Learning optimization method for target intake density of engine

Abstract

The invention relates to an engine target air inlet density learning optimization method. The method comprises the steps that the initial target air inlet density is determined; reading the difference between the current engine request gas path torque and the actual engine gas path torque, and determining the target gas inlet density increment in the Nth sampling period according to the difference; different working conditions are set, the stored target air inlet density increment corresponding to the different working conditions is updated according to the learning condition, and the sum of the updated stored target air inlet density increment and the initial target air inlet density is the optimized target air inlet density. According to the method, the target air inflow is determined based on the request air path torque, meanwhile, when the request torque is different from the actual torque, active learning optimization is conducted on the air inflow density, and therefore the target air inflow is improved, the torque control responsiveness is improved, and the dynamic property, economical efficiency, emission and NVH performance of an engine are improved.

Description

Technical Field

[0001] The present invention relates to the field of engine control, and more specifically to a method for learning and optimizing engine target intake density. Background Art

[0002] Engine torque control affects the performance of engine power, economy, emissions and NVH, so engine torque is an important parameter for engine control. If there is a control deviation in engine torque, the power of the engine will be seriously affected. In the prior art, the intake volume is determined based on the torque on the bench calibration, and the accuracy of the target intake volume over the entire life cycle of the engine is not taken into account. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide an engine target intake density learning optimization method, which can optimize the intake control, thereby improving the target intake volume and improving the torque control responsiveness.

[0004] The technical solution adopted by the present invention to solve the technical problem is: constructing an engine target intake density learning optimization method, comprising:

[0005] Determine the initial target intake air density;

[0006] Read the difference between the current engine requested gas path torque and the actual engine gas path torque, and determine the target intake density increment in the Nth sampling period based on the difference;

[0007] Different operating conditions are set, and the target intake density increments stored corresponding to the different operating conditions are updated according to the learning situation. The sum of the updated stored target intake density increment and the initial target intake density is the optimized target intake density.

[0008] According to the above scheme, the target intake density increment in the Nth sampling cycle is determined according to the following formula:

[0009] Δrho(N)=k TrqToRho ×M AirTrqErr +Δrho(N-1)

[0010] Wherein, N = 1, 2, 3…; Δrho(N) is the target intake density increment at the Nth sampling cycle, Δrho(N-1) is the target intake density increment at the N-1th sampling cycle, M AirTrqErr k is the difference between the current engine requested gas path torque and the actual engine gas path torque; TrqToRho is the target intake air density gain coefficient.

[0011] According to the above scheme, the target intake density gain coefficient is determined according to the following formula:

[0012]

[0013] Among them, dM AirTrqErr is the torque difference M AirTrqErr The rate of change, k Lrn is the self-learning correction coefficient of the target intake density gain coefficient, λ is the target intake density gain coefficient k TrqToRho The filtering time, f(M AirTrqErr , dM AirTrqErr ) is the difference between different torques M AirTrqErr The rate of change of the difference between the torque and the AirTrqErr The correction factor of .

[0014] According to the above scheme, if the target intake density increment Δrho(N) in the Nth sampling period reaches its maximum and minimum allowable values, it is maintained unchanged, that is, Δrho(N) = Δrho(N-1);

[0015] The maximum and minimum values ​​allowed depend on the target intake air density rho Re qRaw (z) and the engine speed n are jointly determined, that is, the maximum value is equal to f(n, rho Re qRaw (z))×(1+r Adap ), the minimum value is equal to f(n,rho Re qRaw (z))×(1+r Adap ), f(n,rho Re qRaw The calibration basis of (z)) is the torque difference M after adjusting the gas volume AirTrqErr When the fluctuation range is within the preset range, the torque difference M AirTrqErr The absolute value of the torque before adjustment is M AirTrqErr The absolute value of r is small; Adap It is the maximum and minimum value self-learning correction coefficient.

[0016] According to the above scheme, when any of the conditions (1) to (3) is met

[0017] (1) The time after Δrho(N) reaches its maximum or minimum value exceeds the preset time;

[0018] (2) The torque difference M read in real time AirTrqErr Within the preset range;

[0019] (3) The stability conditions are met simultaneously for longer than the preset time;

[0020] Then, the updating of the target intake density increment Δrho is stopped immediately, where Δrho(N) refers to the target intake density increment Δrho in the Nth sampling cycle.

[0021] According to the above scheme, if any of the conditions (1) to (3) is met and the following condition (4) is met: the engine request gas path torque M AirTrq Req The actual engine gas path torque M AirTrqAct Difference M AirTrqErr The fluctuation range does not exceed the preset value;

[0022] Record the operating condition information and update the current Δrho to store it in the corresponding same operating condition, and save it after the vehicle is powered off. The stored target intake density increment Δrho Stored The storage method is as follows:

[0023] Δrho Stored =k1×Δrho Stored (z)+(1-k1)×Δrho

[0024] Where Δrho Stored (z) is the target intake density increment learned and stored last time under the same operating conditions, and k1 is the weighting coefficient;

[0025] Updated Δrho Stored Add the initial target intake air density rho ReqRaw Get the optimized target intake density rho Re qNew .

[0026] According to the above scheme, the number of times CNT that any of conditions (1) to (3) is satisfied and condition (4) is satisfied at the same time under the same working conditions is recorded each time, as well as the number of times CNT1, CNT2 and CNT3 that conditions (1), (2) and (3) are satisfied respectively, then CNT1+CNT2+CNT3=CNT;

[0027] If CNT is greater than 15, CNT1 is greater than 10, and CNT2 is less than 2 under the same working conditions, the maximum and minimum self-learning correction coefficient r Adap =r Adap (z)+0.1; where r Adap (z) is the maximum and minimum self-learning correction coefficient of the last learning update. After the update is completed, CNT, CNT1, CNT2 and CNT3 are all cleared;

[0028] If CNT is greater than 15, CNT3 is greater than 10, and CNT2 is less than 2 under the same operating conditions, the target intake density gain coefficient k Lrn =k Lrn (z)+0.02; where k Lrn (z) is the target intake density gain coefficient of the last learning update. After the update is completed, CNT, CNT1, CNT2 and CNT3 are all cleared;

[0029] If CNT is greater than 15, CNT1 is not greater than 2, and CNT3 is greater than 2 under the same operating conditions, then the target intake density gain coefficient k Lrn =k Lrn (z)-0.01; maximum and minimum self-learning correction coefficient r Adap =r Adap (z) -0.1; after the update is completed, CNT, CNT1, CNT2 and CNT3 are all cleared;

[0030] In other cases, the target intake air density gain coefficient k Lrn and the maximum and minimum self-learning correction coefficient r Adap Remain unchanged.

[0031] According to the above scheme, if any of conditions (1) to (3) is met while condition (4) is not met, the operating condition information is recorded and the target intake density increment stored in the corresponding same operating condition is updated. The stored target intake density increment Δrho Stored =0.

[0032] The present invention also provides an engine target intake density learning and optimization device, comprising:

[0033] An initial target intake air density acquisition module is used to determine the initial target intake air density;

[0034] A target intake density increment determination module is used to read the difference between the current engine requested gas path torque and the engine actual gas path torque, and determine the target intake density increment in the Nth sampling period accordingly;

[0035] The learning optimization module is used to set different working conditions and update the target intake density increment stored corresponding to different working conditions according to the learning situation. The sum of the updated stored target intake density increment and the initial target intake density is the optimized target intake density.

[0036] The present invention also provides an engine target intake density learning and optimization device, wherein the target intake density increment determination module determines the target intake density increment in the Nth sampling period according to the following formula:

[0037] Δrho(N)=k TrqToRho ×M AirTrqErr +Δrho(N-1)

[0038] Wherein, N = 1, 2, 3…; Δrho(N) is the target intake density increment at the Nth sampling cycle, Δrho(N-1) is the target intake density increment at the N-1th sampling cycle, M AirTrqErr k is the difference between the current engine requested gas path torque and the actual engine gas path torque; TrqToRho is the target intake air density gain coefficient.

[0039] The present invention also provides an automobile, comprising the engine target intake density learning and optimization device.

[0040] The present invention also provides an electronic device, comprising: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; a computer program is stored in the memory, and when the program is executed by the processor, the processor executes the steps of the engine target intake density learning optimization method.

[0041] The present invention also provides a computer-readable storage medium on which executable instructions are stored. When the instructions are executed by a processor, the processor implements the engine target intake density learning optimization method.

[0042] The implementation of the engine target intake density learning optimization method of the present invention has the following beneficial effects:

[0043] The present invention determines the target intake volume based on the requested gas circuit torque, and actively learns and optimizes the intake density when there is a difference between the requested torque and the actual torque, thereby improving the target intake volume and the torque control responsiveness, thereby improving the engine power, economy, emissions and NVH performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0045] Figure 1 is a flow chart of the engine target intake density learning optimization method of the present invention;

[0046] Figure 2 It is a logic block diagram of the engine target intake density learning optimization method of the present invention. DETAILED DESCRIPTION

[0047] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, specific embodiments of the present invention are now described in detail with reference to the accompanying drawings.

[0048] like Figure 1 As shown, the engine target intake density learning optimization method of the present invention includes:

[0049] S1. Determine the initial target intake air density.

[0050] According to CN202010761489.X "Method for determining the torque efficiency of gasoline engine fire circuit and method for determining the actual ignition efficiency", the target gas circuit average indicated cylinder pressure p can be found AirIMEP Re q and the requested gas circuit torque M AirTrq Req relationship;

[0051] Patent CN202210332492.9 "Target intake density control method, device, equipment and readable storage medium" discloses the target gas path average indicated cylinder pressure p AirIMEP Req The initial target intake air density rho ReqRaw .

[0052] S2, reading the difference between the current engine requested gas path torque and the actual engine gas path torque, and determining the target intake density increment in the Nth sampling cycle accordingly. ReqRaw Optimize and obtain the optimized target intake density rho Re qNew , to improve torque control accuracy.

[0053] The present invention performs learning correction under steady-state conditions. The steady-state conditions are:

[0054] 1. The engine speed n fluctuation range is within the preset range, in this example ±15rpm;

[0055] 2. Engine requested gas circuit torque M AirTrq Req The fluctuation range is within the preset range, in this example, ±5Nm;

[0056] 3. The engine does not request to cut off fuel;

[0057] 4. The engine cooling water temperature is within the preset range, which is 80℃-95℃ in this example;

[0058] 5. The difference between the basic ignition angle efficiency of the engine and the actual ignition angle efficiency does not exceed the preset value, which is 0.7 in this example. If the actual ignition angle efficiency is too small, the engine combustion stability is poor, and the learning accuracy is low at this time.

[0059] 6. Engine requested gas circuit torque M AirTrq Req The actual engine gas path torque M AirTrqAct Difference M AirTrqErr The fluctuation range is within the preset range, in this example, ±5Nm;

[0060] 7. The actual EGR rate fluctuation range of the engine is within the preset range, which is ±0.01 in this example;

[0061] 8. The actual engine equivalence ratio fluctuation range is within the preset range, which is ±0.03 in this example;

[0062] 9. The fluctuation range of the difference between the target intake density and the actual intake density is within the preset range. In this example, it is ±15mgpl. The target intake density refers to the final optimized target intake density rho in the previous sampling cycle. Re qNew (z).

[0063] Once all the above conditions are not met, the learning process will be terminated; after the above conditions are met for a period exceeding the preset time t1 (0.5s in this example), the current engine requested gas path torque M is read. AirTrqReq The difference between the actual engine gas path torque and AirTrqErr ,but

[0064] Δrho(N)=k TrqToRho ×M AirTrqErr +Δrho(N-1)

[0065] Where N = 1, 2, 3…; where Δrho(N) is the target intake density increment at the Nth sampling cycle, Δrho(N-1) is the target intake density increment at the N-1th sampling cycle, and the sampling cycle Δt is 10ms in this example. In particular, the time when Δrho(0) occurs is when the above conditions are met for more than the preset time t1, and Δrho(0) is equal to 0. k TrqToRho is the target intake air density gain coefficient.

[0066] where dM AirTrqErr is the torque difference M AirTrqErr The rate of change of k TrqToRho The larger the value, the faster the target air intake density increases. TrqToRho The smaller the value, the slower the target intake density growth rate; the selection standard is to make it as fast as possible to improve the torque accuracy, but the faster it is, the more torque control fluctuations will be caused. Therefore, the calibration basis is to ensure that the torque difference M AirTrqErr The fluctuation range is within the preset range (±5Nm in this example), while the torque difference M AirTrqErr The absolute value of the torque before adjustment is M AirTrqErr The absolute value of k is small. Lrn It is the self-learning correction coefficient of the target intake density gain coefficient. Its default value is 0 and it can be saved after the vehicle is powered off.

[0067] λ is the target intake density gain coefficient k TrqToRho The filter time is in ms. The calibration data of this example is shown in Table 1.

[0068] Table 1

[0069]

[0070] f(M AirTrqErr , dM AirTrqErr ) is the difference between different torques M AirTrqErr The rate of change of the difference between the torque and the AirTrqErr The correction coefficients are shown in Table 2.

[0071] Table 2

[0072]

[0073] In particular, once the above conditions are not satisfied at the same time, or the time they are satisfied at the same time does not exceed t1, Δrho(N) is reset to 0.

[0074] In particular, once Δrho(N) reaches its maximum and minimum allowable values, it is maintained unchanged, that is, Δrho(N)=Δrho(N-1). Its maximum and minimum allowable values ​​are both dependent on the target intake air density rho Re qRaw (z) and the engine speed n are jointly determined, that is, the maximum value is equal to f(n, rho Re qRaw (z))×(1+r Adap ), the minimum value is equal to f(n,rho Re qRaw (z))×(1+r Adap ), this example is calibrated as follows, and its calibration basis is the torque difference M after adjusting the gas volume AirTrqErr The fluctuation range is within the preset range (±5Nm in this example), while the torque difference M AirTrqErr The absolute value of the torque before adjustment is M AirTrqErr The absolute value of r is small. Adap It is the maximum and minimum self-learning correction coefficient. Its default value is 0 and it can be saved after the vehicle is powered off.

[0075] f(n,rho Re qRaw The values ​​of (z) are shown in Table 3.

[0076] Table 3

[0077]

[0078] S3. Set different operating conditions, and update the stored target intake density increments corresponding to the different operating conditions according to the learning situation. The sum of the updated stored target intake density increment and the initial target intake density is the optimized target intake density.

[0079] Once one of the following conditions is met:

[0080] 1) The time after Δrho(N) reaches its maximum or minimum value exceeds t2, where t2 is equal to 0.2s;

[0081] 2) The torque difference M read in real time AirTrqErr Within the preset range, ±5Nm is taken in this example;

[0082] 3) The stability conditions are simultaneously met for a time exceeding a preset time t3. Where t3 is greater than t1, in this example t3-t1=1.5s;

[0083] Then stop updating Δrho immediately, where Δrho(N) refers to Δrho in the Nth sampling period.

[0084] A. If the following conditions are met at the same time while one of the above conditions is met: The engine requests the gas path torque M AirTrqReq The actual engine gas path torque M AirTrqAct Difference M AirTrqErr The fluctuation range does not exceed the preset value, which is ±5Nm in this example.

[0085] Record the operating information when the above conditions are met from t1 to t3. The operating information includes average engine speed, average equivalence ratio, average EGR rate, average basic ignition efficiency, and average engine requested gas path torque. The current Δrho is updated and stored in the corresponding same working condition. Other working conditions are not updated and stored, and can be saved after the vehicle is powered off. The stored target intake density increment Δrho Stored The storage method is as follows:

[0086] Δrho Stored =k1×Δrho Stored (z)+(1-k1)×Δrho

[0087] Where Δrho Stored (z) is the target intake density increment stored in the last learning under the same operating conditions. If it has never been learned and updated, its default value is 0, and the weighting coefficient k1 is 0.2.

[0088] With the updated Δrho Stored Add the initial target intake air density rho ReqRaw Get the optimized target intake density rho Re qNew .

[0089] Record the number of times CNT that condition A is satisfied under the same working condition each time, as well as the number of times CNT1, CNT2 and CNT3 that conditions 1), 2) and 3) above are satisfied respectively, then CNT1+CNT2+CNT3=CNT, and CNT, CNT1, CNT2 and CNT3 can all be saved after the vehicle is powered off.

[0090] If CNT is greater than 15, CNT1 is greater than 10, and CNT2 is less than 2 under the same working conditions, the maximum and minimum self-learning correction coefficient r Adap =r Adap (z)+0.1; where r Adap (z) is the maximum and minimum self-learning correction coefficient of the last learning update, and its default value is 0. After the update is completed, CNT, CNT1, CNT2 and CNT3 are all cleared.

[0091] If CNT is greater than 15, CNT3 is greater than 10, and CNT2 is less than 2 under the same operating conditions, the target intake density gain coefficient k Lrn =k Lrn (z)+0.02; where k Lrn (z) is the target intake density gain coefficient of the last learning update, and its default value is 0. After the update is completed, CNT, CNT1, CNT2 and CNT3 are all cleared.

[0092] If CNT is greater than 15, CNT1 is not greater than 2, and CNT3 is greater than 2 under the same operating conditions, then the target intake density gain coefficient k Lrn =k Lrn (z)-0.01; maximum and minimum self-learning correction coefficient r Adap =r Adap (z)-0.1; after the update is completed, CNT, CNT1, CNT2 and CNT3 are all cleared.

[0093] Among the above three conditions, at most one of them is updated in each driving cycle, and it is only updated once.

[0094] In other cases, the target intake air density gain coefficient k Lrn and the maximum and minimum self-learning correction coefficient r Adap Remain unchanged.

[0095] B. If the following conditions are not met during the process of meeting one of the above conditions: The engine requests the gas path torque M AirTrqReq The actual engine gas path torque M AirTrqAct Difference M AirTrqErr The fluctuation range does not exceed the preset value, which is ±5Nm in this example.

[0096] Also record the operating information (average engine speed, average equivalence ratio, average EGR rate, average basic ignition efficiency, average engine requested gas path torque) when the above conditions are met from t1 to t3 ), updates the target intake density increment stored in the same operating condition (other operating conditions are not updated and stored), and can be saved after the vehicle is powered off. The stored target intake density increment Δrho Stored The storage method is as follows: Δrho Stored = 0. And immediately use the updated Δrho Stored Add the initial target intake air density rho ReqRaw Get the optimized target intake density rho Re qNew

[0097] C. In other cases, continue to update Δrho. At this time, the optimized target intake density rho Re qNew Remain unchanged.

[0098] In particular, if the steady-state learning condition is not satisfied, the optimized target intake density rho Re qNew remains unchanged, that is, rho Re qNew = rho Re qRaw +Δrho Stored (z).

[0099] Embodiment 2

[0100] The present invention also provides an engine target intake density learning and optimization device, comprising:

[0101] An initial target intake air density acquisition module is used to determine the initial target intake air density;

[0102] A target intake density increment determination module is used to read the difference between the current engine requested gas path torque and the engine actual gas path torque, and determine the target intake density increment in the Nth sampling period accordingly;

[0103] The learning optimization module is used to set different working conditions and update the target intake density increment stored corresponding to different working conditions according to the learning situation. The sum of the updated stored target intake density increment and the initial target intake density is the optimized target intake density.

[0104] Embodiment 3

[0105] The present invention also provides an automobile, comprising the engine target intake density learning and optimization device.

[0106] Embodiment 4

[0107] The present invention also provides an electronic device, comprising: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; a computer program is stored in the memory, and when the program is executed by the processor, the processor executes the steps of the engine target intake density learning optimization method.

[0108] Embodiment 5

[0109] The present invention also provides a computer-readable storage medium on which executable instructions are stored. When the instructions are executed by a processor, the processor implements the engine target intake density learning optimization method.

[0110] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0111] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0112] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0113] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0114] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. A method for learning and optimizing target intake density of an engine, characterized in that: include: Determine the initial target intake air density; Read the difference between the current engine requested gas path torque and the actual engine gas path torque, and determine the target intake density increment in the Nth sampling period based on the difference; Different operating conditions are set, and the target intake density increments stored corresponding to the different operating conditions are updated according to the learning situation. The sum of the updated stored target intake density increment and the initial target intake density is the optimized target intake density.

2. The engine target intake density learning optimization method according to claim 1, characterized in that: The target intake density increment at the Nth sampling period is determined according to the following formula: Δrho(N)=k TrqToRho ×M AirTrqErr +Δrho(N-1) Wherein, N = 1, 2, 3…; Δrho(N) is the target intake density increment at the Nth sampling cycle, Δrho(N-1) is the target intake density increment at the N-1th sampling cycle, M AirTrqErr k is the difference between the current engine requested gas path torque and the actual engine gas path torque; TrqToRho is the target intake air density gain coefficient.

3. The engine target intake density learning optimization method according to claim 2, characterized in that: Determine the target intake air density gain factor according to the following formula: Among them, dM AirTrqErr is the torque difference M AirTrqErr The rate of change, k Lrn is the self-learning correction coefficient of the target intake density gain coefficient, λ is the target intake density gain coefficient k TrqToRho The filtering time, f(M AirTrqErr , dM AirTrqErr ) is the difference between different torques M AirTrqErr The rate of change of the difference between the torque and the AirTrqErr The correction factor of .

4. The engine target intake density learning optimization method according to claim 3, characterized in that: If the target intake density increment Δrho(N) in the Nth sampling period reaches its maximum and minimum allowable values, it is maintained unchanged, that is, Δrho(N) = Δrho(N-1); The maximum and minimum values ​​allowed depend on the target intake air density rho Re q R aw(z) and engine speed n jointly determine the maximum value equal to f(n,rho Re q R aw(z))×(1+r A dap), the minimum value is equal to f(n,rho Re q R aw(z))×(1+r A dap), f(n,rho Re q R The calibration basis of aw(z)) is the torque difference M after adjusting the gas volume AirTrqErr When the fluctuation range is within the preset range, the torque difference M AirTrqErr The absolute value of the torque before adjustment is M AirTrqErr The absolute value of r is small; Adap It is the maximum and minimum value self-learning correction coefficient.

5. The engine target intake density learning optimization method according to claim 4, characterized in that: When any of the conditions (1) to (3) is met (1) The time after Δrho(N) reaches its maximum or minimum value exceeds the preset time; (2) The torque difference M read in real time AirTrqErr Within the preset range; (3) The stability conditions are met simultaneously for longer than the preset time; Then, the updating of the target intake density increment Δrho is stopped immediately, where Δrho(N) refers to the target intake density increment Δrho in the Nth sampling cycle.

6. The engine target intake density learning optimization method according to claim 5, characterized in that: If any of the conditions (1) to (3) is met and the following condition (4) is met: the engine request gas path torque M AirTrqReq The actual engine gas path torque M AirTrqAct Difference M AirTrqErr The fluctuation range does not exceed the preset value; Record the operating condition information and update the current Δrho to store it in the corresponding same operating condition, and save it after the vehicle is powered off. The stored target intake density increment Δrho Stored The storage method is as follows: Δrho Stored =k1×Δrho Stored (z)+(1-k1)×Δrho Where Δrho Stored (z) is the target intake density increment learned and stored last time under the same operating conditions, and k1 is the weighting coefficient; Updated Δrho Stored Add the initial target intake air density rho ReqRaw Get the optimized target intake density rho ReqNew .

7. The engine target intake density learning optimization method according to claim 6, characterized in that: Record the number of times CNT that condition (4) is satisfied while any of conditions (1) to (3) is satisfied under the same working conditions, as well as the number of times CNT1, CNT2 and CNT3 that conditions (1), (2) and (3) are satisfied respectively, then CNT1+CNT2+CNT3=CNT; If CNT is greater than 15, CNT1 is greater than 10, and CNT2 is less than 2 under the same working conditions, the maximum and minimum self-learning correction coefficient r Adap =r Adap (z)+0.1; where r Adap (z) is the maximum and minimum self-learning correction coefficient of the last learning update. After the update is completed, CNT, CNT1, CNT2 and CNT3 are all cleared; If CNT is greater than 15, CNT3 is greater than 10, and CNT2 is less than 2 under the same operating conditions, the target intake density gain coefficient k Lrn =k Lrn (z)+0.02; where k Lrn (z) is the target intake density gain coefficient of the last learning update. After the update is completed, CNT, CNT1, CNT2 and CNT3 are all cleared; If CNT is greater than 15, CNT1 is not greater than 2, and CNT3 is greater than 2 under the same operating conditions, then the target intake density gain coefficient k Lrn =k Lrn (z)-0.01; maximum and minimum self-learning correction coefficient r Adap =r Adap (z) -0.1; after the update is completed, CNT, CNT1, CNT2 and CNT3 are all cleared; In other cases, the target intake air density gain coefficient k Lrn and the maximum and minimum self-learning correction coefficient r Adap Remain unchanged.

8. The engine target intake density learning optimization method according to claim 6, characterized in that: If any of conditions (1) to (3) is met while condition (4) is not met, the operating condition information is recorded and the target intake density increment stored in the corresponding operating condition is updated. The stored target intake density increment Δrho Stored =0.

9. An engine target intake density learning and optimization device, characterized in that: include: An initial target intake air density acquisition module is used to determine the initial target intake air density; A target intake density increment determination module is used to read the difference between the current engine requested gas path torque and the engine actual gas path torque, and determine the target intake density increment in the Nth sampling period accordingly; The learning optimization module is used to set different working conditions and update the target intake density increment stored corresponding to different working conditions according to the learning situation. The sum of the updated stored target intake density increment and the initial target intake density is the optimized target intake density.

10. The engine target intake density learning and optimization device according to claim 9, characterized in that: The target intake density increment determination module determines the target intake density increment in the Nth sampling period according to the following formula: Δrho(N)=k TrqToRho ×M AirTrqErr +Δrho(N-1) Wherein, N = 1, 2, 3…; Δrho(N) is the target intake density increment at the Nth sampling cycle, Δrho(N-1) is the target intake density increment at the N-1th sampling cycle, M AirTrqErr k is the difference between the current engine requested gas path torque and the actual engine gas path torque; TrqToRho is the target intake air density gain coefficient.

11. A car, characterized in that: It comprises the engine target intake density learning and optimization device as described in claim 9 or 10.

12. An electronic device comprising: A processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; characterized in that a computer program is stored in the memory, and when the program is executed by the processor, the processor executes the steps of the engine target intake density learning optimization method according to any one of claims 1 to 8.

13. A computer-readable storage medium having executable instructions stored thereon, characterized in that: When the instruction is executed by the processor, the processor implements the engine target intake density learning optimization method according to any one of claims 1 to 8.

Images