respect to motor torque x2 and input shaft speed ω.

[0107] The corresponding torque constraint condition can be expressed as:

[0108]

[0109] wherein, T e_min (ω) is minimum engine torque value at input shaft speed ω; T e_max (ω) is maximum engine torque value at input shaft speed ω; T m_max (ω) is maximum motor torque value at input shaft speed ω; T req (ω) is target vehicle speed demand torque.

[0110] It can be understood that if the driving working mode is the hybrid driving mode in the irregular working mode, the corresponding target torque function and torque constraint condition can be expressed as:

[0111]

[0112] It should be noted that step B32 can be based on SQP (Sequential Quadratic Programming) algorithm, and the torque constraint problem of nonlinear programming is approximated by quadratic programming at a series of optimization points to obtain a first quadratic programming sub-problem. Specifically, for the kth optimization point, the corresponding first quadratic programming sub-problem can be expressed as:

[0113]

[0114] wherein, x k is the kth optimization point, x k+1 is the k+1th optimization point; B k is the Quasi-Newton matrix of the kth optimization point; δ x is the variable change from the kth optimization point to the k+1th optimization point; is the transpose vector of δ x ; g(x k ) is the target torque gradient of the kth optimization point; C E (x k ) is the equality constraint function of the kth optimization point; J E (x k) is the Jacobian matrix of the equality constraint function C E (x k ) is the Jacobian matrix of the inequality constraint function C I (x k ) is the inequality constraint function of the kth optimization point; J I (x k ) is the Jacobian matrix of the inequality constraint function C I (x k ) is the Jacobian matrix of the inequality constraint function C

[0115] B33, performing sub-problem optimization on the first quadratic programming sub-problem to obtain the engine torque control sequence and the motor torque control sequence.

[0116] Further, the step B33, performing sub-problem optimization on the first quadratic programming sub-problem to obtain the engine torque control sequence and the motor torque control sequence, comprises:

[0117] B331, obtaining a preset optimization precision condition;

[0118] B332, obtaining a first control sequence, a first optimization point, and a first quadratic programming sub-problem corresponding to the first optimization point;

[0119] B333, performing gradient analysis on the target torque function according to the first optimization point to obtain a target torque gradient, and performing constraint condition analysis on the torque constraint condition according to the first optimization point to obtain a torque constraint matrix;

[0120] In the embodiments of the present application, the target optimal solution of the first quadratic programming sub-problem at a plurality of optimization points can be obtained through a cyclic iteration manner, and then the engine torque control sequence and the motor torque control sequence are determined based on all the obtained target optimal solutions. In addition, the optimization precision condition can be a preset precision requirement, and the specific value thereof can be set according to actual conditions; the first control sequence is a sequence set of the target optimal solution corresponding to the previous optimization point; and the first optimization point can be an optimization point of the first quadratic programming sub-problem in the current cyclic iteration round.

[0121] It can be understood that the gradient analysis in step B333 can be to calculate the gradient of the target torque function to obtain the target torque gradient, and there are various specific calculation methods of the gradient, which will not be described herein. In addition, step B333 can first obtain the inequality constraint function and the equality constraint function corresponding to the torque constraint condition at the first optimization point; and then determine the Jacobian matrix corresponding to the inequality constraint function of the first optimization point and the Jacobian matrix corresponding to the equality constraint function of the first optimization point, and determine the two obtained Jacobian matrices as the torque constraint matrix.

[0122] B334、solving the first quadratic programming sub-problem according to the target torque gradient and the torque constraint matrix to obtain a target optimal solution;

[0123] Further, the step B334 of solving the first quadratic programming sub-problem according to the target torque gradient and the torque constraint matrix to obtain a target optimal solution comprises:

[0124] B3341, conditionally solving the first quadratic programming sub-problem according to the target torque gradient and the torque constraint matrix to obtain an intermediate optimal solution;

[0125] Further, the step B3341 of conditionally solving the first quadratic programming sub-problem according to the target torque gradient and the torque constraint matrix to obtain an intermediate optimal solution comprises:

[0126] B33411, problem solution verification is performed on the first quadratic programming sub-problem according to the target torque gradient and the torque constraint matrix to obtain a problem solution verification result, the problem solution verification result being used to represent whether the first quadratic programming sub-problem has a problem solution;

[0127] B33412, if the problem solution verification result is that the first quadratic programming sub-problem has a problem solution, then original solving is performed on the first quadratic programming sub-problem according to the target torque gradient and the torque constraint matrix to obtain the intermediate optimal solution;

[0128] Alternatively, B33413, if the problem solution verification result is that the first quadratic programming sub-problem has a problem solution, then a second quadratic programming sub-problem corresponding to the first quadratic programming sub-problem is obtained, and replacement solving is performed on the second quadratic programming sub-problem according to the target torque gradient and the torque constraint matrix to obtain the intermediate optimal solution.

[0129] In the embodiments of the present application, for the first quadratic programming sub-problem corresponding to the first optimization point, firstly, the first quadratic programming sub-problem corresponding to the first optimization point can be attempted to be solved to determine whether the first quadratic programming sub-problem has a problem solution, and a problem solution verification result is obtained. Specifically, if the problem solution verification result is that the first quadratic programming sub-problem of the first optimization point has a problem solution, then the intermediate optimal solution corresponding to the first optimization point can be directly determined based on the target torque gradient and the torque constraint matrix, and the intermediate optimal solution is used to represent the initial update direction of the first optimization point; or, if the problem solution verification result is that the first quadratic programming sub-problem of the first optimization point has no problem solution, then a second quadratic programming sub-problem corresponding to the first quadratic programming sub-problem can be obtained, and the second quadratic programming sub-problem is solved through the target torque gradient and the torque constraint matrix, so as to obtain the intermediate optimal solution.

[0130] Exemplarily, the embodiment of the present application takes the first optimization point as the kth optimization point as an example, and the second quadratic programming sub-problem can be expressed as:

[0131]

[0132] wherein, is an equal constraint penalty factor; is an unequal constraint penalty factor; m1 is the total number of equal constraints; m2 is the total number of unequal constraints; ξ, ζ and β are artificial variables; ξ i is the ith artificial variable ξ; ζ i is the ith artificial variable ζ; is the i-m1 artificial variable β.

[0133] B3342, performing optimal solution correction on the intermediate optimal solution to obtain the target optimal solution.

[0134] Further, the step B3342, performing optimal solution correction on the intermediate optimal solution to obtain the target optimal solution, comprises:

[0135] B33421, obtaining a preset effect condition;

[0136] B33422, performing second condition verification on the effect condition according to the intermediate optimal solution to obtain a second condition verification result;

[0137] B33423, if the second condition verification result is that the effect condition is satisfied, performing search direction correction on the intermediate optimal solution to obtain the target optimal solution;

[0138] Alternatively, B33424, if the second condition verification result is that the effect condition is not satisfied, determining the intermediate optimal solution as the target optimal solution.

[0139] In the embodiment of the present application, the effect condition can be a verification condition of Maratos effect in the SQP algorithm; the second condition verification can first obtain an optimal solution update vector corresponding to the intermediate optimal solution, and then judge whether the optimal solution update vector satisfies the effect condition, if the optimal solution update vector satisfies the effect condition, a second condition verification result representing that the effect condition is satisfied is obtained, and at this time, the intermediate optimal solution can be corrected in the second order based on the second-order correction method to obtain the target optimal solution; or, if the optimal solution update vector does not satisfy the effect condition, a second condition verification result representing that the effect condition is not satisfied is obtained, and at this time, the intermediate optimal solution can be directly determined as the target optimal solution.

[0140] For example, for the intermediate optimal solution corresponding to the k-th optimization point, its optimal solution update vector can be represented as:

[0141]

[0142] in, Update the vector for the optimal solution corresponding to the k-th optimization point; c i (x k ) represents the value of the i-th constraint function at the k-th optimization point, where the i-th constraint function is a subfunction of either the equality constraint function or the inequality constraint function; d k This is the intermediate optimal solution corresponding to the k-th optimization point;

[0143] The effect condition can be expressed as:

[0144]

[0145] Among them, A k c represents the index of all constraint functions that satisfy constraint ε at the k-th optimization point; i (x k +d k Let be the i-th constraint function at the optimization point x. k +d k The value at that location.

[0146] B335. Based on the target optimal solution, the first optimization point is optimized and updated to obtain the second optimization point;

[0147] Further, step B335, optimizing and updating the first optimization point according to the target optimal solution to obtain the second optimization point, includes:

[0148] B3351. Obtain the penalty factor corresponding to the target optimal solution, and the benefit function corresponding to the target optimal solution;

[0149] B3352. Based on the penalty factor, solve the benefit function to obtain the benefit step size corresponding to the target optimal solution;

[0150] B3353. Based on the benefit step size and the target optimal solution, update the first optimization point to obtain the second optimization point.

[0151] In this embodiment, the penalty factor includes an equality constraint penalty factor and an inequality constraint penalty factor. Taking the penalty factor corresponding to the k-th optimization point as an example, the equality constraint penalty factor for the k-th optimization point can be expressed as:

[0152]

[0153] wherein, is the equality constraint penalty factor of the kthoptimization point; g k is a simplified expression of g(x k ), which is the target torque gradient of the kthoptimization point;

[0154] The inequality constraint penalty factor of the kthoptimization point can be expressed as:

[0155]

[0156] wherein, is the inequality constraint penalty factor of the kthoptimization point; [·] T is the transpose symbol.

[0157] The merit function can be expressed as:

[0158]

[0159] wherein, is the merit function of the kthoptimization point; is the equality constraint penalty factor of the kthoptimization point; is the inequality constraint penalty factor of the kthoptimization point; f(x k ) is the target torque function; c i (x k ) is the value of the ithconstraint function at the kthoptimization point.

[0160] It can be understood that, for an optimization point, step B3352 can be to input the equality constraint penalty factor and the inequality constraint penalty factor of the optimization point into the merit function, to obtain a step length of the merit function in the direction indicated by the target optimal solution at the optimization point by minimizing the merit function, so as to obtain a merit step length; then, based on the merit step length and the target optimal solution, the first optimization point is updated to obtain a second optimization point. Specifically, if the first optimization point is the kthoptimization point, and the intermediate optimal solution of the first optimization point is the same as the target optimal solution, the corresponding second optimization point can be expressed as:

[0161] x k+1 = x k + a k d k

[0162] wherein, x k+1 is the second optimization point; a k is the merit step length of the kthoptimization point; d k is the target optimal solution of the kthoptimization point.

[0163] B336, performing first condition verification on the optimization precision condition according to the first optimization point and the second optimization point, to obtain a first condition verification result;

[0164] B337, if the first condition verification result is that the optimization precision condition is satisfied, updating the first control sequence according to the target optimal solution, to obtain a second control sequence, and obtaining the engine torque control sequence and the motor torque control sequence according to the second control sequence;

[0165] Alternatively, B338, if the first condition verification result is that the optimization precision condition is not satisfied, updating the first control sequence according to the target optimal solution, and updating the first optimization point according to the second optimization point, and then returning to execute the steps of obtaining the first control sequence, the first optimization point, and the first quadratic programming sub-problem corresponding to the first optimization point.

[0166] In the embodiments of the present application, step B336 can first obtain an optimization norm between the first optimization point and the second optimization point, which can specifically be difference calculation on the first optimization point and the second optimization point, and then calculating the norm of the difference vector to obtain the optimization norm. Then, the size relationship between the optimization norm and the optimization precision condition is compared. If the optimization norm is less than the optimization precision condition, the first condition verification result representing that the optimization precision condition is satisfied can be obtained, which indicates that the torque distribution has reached the exit condition of the cyclic iteration. At this time, the latest target optimal solution can be added to the first control sequence to obtain the second control sequence, and then the engine torque control sequence and the motor torque control sequence are obtained based on the second control sequence. Alternatively, if the optimization norm is greater than or equal to the optimization precision condition, the first condition verification result that the optimization precision condition is not satisfied can be obtained, which indicates that the torque distribution has not reached the exit condition of the cyclic iteration. At this time, the first control sequence can be updated according to the target optimal solution, the updated first control sequence is taken as the first control sequence of the next cyclic iteration round, and the second optimization point is determined as the first optimization point of the next cyclic iteration round, and then the step B32 is executed.

[0167] It can be understood that, for the target optimal solution corresponding to each optimization point of the control sequence, it can be the energy control strategy corresponding to the engine, or the energy control strategy corresponding to the motor, and the application does not limit this. In addition, when the engine torque control sequence and the motor torque control sequence are used to jointly control the energy of the target vehicle, the target vehicle can be caused to sequentially execute each energy control strategy in the engine torque control sequence and each energy control strategy in the motor torque control sequence, and when all the energy control strategies in the control sequence have been executed, return to step 110; or, the target vehicle can be caused to execute the first energy control strategy in the engine torque control sequence and the first energy control strategy in the motor torque control sequence, and then return to step 110 to jointly control the energy of the target vehicle by acquiring the latest engine torque control sequence and motor torque control sequence in real time, which can continuously correct the energy control deviation and is beneficial to improving the effect of energy control.

[0168] A hybrid vehicle energy control system according to an embodiment of the application is described in detail below with reference to the accompanying drawings.

[0169] With reference to Figure 2 The hybrid vehicle energy control system according to an embodiment of the application includes:

[0170] The first processing unit 101 is configured to acquire a trained vehicle speed prediction model and a preset torque control rule, and driving speed data and remaining power data of a target vehicle.

[0171] The second processing unit 102 is configured to input the driving speed data into the trained vehicle speed prediction model to perform vehicle speed prediction and obtain predicted vehicle speed data.

[0172] The third processing unit 103 is configured to acquire a driving working mode of the target vehicle according to driving demand torque of the driving speed data and the remaining power data, where the driving working mode includes a regular working mode and an irregular working mode.

[0173] The fourth processing unit 104 is configured to perform energy control on the target vehicle according to the torque control rule if the driving working mode is the regular working mode, or perform torque distribution on the target vehicle demand torque according to the driving speed data and the remaining power data if the driving working mode is the irregular working mode, to obtain an engine torque control sequence and a motor torque control sequence, and perform joint energy control on the target vehicle according to the engine torque control sequence and the motor torque control sequence.

[0174] It is understood that the content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0175] Reference Figure 3 This application also provides an electronic device, including:

[0176] At least one processor 201;

[0177] At least one memory 202 is used to store at least one program;

[0178] When the at least one program is executed by the at least one processor 201, the at least one processor 201 implements the method embodiment described above.

[0179] Similarly, it can be understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0180] This application also provides a computer-readable storage medium storing a program executable by a processor 201, which, when executed by the processor 201, is used to implement the above-described method embodiments.

[0181] Similarly, the content of the above method embodiments is applicable to the present computer-readable storage medium embodiments. The specific functions implemented by the present computer-readable storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0182] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this application are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0183] Furthermore, although the present application is described in the context of functional modules, it is understood that one or more of the functions and / or features can be integrated in a single physical device and / or software module, or one or more functions and / or features can be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary to an understanding of the present application. Rather, the actual implementation is within the routine skill of engineers familiar with the property, function and internal relationships of the various functional modules disclosed herein. Accordingly, the present application is not limited to the specific details of the functional modules described herein. Rather, it is understood that the skilled artisan, using ordinary skill in the art, can implement the application as taught in the claims without undue experimentation. It is also understood that the specific concepts disclosed are merely illustrative and that the scope of the present application is determined by the appended claims and their equivalents.

[0184] If the functions are implemented in software, the functions can be stored in or implemented as one or more computer program products. The computer program product can be stored in a computer readable medium, which can include, but is not limited to, RAM, ROM, electrically programmable ROM (EPROM or EEPROM), flash memory, or a magnetic or optical card, or any suitable device used for storing a computer program. Furthermore, the computer program product can be implemented as at least one program that can be executed by one or more processors.

[0185] The logic and / or steps represented in the flowcharts and / or otherwise described herein, for example, can be embodied in non-transitory computer-readable media, which can be executed by an instruction execution system, apparatus, or device such as a computer-based system, processor, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. In the context of this specification, a "computer-readable medium" can be any means that can contain, store, communicate, propagate or transport the program for use by or in connection with the instruction execution system, apparatus, or device.

[0186] More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection (electronic) having one or more wires, a portable computer diskette (magnetic), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can also be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, for example, via optical scanning of the paper or other medium, then compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.

[0187] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the above embodiments, various steps or methods can be implemented in software or firmware that is stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any of the following technologies, or combinations thereof, can be used: a discrete logic circuit having logic gates for implementing logic functions upon data signals, an application specific integrated circuit having appropriate combinational logic gates, a programmable gate array (PGA), a field programmable gate array (FPGA), and / or the like.

[0188] In the above description of the present specification, the description referring to the terms "one embodiment", "another embodiment", or "certain embodiments" or the like means that a specific feature, structure, material or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present specification. The illustrative expressions of the above terms do not necessarily refer to the same embodiment or example throughout the present specification. Also, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0189] Although the embodiments of the present application have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, alternatives and variations to these embodiments can be made without departing from the principles and spirit of the application, the scope of which is defined by the claims and their equivalents.

[0190] The above is a specific description of the preferred embodiments of the present application, but the present application is not limited to the embodiments, and those skilled in the art can make various equivalent modifications or replacements without departing from the spirit of the present application, and these equivalent modifications or replacements are included in the scope defined by the claims of the present application.

Claims

1. An energy control method for a hybrid vehicle, characterized in that, include: Acquire the trained vehicle speed prediction model and preset torque control rules, as well as the target vehicle's driving speed data and remaining battery power data; The driving speed data is input into the trained vehicle speed prediction model to predict the vehicle speed and obtain the predicted vehicle speed data. Based on the remaining battery power data and the driving speed data, the driving torque demand is obtained for the target vehicle. The driving operating mode includes a regular operating mode and an irregular operating mode. If the driving mode is the rule-based working mode, then energy control is performed on the target vehicle according to the torque control rule; Alternatively, if the driving mode is the irregular working mode, then based on the driving speed data and the remaining battery power data, torque allocation is performed on the target speed torque requirement to obtain the engine torque control sequence and the motor torque control sequence, and energy joint control is performed on the target vehicle based on the engine torque control sequence and the motor torque control sequence. The constraint solution for the torque constraint problem corresponding to the engine torque control sequence and the motor torque control sequence includes: Obtain the objective torque function and torque constraint conditions for the torque constraint problem; Based on the target torque function and the torque constraint conditions, construct a first quadratic programming subproblem corresponding to the torque constraint problem; The first quadratic programming subproblem is optimized to obtain the engine torque control sequence and the motor torque control sequence. The sub-problem optimization of the first quadratic programming sub-problem to obtain the engine torque control sequence and the motor torque control sequence includes: Obtain the preset optimization accuracy conditions; Obtain the first control sequence, the first optimization point, and the first quadratic programming subproblem corresponding to the first optimization point; Based on the first optimization point, gradient analysis is performed on the target torque function to obtain the target torque gradient, and constraint analysis is performed on the torque constraint condition based on the first optimization point to obtain the torque constraint matrix; Based on the target torque gradient and the torque constraint matrix, the first quadratic programming subproblem is solved to obtain the target optimal solution; Based on the target optimal solution, the first optimization point is optimized and updated to obtain the second optimization point; Based on the first optimization point and the second optimization point, the optimization accuracy condition is verified by the first condition to obtain the first condition verification result; If the first condition verification result indicates that the optimization accuracy condition is met, then the first control sequence is updated according to the target optimal solution to obtain the second control sequence, and the engine torque control sequence and the motor torque control sequence are obtained according to the second control sequence; or, if the first condition verification result indicates that the optimization accuracy condition is not met, then the first control sequence is updated according to the target optimal solution, and the first optimization point is updated according to the second optimization point, and then the process returns to the steps of obtaining the first control sequence, the first optimization point, and the first quadratic programming subproblem corresponding to the first optimization point.

2. The method according to claim 1, characterized in that, The step of obtaining the driving operating mode of the target vehicle based on the driving demand torque according to the remaining battery power data and the driving speed data includes: Obtain the minimum battery threshold, maximum battery threshold, starting torque threshold, and optimal torque threshold; Based on the minimum and maximum power thresholds, the remaining power data is compared to obtain a power comparison result; Based on the starting torque threshold and the optimal torque threshold, the driving demand torque is compared to obtain the torque comparison result; Based on the comparison results of the electric power and the torque, the driving mode of the target vehicle is obtained.

3. The method according to claim 1, characterized in that, The step of allocating torque based on the vehicle speed data and the remaining battery power data to the torque required at the target vehicle speed, resulting in an engine torque control sequence and a motor torque control sequence, includes: The engine torque and motor torque of the target vehicle are obtained, as well as the input shaft speed corresponding to the driving speed data and the power equivalence factor corresponding to the remaining power data. Based on the electric power equivalence factor, the input shaft speed, the target vehicle speed torque requirement, the vehicle engine torque, and the vehicle motor torque, a torque constraint problem is constructed; The torque constraint problem is solved to obtain the engine torque control sequence and the motor torque control sequence.

4. The method according to claim 1, characterized in that, The step of solving the first quadratic programming subproblem based on the target torque gradient and the torque constraint matrix to obtain the target optimal solution includes: Based on the target torque gradient and the torque constraint matrix, the first quadratic programming subproblem is solved conditionally to obtain the intermediate optimal solution; The intermediate optimal solution is corrected to obtain the target optimal solution.

5. The method according to claim 4, characterized in that, The step of solving the first quadratic programming subproblem conditionally based on the target torque gradient and the torque constraint matrix to obtain an intermediate optimal solution includes: Based on the target torque gradient and the torque constraint matrix, the solution to the first quadratic programming subproblem is verified to obtain the solution verification result. The solution verification result is used to characterize whether there is a solution to the first quadratic programming subproblem. If the verification result of the problem solution indicates that the first quadratic programming subproblem has a solution, then the first quadratic programming subproblem is solved in its original form according to the target torque gradient and the torque constraint matrix to obtain the intermediate optimal solution; or, if the verification result of the problem solution indicates that the first quadratic programming subproblem has a solution, then the second quadratic programming subproblem corresponding to the first quadratic programming subproblem is obtained, and the second quadratic programming subproblem is solved by substitution according to the target torque gradient and the torque constraint matrix to obtain the intermediate optimal solution.

6. The method according to claim 4, characterized in that, The step of correcting the intermediate optimal solution to obtain the target optimal solution includes: Obtain the preset effect conditions; Based on the intermediate optimal solution, the effect condition is verified by a second condition, and the second condition verification result is obtained. If the second condition verification result indicates that the effect condition is satisfied, then the search direction of the intermediate optimal solution is corrected to obtain the target optimal solution; or, if the second condition verification result indicates that the effect condition is not satisfied, then the intermediate optimal solution is determined as the target optimal solution.

7. The method according to claim 1, characterized in that, The step of optimizing and updating the first optimization point based on the target optimal solution to obtain the second optimization point includes: Obtain the penalty factor corresponding to the target optimal solution, and the benefit function corresponding to the target optimal solution; Based on the penalty factor, the benefit function is solved to obtain the benefit step size corresponding to the target optimal solution; Based on the benefit step size and the target optimal solution, the first optimization point is updated to obtain the second optimization point.

8. An energy control system for a hybrid vehicle, characterized in that, include: The first processing unit is used to acquire the trained vehicle speed prediction model and the preset torque control rules, as well as the target vehicle's driving speed data and remaining battery power data. The second processing unit is used to input the driving speed data into the trained vehicle speed prediction model to predict the vehicle speed and obtain the predicted vehicle speed data. The third processing unit is used to obtain the driving operating mode of the target vehicle based on the remaining battery power data and the driving speed data, the driving operating mode including regular operating mode and irregular operating mode. The fourth processing unit is used to perform energy control on the target vehicle according to the torque control rule if the driving mode is the rule-based working mode. Alternatively, if the driving mode is the irregular working mode, then based on the driving speed data and the remaining battery power data, torque allocation is performed on the target speed torque requirement to obtain the engine torque control sequence and the motor torque control sequence, and energy joint control is performed on the target vehicle based on the engine torque control sequence and the motor torque control sequence. The system is also used to perform constraint solving of torque constraint problems corresponding to the engine torque control sequence and the motor torque control sequence, wherein the constraint solving of the torque constraint problems includes: Obtain the objective torque function and torque constraint conditions for the torque constraint problem; Based on the target torque function and the torque constraint conditions, construct a first quadratic programming subproblem corresponding to the torque constraint problem; The first quadratic programming subproblem is optimized to obtain the engine torque control sequence and the motor torque control sequence. The sub-problem optimization of the first quadratic programming sub-problem to obtain the engine torque control sequence and the motor torque control sequence includes: Obtain the preset optimization accuracy conditions; Obtain the first control sequence, the first optimization point, and the first quadratic programming subproblem corresponding to the first optimization point; Based on the first optimization point, gradient analysis is performed on the target torque function to obtain the target torque gradient, and constraint analysis is performed on the torque constraint condition based on the first optimization point to obtain the torque constraint matrix; Based on the target torque gradient and the torque constraint matrix, the first quadratic programming subproblem is solved to obtain the target optimal solution; Based on the target optimal solution, the first optimization point is optimized and updated to obtain the second optimization point; Based on the first optimization point and the second optimization point, the optimization accuracy condition is verified by the first condition to obtain the first condition verification result; If the first condition verification result indicates that the optimization accuracy condition is met, then the first control sequence is updated according to the target optimal solution to obtain the second control sequence, and the engine torque control sequence and the motor torque control sequence are obtained according to the second control sequence; or, if the first condition verification result indicates that the optimization accuracy condition is not met, then the first control sequence is updated according to the target optimal solution, and the first optimization point is updated according to the second optimization point, and then the process returns to the steps of obtaining the first control sequence, the first optimization point, and the first quadratic programming subproblem corresponding to the first optimization point.

Images