Hybrid electric vehicle control method, device and hybrid electric vehicle

The prediction model determines the oil discharge control signal, which solves the problem of slow power response in the energy recovery process of hybrid cars, achieves rapid power response and energy recovery, and improves battery life and driving experience.

CN117984985BActive Publication Date: 2024-11-01CHONGQING JINKANG NEW ENERGY VEHICLE CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311593070.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-11-27
Publication Date
2024-11-01
Estimated Expiration
2043-11-27

AI Technical Summary

Technical Problem

During the energy recovery process of hybrid cars, drivers respond slowly when changing their driving intentions, which is prone to power interruptions, affecting battery life and driving experience.

Method used

By acquiring and preprocessing the parameter information of hybrid vehicles, the pre-constructed predictive model is used to determine the oil discharge control signal, which can achieve fast power response and energy recovery mode switching to avoid power interruption.

Benefits of technology

Improves the driver's power response speed when changing driving intentions, avoids power interruptions, and improves energy utilization and range.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117984985B_ABST
    Figure CN117984985B_ABST
Patent Text Reader

Abstract

The present application relates to a hybrid vehicle control method, device and hybrid vehicle, and belongs to the field of new energy vehicle technology. The method includes: obtaining and preprocessing the first parameter information of the hybrid vehicle to obtain the target input signal value; inputting the target input signal value into a pre-built prediction model to obtain the target output result; obtaining the second parameter information of the hybrid vehicle, and determining the fuel injection cut-off control signal of the hybrid vehicle based on the target output result and the second parameter information; in response to detecting the fuel injection cut-off control signal, determining the energy recovery mode of the hybrid vehicle based on the second parameter information, and executing the operation corresponding to the fuel injection cut-off control signal. The present application can improve the power response when the driver changes the driving intention during braking or gliding, avoid the problem of power interruption in traditional vehicles, improve the driving experience, and meet the energy recovery requirements at the same time, improve energy utilization and driving range.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of new energy vehicles, and in particular to a hybrid vehicle control method, device and hybrid vehicle. Background Art

[0002] Energy recovery in hybrid vehicles is the process of converting the kinetic energy of the vehicle during coasting or braking into electrical energy to improve energy utilization, thereby alleviating the range anxiety of hybrid vehicles to a certain extent.

[0003] At present, during the energy recovery process of hybrid vehicles, the driving pedal opening, brake pedal opening, vehicle speed, SOC (remaining capacity, indicating the battery's ability to continue working) and other signals are basically received to determine whether the vehicle has entered energy recovery, determine the motor's target feedback torque, and control the clutch to disengage and the engine to shut down; when the driver changes his driving intention and steps on the accelerator pedal again during the energy recovery process, the vehicle is controlled to drive in pure electric mode or the engine is started again and the clutch is engaged to enter parallel mode after certain conditions are met. However, when the vehicle speed is still high and the accelerator pedal is stepped on again, the engine needs to be started and the clutch engaged before the vehicle enters parallel mode. The response to the driver's intention is slow, and there is also a risk of power interruption.

[0004] Therefore, there is an urgent need to propose a hybrid vehicle control method, device and hybrid vehicle that can avoid vehicle power interruption while meeting energy recovery requirements. Summary of the invention

[0005] Based on this, it is necessary to provide a hybrid vehicle control method, device and hybrid vehicle that can avoid vehicle power interruption while meeting energy recovery requirements in order to address the above technical issues.

[0006] In one aspect, a hybrid vehicle control method is provided, the method comprising:

[0007] Acquiring first parameter information of the hybrid electric vehicle, and preprocessing the first parameter information to obtain a target input signal value;

[0008] Inputting the target input signal value into a pre-built prediction model to obtain a target output result;

[0009] Acquiring second parameter information of the hybrid vehicle, and determining a fuel injection cut-off control signal of the hybrid vehicle based on the target output result and the second parameter information;

[0010] In response to detecting the fuel injection cut-off control signal, an energy recovery mode of the hybrid vehicle is determined based on the second parameter information, and an operation corresponding to the fuel injection cut-off control signal is performed.

[0011] Optionally, before acquiring the first parameter information of the hybrid vehicle and preprocessing the first parameter information to obtain the target input signal value, the method further includes:

[0012] Acquire third parameter information, where the third parameter information includes vehicle speed, accelerator pedal change rate, vehicle gross mass, battery pack remaining capacity, road slope, and road mileage corresponding to at least one historical time node;

[0013] Based on a standardization function, the third parameter information is standardized to obtain a third parameter information processing result, wherein the standardization function includes:

[0014]

[0015] Among them, V x Indicates the standard value, v x Represents the original value, v avr represents the mean;

[0016] Based on the third parameter information processing result, the bias of the prediction model and the one-dimensional vector weight corresponding to each parameter are determined.

[0017] Optionally, the first parameter information includes at least one of the following: vehicle speed, accelerator pedal change rate, vehicle gross mass, battery pack remaining capacity, road slope, and road mileage corresponding to the prediction time node. The acquiring the first parameter information of the hybrid vehicle and preprocessing the first parameter information to obtain the target input signal value includes:

[0018] Acquiring first parameter information of the hybrid electric vehicle;

[0019] Based on the standardization function, the first parameter information is standardized to obtain a first parameter information processing result;

[0020] Based on the first parameter information processing result, construct the characteristic signal vector X corresponding to each parameter = x1, x2, x3, ... x n , which is the target input signal value.

[0021] Optionally, inputting the target input signal value into a pre-built prediction model to obtain a target output result includes:

[0022] The characteristic signal vector X corresponding to each parameter is X=x1,x2,x3,...x n Input into the pre-built prediction model, the expression of the prediction model is:

[0023] f=x1×w1+x2×w2+...+x n × n +b

[0024]

[0025] Where W = w1, w2, w3, ... w n represents the one-dimensional vector weight corresponding to each parameter, A represents the fuel injection cut-off signal value, δ represents the preset threshold, f represents the predicted value, and b represents the bias;

[0026] A mapping relationship between the fuel injection cut-off signal value and the road mileage is established, which is the target output result.

[0027] Optionally, the second parameter information includes at least a current vehicle speed and a calculation cycle, and acquiring the second parameter information of the hybrid vehicle and determining the fuel injection cut-off control signal of the hybrid vehicle based on the target output result and the second parameter information includes:

[0028] Determining a travel distance of the hybrid vehicle within the calculation period based on the current vehicle speed and the calculation period;

[0029] Obtaining the difference between the road mileage and the current traveled distance;

[0030] In response to detecting that the difference is less than or equal to the driving distance, the fuel cut-off signal value and the fuel cut-off control signal of the hybrid vehicle are determined based on a mapping relationship corresponding to the road mileage.

[0031] Optionally, determining the fuel cut-off control signal of the hybrid vehicle based on the fuel cut-off signal value includes:

[0032] In response to detecting that the fuel injection cut-off signal value A=1, determining that the fuel injection cut-off control signal of the hybrid vehicle is a fuel injection signal;

[0033] In response to detecting that the fuel injection cut-off signal value A=-1, the fuel injection cut-off control signal of the hybrid vehicle is determined to be a fuel cut-off signal.

[0034] Optionally, the second parameter information further includes at least a current brake pedal state, an accelerator pedal opening, and a remaining capacity of a battery pack. Based on the second parameter information, determining the energy recovery mode of the hybrid vehicle includes:

[0035] In response to detecting that the current brake pedal state is a pressed state, the remaining capacity of the battery pack is less than a second preset value, and the current vehicle speed is greater than a third preset value, determining that the hybrid vehicle enters a brake energy recovery mode;

[0036] In response to detecting that the current brake pedal state is not pressed, the accelerator pedal opening is less than a first preset value, the remaining capacity of the battery pack is less than a second preset value, and the current vehicle speed is greater than a fourth preset value, it is determined that the hybrid vehicle enters a coasting energy recovery mode.

[0037] Optionally, the second parameter information also includes at least a current temperature of the battery pack, and the method further includes:

[0038] In response to detecting that the difference is greater than the driving distance, determining the battery pack discharge power according to the remaining capacity of the battery pack and the current temperature of the battery pack, and determining the hybrid vehicle required power according to the current vehicle speed and the accelerator pedal opening;

[0039] In response to detecting that the discharge power of the battery pack is less than the required power of the hybrid vehicle, and the accelerator pedal opening is greater than or equal to a first preset value, controlling the hybrid vehicle to perform a fuel injection operation;

[0040] In response to detecting that the discharge power of the battery pack is greater than or equal to the required power of the hybrid vehicle, and the accelerator pedal opening is less than a first preset value, the hybrid vehicle is controlled to perform a fuel cut operation.

[0041] In another aspect, a hybrid vehicle control device is provided, the device comprising:

[0042] A preprocessing module, used for acquiring first parameter information of the hybrid electric vehicle, and preprocessing the first parameter information to obtain a target input signal value;

[0043] A prediction module, used to input the target input signal value into a pre-built prediction model to obtain a target output result;

[0044] a signal determination module, configured to obtain second parameter information of the hybrid vehicle, and determine a fuel injection cut-off control signal of the hybrid vehicle based on the target output result and the second parameter information;

[0045] An execution module is used to determine the energy recovery mode of the hybrid vehicle based on the second parameter information when the fuel injection cut-off control signal is detected, and execute an operation corresponding to the fuel injection cut-off control signal.

[0046] In another aspect, a hybrid vehicle is provided, the hybrid vehicle comprising:

[0047] Memory;

[0048] processor; and,

[0049] A hybrid electric vehicle control device, the device being installed in the memory and comprising one or more software function modules executed by the processor, the hybrid electric vehicle control device comprising:

[0050] A preprocessing module, used for acquiring first parameter information of the hybrid electric vehicle, and preprocessing the first parameter information to obtain a target input signal value;

[0051] A prediction module, used to input the target input signal value into a pre-built prediction model to obtain a target output result;

[0052] a signal determination module, configured to obtain second parameter information of the hybrid vehicle, and determine a fuel injection cut-off control signal of the hybrid vehicle based on the target output result and the second parameter information;

[0053] an execution module, configured to determine the energy recovery mode of the hybrid vehicle based on the second parameter information when the fuel injection cut-off control signal is detected, and execute an operation corresponding to the fuel injection cut-off control signal;

[0054] When the processor executes the software function module, the following steps are implemented:

[0055] Acquiring first parameter information of the hybrid electric vehicle, and preprocessing the first parameter information to obtain a target input signal value;

[0056] Inputting the target input signal value into a pre-built prediction model to obtain a target output result;

[0057] Acquiring second parameter information of the hybrid vehicle, and determining a fuel injection cut-off control signal of the hybrid vehicle based on the target output result and the second parameter information;

[0058] In response to detecting the fuel injection cut-off control signal, determining an energy recovery mode of the hybrid vehicle based on the second parameter information, and performing an operation corresponding to the fuel injection cut-off control signal;

[0059] When the software function module is executed by the processor, the following steps are implemented:

[0060] Acquiring first parameter information of the hybrid electric vehicle, and preprocessing the first parameter information to obtain a target input signal value;

[0061] Inputting the target input signal value into a pre-built prediction model to obtain a target output result;

[0062] Acquiring second parameter information of the hybrid vehicle, and determining a fuel injection cut-off control signal of the hybrid vehicle based on the target output result and the second parameter information;

[0063] In response to detecting the fuel injection cut-off control signal, an energy recovery mode of the hybrid vehicle is determined based on the second parameter information, and an operation corresponding to the fuel injection cut-off control signal is performed.

[0064] The above-mentioned hybrid vehicle control method, device and hybrid vehicle, the method includes: obtaining first parameter information of the hybrid vehicle, and preprocessing the first parameter information to obtain a target input signal value; inputting the target input signal value into a pre-constructed prediction model to obtain a target output result; obtaining second parameter information of the hybrid vehicle, and determining an injection-cut control signal of the hybrid vehicle based on the target output result and the second parameter information; in response to detecting the injection-cut control signal, determining an energy recovery mode of the hybrid vehicle based on the second parameter information, and executing an operation corresponding to the injection-cut control signal. The present application can improve the power response when the driver changes his driving intention during braking or gliding, avoid the problem of power interruption in traditional vehicles, enhance the driving experience, and at the same time meet energy recovery requirements, improve energy utilization and cruising range. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 A diagram showing an application environment of a hybrid vehicle control method in one embodiment;

[0066] Figure 2 A schematic diagram of a flow chart of a hybrid vehicle control method in one embodiment;

[0067] Figure 3 FIG. 4 is a structural block diagram of a hybrid vehicle control device in one embodiment. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0069] It should be understood that in the description of the present application, unless the context clearly requires otherwise, words such as "include", "comprises", and the like throughout the specification should be interpreted as including rather than being exclusive or exhaustive; that is, as including but not limited to.

[0070] It should also be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, "plurality" means two or more.

[0071] It should be noted that the terms "S1", "S2", etc. are only used for the purpose of describing the steps, and do not specifically refer to the order or sequence, nor are they used to limit the present application. They are only for the convenience of describing the method of the present application, and cannot be understood as indicating the order of the steps. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in this field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present application.

[0072] The hybrid vehicle control method provided in this application can be applied to Figure 1 In the vehicle 100 shown, the vehicle 100 may include an onboard terminal 120. The onboard terminal 120 includes at least one memory and at least one processor, wherein a computer program is stored in the at least one memory, and when the computer program is executed by the at least one processor, a hybrid vehicle control method according to an exemplary embodiment of the present disclosure is executed. Here, the onboard terminal 120 is not necessarily a single electronic device, but may also be any collection of devices or circuits that can execute the above-mentioned computer program alone or in combination.

[0073] In the vehicle terminal 120, the processor may include a central processing unit (CPU), a graphics processing unit (GPU), a programmable logic device, a dedicated processor system, a microcontroller or a microprocessor. As an example and not a limitation, the processor may also include an analog processor, a digital processor, a microprocessor, a multi-core processor, a processor array, a network processor, etc.; in the vehicle terminal 120, the processor may run a computer program stored in a memory, which may be divided into one or more modules / units (such as computer program 1, computer program 2, ...), and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program in the terminal device. The memory may be integrated with the processor, for example, RAM or flash memory is arranged within an integrated circuit microprocessor, etc. In addition, the memory may include an independent device, such as an external disk drive, a storage array, or any other storage device that can be used by any database system. The memory and the processor may be coupled in operation, or may communicate with each other, for example, through an I / O port, a network connection, etc., so that the processor can read files stored in the memory.

[0074] In addition, the vehicle terminal 120 may also include a display device (such as a liquid crystal display, etc.) and a user interaction interface (such as a keyboard, a mouse, a touch input device, etc.), and all components of the vehicle terminal 120 may be connected to each other via a bus and / or a network.

[0075] Embodiment 1: In one embodiment, as Figure 2 As shown, a hybrid vehicle control method is provided, and the method is applied to Figure 1 The terminal in is used as an example to illustrate, including the following steps:

[0076] S1: Acquire first parameter information of a hybrid vehicle, and preprocess the first parameter information to obtain a target input signal value.

[0077] It should be noted that a hybrid vehicle refers to a vehicle whose vehicle drive system is composed of two or more single drive systems that can operate simultaneously, and the vehicle's driving power is provided by a single drive system alone or together according to the actual vehicle driving state; the first parameter information includes at least one of the following: the vehicle speed corresponding to the prediction time node, the accelerator pedal change rate, the total vehicle mass, the remaining capacity of the battery pack, the road slope and the road mileage, wherein the relevant data corresponding to the prediction time node refers to the data that can be predicted based on the navigation map and the vehicle control system, or can be obtained based on the factory setting data, and the accelerator pedal change rate can be divided into based on the change gradient value Different driving styles, such as standard, aggressive and gentle, each style corresponds to a standard value, preferably 0, 1, 2. For example, if the accelerator pedal change rate may become larger during the uphill stage, the corresponding driving style may be aggressive (i.e., an aggressive driving mode, such as driving at low or medium speeds in urban areas, encountering traffic lights or congested road conditions, the driver suddenly steps on the brake pedal to stop and wait, or suddenly steps on the accelerator pedal to start driving, etc., which can be judged by road conditions, vehicle speed, and pedal opening change rate), and the preferred value is 1; the target input signal value refers to the data value obtained after preprocessing the collected first parameter information, which is used as the input value of the prediction model.

[0078] In some specific implementations, before acquiring the first parameter information of the hybrid vehicle and preprocessing the first parameter information to obtain the target input signal value, the method further includes:

[0079] Acquire third parameter information, the third parameter information including vehicle speed, accelerator pedal change rate, vehicle gross mass, battery pack remaining capacity, road slope, and road mileage corresponding to at least one historical time node, wherein the third parameter information is historical data information stored in a memory, and is used to train and verify the prediction model;

[0080] Based on the standardization function, the third parameter information is standardized to obtain the third parameter information processing result, wherein the third parameter information to be standardized includes vehicle speed, total vehicle mass, road mileage, battery pack remaining capacity, and road slope can directly take their standard values, the range of standard values ​​is (0,100), and the acceleration pedal change rate also directly takes its corresponding standard value of 0 or 1 or 2. The standardization function includes:

[0081]

[0082] Among them, V x Indicates the standard value, v x Represents the original value, v avr represents the mean;

[0083] Based on the processing result of the third parameter information, the bias of the prediction model and the one-dimensional vector weight corresponding to each parameter are determined. Specifically, the prediction model is established based on a perceptron, and its activation function is:

[0084]

[0085] The calculation process of the perceptron is:

[0086] f=x1×w1+x2×w2+...+x n × n +b

[0087] The corresponding loss function is:

[0088] L(w,b)=-∑A(x n × n +b)

[0089] Where W = w1, w2, w3, ... w n represents the one-dimensional vector weight corresponding to each parameter, A represents the fuel injection cut-off signal value, δ represents the preset threshold, f represents the predicted value, b represents the bias, X = x1, x2, x3, ... x n represents the characteristic signal vector corresponding to each parameter, L(w,b) represents the loss function, and the minimum value of the loss function can be obtained by training the standardized third parameter information to determine the one-dimensional vector weight W and the bias b.

[0090] In some specific implementations, obtaining first parameter information of the hybrid vehicle and preprocessing the first parameter information to obtain the target input signal value includes:

[0091] Acquiring first parameter information of the hybrid electric vehicle;

[0092] Based on the standardization function, the first parameter information is standardized to obtain a first parameter information processing result, wherein the standardization function here is the same as the above standardization function, and the processing process is also the same, which will not be repeated here;

[0093] Based on the first parameter information processing result, construct the characteristic signal vector X corresponding to each parameter = x1, x2, x3, ... x n , which is the target input signal value.

[0094] In the above-mentioned embodiment, the third parameter information is standardized to train the prediction model, and the bias of the prediction model and the one-dimensional vector weight corresponding to each parameter are obtained, which are used for subsequent prediction of the fuel injection cut-off signal of the hybrid vehicle to ensure that the power response speed is improved when the driver changes the driving intention during high-speed braking or gliding of the hybrid vehicle. In addition, the first parameter information is obtained and standardized to obtain the target input signal value of the prediction model, so as to obtain the fuel injection cut-off signal value corresponding to the future time node, thereby further improving the power response speed.

[0095] S2: Input the target input signal value into a pre-built prediction model to obtain a target output result.

[0096] It should be noted that this step specifically includes:

[0097] The characteristic signal vector X corresponding to each parameter is X=x1,x2,x3,...x n Input into the pre-built prediction model, and obtain the output value corresponding to the prediction model, which is the target output result;

[0098] A mapping relationship between the fuel injection cut-off signal value and the road mileage is established, which is the target output result. For example, the set of road mileage is S = [s1, s2, s3, ..., s x ], the set of oil injection cut-offs A = [a1, a2, a3, …, a x ], a x Indicates that hybrid vehicles are x The predicted fuel injection and fuel cut-off status.

[0099] In the above implementation, by constructing a mapping relationship between road mileage and fuel cut-off state, the hybrid vehicle is in the predicted fuel cut-off state when it is at a certain road mileage, thereby avoiding the power interruption problem of traditional vehicles and improving the driving experience.

[0100] S3: Acquire second parameter information of the hybrid vehicle, and determine a fuel injection-cutoff control signal of the hybrid vehicle based on the target output result and the second parameter information.

[0101] It should be noted that the second parameter information includes at least the current vehicle speed, calculation cycle, current brake pedal state, accelerator pedal opening, current battery pack temperature and remaining battery pack capacity, wherein the calculation cycle is generally taken as 0.1s.

[0102] In some specific implementations, obtaining the second parameter information of the hybrid vehicle, and determining the fuel injection cut-off control signal of the hybrid vehicle based on the target output result and the second parameter information includes:

[0103] Based on the current vehicle speed and the calculation cycle, the driving distance of the hybrid vehicle within the calculation cycle is determined, that is, when the road mileage s is about to be reached, x When , the judgment threshold Δs=v*t is set, where v represents the current vehicle speed and t represents the calculation cycle;

[0104] Obtaining the difference between the road mileage and the current traveled distance;

[0105] In response to detecting that the difference is less than or equal to the driving distance, the fuel cut-off signal value and the fuel cut-off control signal of the hybrid vehicle are determined based on the mapping relationship corresponding to the road mileage. For example, when the road mileage is s1, the corresponding fuel cut-off signal value is a1, and the fuel cut-off control signal of the hybrid vehicle is determined based on the fuel cut-off signal value, specifically:

[0106] In response to detecting that the fuel injection cut-off signal value A=1, determining that the fuel injection cut-off control signal of the hybrid vehicle is a fuel injection signal;

[0107] In response to detecting that the fuel injection cut-off signal value A=-1, the fuel injection cut-off control signal of the hybrid vehicle is determined to be a fuel cut-off signal.

[0108] In the above implementation, because the mapping relationship between the output result corresponding to the prediction model and the fuel cut-off state is constantly changing according to the parameter information collected in real time, in order to ensure the accuracy of the fuel cut-off state switching, the present application sets a judgment threshold to ensure that before the start of the next calculation cycle, the state of the hybrid vehicle has been switched to the fuel cut-off state corresponding to the fuel cut-off signal value obtained in the current calculation cycle, thereby avoiding the power interruption problem of traditional vehicles and further improving the driving experience.

[0109] In some specific embodiments, in response to detecting that the difference is greater than the driving distance, the battery pack discharge power is determined according to the remaining capacity of the battery pack and the current temperature of the battery pack, and the hybrid vehicle required power is determined according to the current vehicle speed and the accelerator pedal opening, wherein the battery pack discharge power and the hybrid vehicle required power are respectively determined according to parameters such as the remaining capacity of the battery pack, the current temperature of the battery pack, the accelerator pedal opening and the current vehicle speed. This is a common method and will not be described in detail here; in response to detecting that the battery pack discharge power is less than the hybrid vehicle required power, and the accelerator pedal opening is greater than or equal to a first preset value, the hybrid vehicle is controlled to perform a fuel injection operation, wherein the first preset value can be set according to actual needs, such as 3%;

[0110] In response to detecting that the discharge power of the battery pack is greater than or equal to the required power of the hybrid vehicle, and the accelerator pedal opening is less than a first preset value, the hybrid vehicle is controlled to perform a fuel cut operation.

[0111] In the above embodiment, if the road mileage or fuel injection cut-off state of the hybrid vehicle is not included in the above mapping relationship, the fuel injection cut-off signal is judged according to the real-time state of the vehicle, and then the hybrid vehicle is controlled to switch the fuel injection cut-off state, so as to ensure the accuracy of the state switching from a multi-dimensional perspective, thereby improving the power response of the driver to change the driving intention during high-speed braking or gliding, avoiding the power interruption problem of traditional vehicles, and improving the driving experience.

[0112] S4: in response to detecting the fuel injection cut-off control signal, determining an energy recovery mode of the hybrid vehicle based on the second parameter information, and executing an operation corresponding to the fuel injection cut-off control signal.

[0113] It should be noted that this step specifically includes:

[0114] In response to detecting that the current brake pedal state is a pressed state (Pressed), the remaining capacity of the battery pack is less than a second preset value, and the current vehicle speed is greater than a third preset value, determining that the hybrid vehicle enters a braking energy recovery mode, at which time the accelerator pedal is in a released state, and exiting the braking energy recovery mode when the current vehicle speed is less than or equal to a fifth preset value;

[0115] In response to detecting that the current brake pedal state is not pressed (NoPressed), the accelerator pedal opening is less than a first preset value, the remaining capacity of the battery pack is less than a second preset value, and the current vehicle speed is greater than a fourth preset value, it is determined that the hybrid vehicle enters a coasting energy recovery mode, and when the current vehicle speed is less than or equal to a sixth preset value, the coasting energy recovery mode is exited.

[0116] Among them, the above-mentioned first preset value, second preset value, third preset value, fourth preset value, fifth preset value and sixth preset value can all be set according to actual needs. Preferably, the fourth preset value is less than the third preset value, and the sixth preset value is less than the fifth preset value. For example, the first preset value is 3%, the second preset value is 90%, the third preset value is 15km / h, the fourth preset value is 8km / h, the fifth preset value is 13km / h, and the sixth preset value is 6km / h.

[0117] Before determining the energy recovery mode of the hybrid vehicle, the vehicle mode is judged to enter the parallel mode through the conditions that the current vehicle speed is greater than or equal to 55km / h, the engine and the clutch have no prohibiting working faults, and the battery pack SOC is greater than 10%. When the current vehicle speed is less than the parallel exit speed critical value of 55km / h, the whole vehicle enters the series mode. The energy recovery mode of the hybrid vehicle is further determined based on the judged series-parallel mode. Among them, after the whole vehicle enters the series mode, the method for judging the fuel injection cut-off signal according to the real-time state of the vehicle also includes: obtaining the difference between the current remaining capacity of the battery pack and the target remaining capacity of the battery pack When the difference is greater than a seventh preset value, the hybrid vehicle is controlled to perform a fuel cut-off operation; when the difference is less than an eighth preset value, the hybrid vehicle is controlled to perform a fuel injection operation; the seventh preset value and the eighth preset value can be set according to actual needs, such as the seventh preset value is 5% and the eighth preset value is -1%. This method and the above-mentioned method for determining the fuel cut-off signal according to the real-time state of the vehicle are in an "or" relationship, such as when the battery pack discharge power is less than the hybrid vehicle demand power and the accelerator pedal opening is greater than or equal to the first preset value, or the difference is less than the eighth preset value, the hybrid vehicle is controlled to perform a fuel injection operation.

[0118] Furthermore, during braking energy recovery, the vehicle controller obtains the target braking deceleration by looking up the table according to the current vehicle speed and brake pedal opening, and then converts it into the motor target feedback torque through the transmission speed ratio, efficiency, and charging torque limit. The engine target torque is 0; during coasting energy recovery, the coasting recovery torque is obtained by looking up the table according to the current vehicle speed and accelerator pedal opening, and then converted into the motor target feedback torque through the charging torque limit. The engine target torque is 0.

[0119] Furthermore, if the fuel injection cut-off control signal is a fuel injection signal, based on the accelerator pedal opening and the required power of the vehicle, the corresponding fuel injection amount in the preset two-dimensional table is obtained through linear interpolation to perform fuel injection operation control. If it is a fuel cut-off signal, the vehicle controller is controlled to send a fuel cut-off signal to achieve a fuel cut-off operation.

[0120] In the above-mentioned embodiment, the energy recovery mode is judged according to the predicted fuel injection cut-off control signal, so as to meet the energy recovery demand while improving the power response, thereby improving the energy utilization rate and the cruising range of the whole vehicle.

[0121] In the above-mentioned hybrid vehicle control method, the method includes: obtaining first parameter information of the hybrid vehicle, and preprocessing the first parameter information to obtain a target input signal value; inputting the target input signal value into a pre-constructed prediction model to obtain a target output result; obtaining second parameter information of the hybrid vehicle, and determining an injection-cut control signal of the hybrid vehicle based on the target output result and the second parameter information; in response to detecting the injection-cut control signal, determining an energy recovery mode of the hybrid vehicle based on the second parameter information, and executing an operation corresponding to the injection-cut control signal. The present application can improve the power response when the driver changes his driving intention during braking or gliding, avoid the problem of power interruption in traditional vehicles, enhance the driving experience, and at the same time meet energy recovery requirements, improve energy utilization and cruising range.

[0122] It should be understood that although Figure 2 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0123] Embodiment 2: In one embodiment, as Figure 3 As shown, a hybrid vehicle control device is provided, comprising: a preprocessing module, a prediction module, a signal determination module and an execution module, wherein:

[0124] A preprocessing module, used for acquiring first parameter information of the hybrid electric vehicle, and preprocessing the first parameter information to obtain a target input signal value;

[0125] A prediction module, used to input the target input signal value into a pre-built prediction model to obtain a target output result;

[0126] a signal determination module, configured to obtain second parameter information of the hybrid vehicle, and determine a fuel injection cut-off control signal of the hybrid vehicle based on the target output result and the second parameter information;

[0127] An execution module is used to determine the energy recovery mode of the hybrid vehicle based on the second parameter information when the fuel injection cut-off control signal is detected, and execute an operation corresponding to the fuel injection cut-off control signal.

[0128] As a preferred implementation, in the embodiment of the present invention, the device further includes a model parameter determination module, and the model parameter determination module is specifically used to:

[0129] Acquire third parameter information, where the third parameter information includes vehicle speed, accelerator pedal change rate, vehicle gross mass, battery pack remaining capacity, road slope, and road mileage corresponding to at least one historical time node;

[0130] Based on a standardization function, the third parameter information is standardized to obtain a third parameter information processing result, wherein the standardization function includes:

[0131]

[0132] Among them, V x Indicates the standard value, v x Represents the original value, v avr represents the mean;

[0133] Based on the third parameter information processing result, the bias of the prediction model and the one-dimensional vector weight corresponding to each parameter are determined.

[0134] As a preferred implementation, in the embodiment of the present invention, the preprocessing module is specifically used for:

[0135] Acquire first parameter information of the hybrid vehicle, the first parameter information including at least one of the following: vehicle speed, accelerator pedal change rate, vehicle gross mass, battery pack remaining capacity, road slope, and road mileage corresponding to the prediction time node;

[0136] Based on the standardization function, the first parameter information is standardized to obtain a first parameter information processing result;

[0137] Based on the first parameter information processing result, construct the characteristic signal vector X corresponding to each parameter = x1, x2, x3, ... x n , which is the target input signal value.

[0138] As a preferred implementation, in the embodiment of the present invention, the prediction module is specifically used for:

[0139] The characteristic signal vector X corresponding to each parameter is X=x1,x2,x3,...x n Input into the pre-built prediction model, the expression of the prediction model is:

[0140] f=x1×w1+x2×w2+...+x n × n +b

[0141]

[0142] Where W = w1, w2, w3, ... w n represents the one-dimensional vector weight corresponding to each parameter, A represents the fuel injection cut-off signal value, δ represents the preset threshold, f represents the predicted value, and b represents the bias;

[0143] A mapping relationship between the fuel injection cut-off signal value and the road mileage is established, which is the target output result.

[0144] As a preferred implementation, in the embodiment of the present invention, the signal determination module is specifically used for:

[0145] Acquiring second parameter information of the hybrid electric vehicle, wherein the second parameter information at least includes a current vehicle speed and a calculation cycle;

[0146] Determining a travel distance of the hybrid vehicle within the calculation period based on the current vehicle speed and the calculation period;

[0147] Obtaining the difference between the road mileage and the current traveled distance;

[0148] In response to detecting that the difference is less than or equal to the driving distance, the fuel cut-off signal value and the fuel cut-off control signal of the hybrid vehicle are determined based on a mapping relationship corresponding to the road mileage.

[0149] As a preferred implementation, in the embodiment of the present invention, the signal determination module is further used to:

[0150] In response to detecting that the fuel injection cut-off signal value A=1, determining that the fuel injection cut-off control signal of the hybrid vehicle is a fuel injection signal;

[0151] In response to detecting that the fuel injection cut-off signal value A=-1, the fuel injection cut-off control signal of the hybrid vehicle is determined to be a fuel cut-off signal.

[0152] As a preferred implementation, in the embodiment of the present invention, the execution module is specifically used for:

[0153] Acquiring second parameter information of the hybrid vehicle, the second parameter information at least including a current brake pedal state, an accelerator pedal opening, and a remaining capacity of a battery pack;

[0154] In response to detecting that the current brake pedal state is a pressed state, the remaining capacity of the battery pack is less than a second preset value, and the current vehicle speed is greater than a third preset value, determining that the hybrid vehicle enters a brake energy recovery mode;

[0155] In response to detecting that the current brake pedal state is not pressed, the accelerator pedal opening is less than a first preset value, the remaining capacity of the battery pack is less than a second preset value, and the current vehicle speed is greater than a fourth preset value, it is determined that the hybrid vehicle enters a coasting energy recovery mode.

[0156] As a preferred implementation, in the embodiment of the present invention, the device further includes an injection-cut-off operation determination module, and the model parameter determination module is specifically used for:

[0157] In response to detecting that the difference is greater than the driving distance, determining the battery pack discharge power and the hybrid vehicle required power according to the remaining capacity of the battery pack and the current vehicle speed;

[0158] In response to detecting that the discharge power of the battery pack is less than the required power of the hybrid vehicle, and the accelerator pedal opening is greater than or equal to a first preset value, controlling the hybrid vehicle to perform a fuel injection operation;

[0159] In response to detecting that the discharge power of the battery pack is greater than or equal to the required power of the hybrid vehicle, and the accelerator pedal opening is less than a first preset value, the hybrid vehicle is controlled to perform a fuel cut operation.

[0160] The specific definition of the hybrid vehicle control device can be found in the definition of the hybrid vehicle control method above, which will not be repeated here. Each module in the above hybrid vehicle control device can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0161] Embodiment 3: In one embodiment, a hybrid vehicle is provided, the hybrid vehicle comprising a memory, a processor; and,

[0162] A hybrid electric vehicle control device, the device being installed in the memory and comprising one or more software function modules executed by the processor, the hybrid electric vehicle control device comprising:

[0163] A preprocessing module, used for acquiring first parameter information of the hybrid electric vehicle, and preprocessing the first parameter information to obtain a target input signal value;

[0164] A prediction module, used to input the target input signal value into a pre-built prediction model to obtain a target output result;

[0165] a signal determination module, configured to obtain second parameter information of the hybrid vehicle, and determine a fuel injection cut-off control signal of the hybrid vehicle based on the target output result and the second parameter information;

[0166] An execution module is used to determine the energy recovery mode of the hybrid vehicle based on the second parameter information when the fuel injection cut-off control signal is detected, and execute an operation corresponding to the fuel injection cut-off control signal.

[0167] When the processor executes the software function module, the following steps are implemented:

[0168] S1: Acquire first parameter information of the hybrid vehicle, and preprocess the first parameter information to obtain a target input signal value;

[0169] S2: Inputting the target input signal value into a pre-built prediction model to obtain a target output result;

[0170] S3: acquiring second parameter information of the hybrid vehicle, and determining a fuel injection cut-off control signal of the hybrid vehicle based on the target output result and the second parameter information;

[0171] S4: in response to detecting the fuel injection cut-off control signal, determining the energy recovery mode of the hybrid vehicle based on the second parameter information, and executing an operation corresponding to the fuel injection cut-off control signal;

[0172] When the software function module is executed by the processor, the following steps are implemented:

[0173] S1: Acquire first parameter information of the hybrid vehicle, and preprocess the first parameter information to obtain a target input signal value;

[0174] S2: Inputting the target input signal value into a pre-built prediction model to obtain a target output result;

[0175] S3: acquiring second parameter information of the hybrid vehicle, and determining a fuel injection cut-off control signal of the hybrid vehicle based on the target output result and the second parameter information;

[0176] S4: in response to detecting the fuel injection cut-off control signal, determining an energy recovery mode of the hybrid vehicle based on the second parameter information, and executing an operation corresponding to the fuel injection cut-off control signal.

[0177] In one embodiment, the processor executes the software function module, and / or the software function module further implements the following steps when executed by the processor:

[0178] In one embodiment, the processor executes the software function module, and / or the software function module further implements the following steps when executed by the processor:

[0179] Acquire third parameter information, where the third parameter information includes vehicle speed, accelerator pedal change rate, vehicle gross mass, battery pack remaining capacity, road slope, and road mileage corresponding to at least one historical time node;

[0180] Based on a standardization function, the third parameter information is standardized to obtain a third parameter information processing result, wherein the standardization function includes:

[0181]

[0182] Among them, V x Indicates the standard value, v x Represents the original value, v avr represents the mean;

[0183] Based on the third parameter information processing result, the bias of the prediction model and the one-dimensional vector weight corresponding to each parameter are determined.

[0184] In one embodiment, the processor executes the software function module, and / or the software function module further implements the following steps when executed by the processor:

[0185] Acquire first parameter information of the hybrid vehicle, the first parameter information including at least one of the following: vehicle speed, accelerator pedal change rate, vehicle gross mass, battery pack remaining capacity, road slope, and road mileage corresponding to the prediction time node;

[0186] Based on the standardization function, the first parameter information is standardized to obtain a first parameter information processing result;

[0187] Based on the first parameter information processing result, construct the characteristic signal vector X corresponding to each parameter = x1, x2, x3, ... x n , which is the target input signal value.

[0188] In one embodiment, the processor executes the software function module, and / or the software function module further implements the following steps when executed by the processor:

[0189] The characteristic signal vector X corresponding to each parameter is X=x1,x2,x3,...x n Input into the pre-built prediction model, the expression of the prediction model is:

[0190] f=x1×w1+x2×w2+...+x n × n +b

[0191]

[0192] Where W = w1, w2, w3, ... w n represents the one-dimensional vector weight corresponding to each parameter, A represents the fuel injection cut-off signal value, δ represents the preset threshold, f represents the predicted value, and b represents the bias;

[0193] A mapping relationship between the fuel injection cut-off signal value and the road mileage is established, which is the target output result.

[0194] In one embodiment, the processor executes the software function module, and / or the software function module further implements the following steps when executed by the processor:

[0195] Acquiring second parameter information of the hybrid electric vehicle, wherein the second parameter information at least includes a current vehicle speed and a calculation cycle;

[0196] Determining a travel distance of the hybrid vehicle within the calculation period based on the current vehicle speed and the calculation period;

[0197] Obtaining the difference between the road mileage and the current traveled distance;

[0198] In response to detecting that the difference is less than or equal to the driving distance, the fuel cut-off signal value and the fuel cut-off control signal of the hybrid vehicle are determined based on a mapping relationship corresponding to the road mileage.

[0199] In one embodiment, the processor executes the software function module, and / or the software function module further implements the following steps when executed by the processor:

[0200] In response to detecting that the fuel injection cut-off signal value A=1, determining that the fuel injection cut-off control signal of the hybrid vehicle is a fuel injection signal;

[0201] In response to detecting that the fuel injection cut-off signal value A=-1, the fuel injection cut-off control signal of the hybrid vehicle is determined to be a fuel cut-off signal.

[0202] In one embodiment, the processor executes the software function module, and / or the software function module further implements the following steps when executed by the processor:

[0203] Acquiring second parameter information of the hybrid vehicle, the second parameter information at least including a current brake pedal state, an accelerator pedal opening, and a remaining capacity of a battery pack;

[0204] In response to detecting that the current brake pedal state is a pressed state, the remaining capacity of the battery pack is less than a second preset value, and the current vehicle speed is greater than a third preset value, determining that the hybrid vehicle enters a brake energy recovery mode;

[0205] In response to detecting that the current brake pedal state is not pressed, the accelerator pedal opening is less than a first preset value, the remaining capacity of the battery pack is less than a second preset value, and the current vehicle speed is greater than a fourth preset value, it is determined that the hybrid vehicle enters a coasting energy recovery mode.

[0206] In one embodiment, the processor executes the software function module, and / or the software function module further implements the following steps when executed by the processor:

[0207] In response to detecting that the difference is greater than the driving distance, determining the battery pack discharge power and the hybrid vehicle required power according to the remaining capacity of the battery pack and the current vehicle speed;

[0208] In response to detecting that the discharge power of the battery pack is less than the required power of the hybrid vehicle, and the accelerator pedal opening is greater than or equal to a first preset value, controlling the hybrid vehicle to perform a fuel injection operation;

[0209] In response to detecting that the discharge power of the battery pack is greater than or equal to the required power of the hybrid vehicle, and the accelerator pedal opening is less than a first preset value, the hybrid vehicle is controlled to perform a fuel cut operation.

[0210] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0211] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0212] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application.

Claims

1. A hybrid vehicle control method, characterized in that: The method comprises: Acquire first parameter information of the hybrid vehicle, and preprocess the first parameter information to obtain a target input signal value, wherein the first parameter information includes at least one of the following: vehicle speed, accelerator pedal change rate, vehicle gross mass, battery pack remaining capacity, road slope, and road mileage corresponding to a prediction time node; The target input signal value is input into the pre-built prediction model to obtain the target output result. The expression of the prediction model is: f=x1×w1+x2×w2+...+x n ×w n +b Where W = w1, w2, w3, ... w n represents the one-dimensional vector weight corresponding to each parameter, A represents the fuel injection cut-off signal value, δ represents the preset threshold, f represents the predicted value, b represents the bias, X=x1,x2,x3,...x n represents the characteristic signal vector; Acquire second parameter information of the hybrid vehicle, and determine a fuel injection cut-off control signal of the hybrid vehicle based on the target output result and the second parameter information, wherein the second parameter information at least includes a current vehicle speed and a calculation cycle; In response to detecting the fuel injection cut-off control signal, an energy recovery mode of the hybrid vehicle is determined based on the second parameter information, and an operation corresponding to the fuel injection cut-off control signal is performed.

2. The hybrid vehicle control method according to claim 1, characterized in that: Before acquiring the first parameter information of the hybrid vehicle and preprocessing the first parameter information to obtain the target input signal value, the method further includes: Acquire third parameter information, where the third parameter information includes vehicle speed, accelerator pedal change rate, vehicle gross mass, battery pack remaining capacity, road slope, and road mileage corresponding to at least one historical time node; Based on a standardization function, the third parameter information is standardized to obtain a third parameter information processing result, wherein the standardization function includes: Among them, V x Indicates the standard value, v x Represents the original value, v avr represents the mean; Based on the third parameter information processing result, the bias of the prediction model and the one-dimensional vector weight corresponding to each parameter are determined.

3. The hybrid vehicle control method according to claim 1, characterized in that: The step of acquiring first parameter information of the hybrid vehicle and preprocessing the first parameter information to obtain a target input signal value includes: Acquiring first parameter information of the hybrid electric vehicle; Based on the standardization function, the first parameter information is standardized to obtain a first parameter information processing result; Based on the first parameter information processing result, a characteristic signal vector X corresponding to each parameter is constructed. n , which is the target input signal value.

4. The hybrid vehicle control method according to claim 3, characterized in that: Inputting the target input signal value into the pre-built prediction model to obtain the target output result includes: The characteristic signal vector X corresponding to each parameter is X=x1,x2,x3,...x n input into the pre-built prediction model; A mapping relationship between the fuel injection cut-off signal value and the road mileage is established, which is the target output result.

5. The hybrid vehicle control method according to claim 4, characterized in that: Determining the fuel injection cut-off control signal of the hybrid vehicle based on the target output result and the second parameter information includes: Determining a travel distance of the hybrid vehicle within the calculation period based on the current vehicle speed and the calculation period; Obtaining the difference between the road mileage and the current traveled distance; In response to detecting that the difference is less than or equal to the driving distance, the fuel cut-off signal value and the fuel cut-off control signal of the hybrid vehicle are determined based on a mapping relationship corresponding to the road mileage.

6. The hybrid vehicle control method according to claim 4, characterized in that: Determining the fuel cut-off control signal of the hybrid vehicle based on the fuel cut-off signal value includes: In response to detecting that the fuel injection cut-off signal value A=1, determining that the fuel injection cut-off control signal of the hybrid vehicle is a fuel injection signal; In response to detecting that the fuel injection cut-off signal value A=-1, the fuel injection cut-off control signal of the hybrid vehicle is determined to be a fuel cut-off signal.

7. The hybrid vehicle control method according to claim 1, characterized in that: The second parameter information at least includes a current brake pedal state, an accelerator pedal opening, and a remaining capacity of a battery pack. Based on the second parameter information, determining the energy recovery mode of the hybrid vehicle includes: In response to detecting that the current brake pedal state is a pressed state, the remaining capacity of the battery pack is less than a second preset value, and the current vehicle speed is greater than a third preset value, determining that the hybrid vehicle enters a brake energy recovery mode; In response to detecting that the current brake pedal state is not pressed, the accelerator pedal opening is less than a first preset value, the remaining capacity of the battery pack is less than a second preset value, and the current vehicle speed is greater than a fourth preset value, it is determined that the hybrid vehicle enters a coasting energy recovery mode.

8. The hybrid vehicle control method according to claim 5, characterized in that: The second parameter information also includes at least the current temperature of the battery pack, and the method further includes: In response to detecting that the difference is greater than the driving distance, determining the battery pack discharge power according to the remaining capacity of the battery pack and the current temperature of the battery pack, and determining the hybrid vehicle required power according to the current vehicle speed and the accelerator pedal opening; In response to detecting that the discharge power of the battery pack is less than the required power of the hybrid vehicle, and the accelerator pedal opening is greater than or equal to a first preset value, controlling the hybrid vehicle to perform a fuel injection operation; In response to detecting that the discharge power of the battery pack is greater than or equal to the required power of the hybrid vehicle, and the accelerator pedal opening is less than a first preset value, the hybrid vehicle is controlled to perform a fuel cut operation.

9. A hybrid vehicle control device, characterized in that: The device comprises: A preprocessing module is used to obtain first parameter information of the hybrid vehicle and preprocess the first parameter information to obtain a target input signal value, wherein the first parameter information includes at least one of the following: vehicle speed, accelerator pedal change rate, vehicle gross mass, battery pack remaining capacity, road slope, and road mileage corresponding to a prediction time node; The prediction module is used to input the target input signal value into a pre-built prediction model to obtain a target output result. The expression of the prediction model is: f=x1×w1+x2×w2+...+x n ×w n +b Where W = w1, w2, w3, ... w n represents the one-dimensional vector weight corresponding to each parameter, A represents the fuel injection cut-off signal value, δ represents the preset threshold, f represents the predicted value, b represents the bias, X=x1,x2,x3,...x n represents the characteristic signal vector; a signal determination module, configured to obtain second parameter information of the hybrid vehicle, and determine a fuel injection cut-off control signal of the hybrid vehicle based on the target output result and the second parameter information; An execution module is used to determine the energy recovery mode of the hybrid vehicle based on the second parameter information when the injection-cut control signal is detected, and execute the operation corresponding to the injection-cut control signal, wherein the second parameter information at least includes the current vehicle speed and the calculation cycle.

10. A hybrid vehicle, characterized in that: The hybrid vehicle comprises: Memory; processor; and, A hybrid electric vehicle control device, the device being installed in the memory and comprising one or more software function modules executed by the processor, the hybrid electric vehicle control device comprising: A preprocessing module is used to obtain first parameter information of the hybrid vehicle and preprocess the first parameter information to obtain a target input signal value, wherein the first parameter information includes at least one of the following: vehicle speed, accelerator pedal change rate, vehicle gross mass, battery pack remaining capacity, road slope, and road mileage corresponding to a prediction time node; The prediction module is used to input the target input signal value into a pre-built prediction model to obtain a target output result. The expression of the prediction model is: Where W = w1, w2, w3, ... w n represents the one-dimensional vector weight corresponding to each parameter, A represents the fuel injection cut-off signal value, δ represents the preset threshold, f represents the predicted value, b represents the bias, X=x1,x2,x3,...x n represents the characteristic signal vector; a signal determination module, configured to obtain second parameter information of the hybrid vehicle, and determine a fuel injection cut-off control signal of the hybrid vehicle based on the target output result and the second parameter information; An execution module is used to determine the energy recovery mode of the hybrid vehicle based on the second parameter information when the injection-cut control signal is detected, and execute the operation corresponding to the injection-cut control signal, wherein the second parameter information at least includes the current vehicle speed and the calculation cycle.