A self-learning method, device, apparatus and storage medium

Abstract

The application discloses a self-learning method and device, equipment and a storage medium, and is used for improving the efficiency of vehicle connection self-learning. The application monitors a vehicle, obtains parameter information corresponding to a shift operation if it is determined that the shift operation is triggered, determines a shift speed difference corresponding to the shift operation based on the parameter information, determines whether self-learning of a target working condition corresponding to the shift operation converges according to the shift speed difference, determines a target fuel injection pressure value corresponding to the vehicle based on the shift speed difference if the self-learning does not converge, and updates a current fuel injection pressure of the vehicle according to the target fuel injection pressure value. In the embodiment of the application, whether the self-learning of the target working condition converges is determined according to the shift speed difference, the current fuel injection pressure of the vehicle is updated in the case where it is determined that the self-learning of the target working condition does not converge, and then the shift time can be reduced and the shift process can be optimized.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a self-learning method, apparatus, device, and storage medium. Background Technology

[0002] In related technologies, some multi-speed automatic gasoline vehicles equipped with multi-plate clutches require establishing hydraulic pressure to drive piston movement until the multi-plate clutches are fully engaged to complete the gear shift. The shifting process during parking mainly refers to shifting from Neutral to Drive, D to N, N to Reverse, and R to N while stationary. Shifting from a non-drive gear to a drive gear primarily involves an oil filling process, while shifting from a drive gear to a non-drive gear primarily involves an oil unloading process.

[0003] During the filling process, the oil pressure pushes the piston to move. The clutch only starts to engage after the oil chamber is full. At this time, the turbine speed starts to drop from the steady-state speed until it becomes zero. The speed at which the filling oil pressure is built up will directly affect the magnitude of the speed fluctuation and the time for shifting gears, thus affecting the overall vehicle perception.

[0004] In related technologies, during the self-learning process of shifting gears in a parking space, if the shifting time is too long, the base oil filling pressure value will increase; if the shifting time is too short or the speed fluctuates greatly, the base oil filling pressure value will decrease. However, this self-learning method has a long self-learning time and converges slowly when there are many operating conditions of the whole vehicle, which leads to low self-learning efficiency. Summary of the Invention

[0005] In view of this, this application provides a self-learning method, apparatus, device, and storage medium to help solve the above-mentioned technical problems.

[0006] In a first aspect, embodiments of this application provide a self-learning method, the method comprising:

[0007] The vehicle is monitored, and if it is determined that a shifting operation has been triggered, the parameter information corresponding to the shifting operation is obtained.

[0008] The shift speed difference corresponding to the shifting operation is determined based on the parameter information.

[0009] Whether the self-learning of the target working condition corresponding to the shifting operation has converged is determined based on the shifting speed difference.

[0010] If convergence is not achieved, the target filling pressure value corresponding to the vehicle is determined based on the shift speed difference; and the current filling pressure of the vehicle is updated according to the target filling pressure value.

[0011] In some possible embodiments, the parameter information includes: current required torque, current transmission temperature, accelerator pedal opening degree, and current turbo speed. Determining the target fuel injection pressure value corresponding to the vehicle based on the shift speed difference includes:

[0012] The target operating condition corresponding to the warehouse transfer and gear shifting operation is determined based on the parameter information.

[0013] Determine the target acceleration factor and cumulative filling pressure corresponding to the target operating condition;

[0014] The basic value of the filling pressure is obtained based on the current required torque and the current gearbox temperature.

[0015] The oil filling ratio is obtained based on the current required torque, the current transmission temperature, and the accelerator pedal opening degree.

[0016] The target filling pressure value is obtained based on the target acceleration factor, the cumulative filling pressure, the base value of the filling pressure, and the filling ratio.

[0017] In some possible embodiments, obtaining the fill ratio based on the current required torque, the current transmission temperature, and the accelerator pedal opening degree includes:

[0018] The target shift time corresponding to the target operating condition is obtained based on the current transmission temperature and the accelerator pedal opening degree.

[0019] The target turbo speed is obtained based on the current required torque and the target shift time.

[0020] The turbine speed difference is obtained based on the difference between the target turbine speed and the current turbine speed;

[0021] The oil filling ratio is obtained based on the turbine speed difference.

[0022] In some possible embodiments, obtaining the target filling pressure value based on the target acceleration factor, the cumulative filling pressure, the baseline filling pressure value, and the filling ratio includes:

[0023] The first product value is obtained based on the oil filling ratio and the basic value of the oil filling pressure;

[0024] The sum of the first product value, the target acceleration factor, and the cumulative filling pressure is taken as the target filling pressure value.

[0025] In some possible embodiments, the step of determining whether the self-learning of the target operating condition corresponding to the shifting operation based on the shift speed difference has converged includes:

[0026] Determine whether the shift speed difference is greater than the calibrated shift speed difference corresponding to the target operating condition;

[0027] If it is determined that the shift speed difference is greater than or equal to the calibrated shift speed difference, then the self-learning convergence of the target operating condition is determined.

[0028] In some possible embodiments, after determining the self-learning convergence of the target operating condition, the method further includes:

[0029] The convergence count for the target operating condition is updated based on the historical convergence count to obtain the current convergence count.

[0030] In some possible embodiments, the method further includes:

[0031] Determine whether the current convergence count is greater than the preset convergence count;

[0032] If it is determined that the current convergence count is less than the preset convergence count, then return to the step of monitoring the vehicle.

[0033] In some possible embodiments, the method further includes:

[0034] Determine whether the driving cycle duration of the vehicle is greater than a preset duration;

[0035] If it is determined that the driving cycle duration of the vehicle is greater than the preset duration, then all self-learning converged working conditions from the start time of the vehicle driving cycle to the current time are obtained.

[0036] The first and second working conditions are determined from the self-learning convergence working conditions;

[0037] The target filling pressure value for the unlearned operating condition is determined based on the first operating condition and the second operating condition; the unlearned operating condition is the operating condition that has not been monitored from the start of the vehicle driving cycle to the current time.

[0038] The target filling pressure value of the unlearned working condition is used to update the filling pressure value of the unlearned working condition.

[0039] In some possible embodiments, determining the target filling pressure value for the unlearned operating condition based on the first operating condition and the second operating condition includes:

[0040] Based on the obtained current required torque and target filling pressure value corresponding to the first working condition, the current required torque and target filling pressure value corresponding to the second working condition, and the calibration required torque and calibration filling pressure value corresponding to the unlearned working condition, the self-learning offset corresponding to the unlearned working condition is obtained.

[0041] The current filling pressure value of the unlearned working condition is obtained based on the self-learning offset and the calibration filling pressure value corresponding to the unlearned working condition.

[0042] Secondly, embodiments of this application provide a self-learning device, the device comprising:

[0043] The monitoring module is used to monitor the vehicle. If it is determined that a shifting operation has been triggered, the module obtains the parameter information corresponding to the shifting operation.

[0044] The shift speed difference determination module is used to determine the shift speed difference corresponding to the shift operation based on the parameter information.

[0045] The self-learning module is used to determine whether the self-learning of the target working condition corresponding to the shifting operation has converged based on the shifting speed difference.

[0046] The oil filling pressure update module is used to determine the target oil filling pressure value corresponding to the vehicle based on the shift speed difference if convergence is not achieved; and to update the current oil filling pressure of the vehicle according to the target oil filling pressure value.

[0047] In some possible embodiments, the parameter information includes: current required torque, current transmission temperature, accelerator pedal opening, and current turbo speed. The oil pressure update module is specifically used for:

[0048] The target operating condition corresponding to the warehouse transfer and gear shifting operation is determined based on the parameter information.

[0049] Determine the target acceleration factor and cumulative filling pressure corresponding to the target operating condition;

[0050] The basic value of the filling pressure is obtained based on the current required torque and the current gearbox temperature.

[0051] The oil filling ratio is obtained based on the current required torque, the current transmission temperature, and the accelerator pedal opening degree.

[0052] The target filling pressure value is obtained based on the target acceleration factor, the cumulative filling pressure, the base value of the filling pressure, and the filling ratio.

[0053] In some possible embodiments, the oil filling pressure update module is specifically used for:

[0054] The target shift time corresponding to the target operating condition is obtained based on the current transmission temperature and the accelerator pedal opening degree.

[0055] The target turbo speed is obtained based on the current required torque and the target shift time.

[0056] The turbine speed difference is obtained based on the difference between the target turbine speed and the current turbine speed;

[0057] The oil filling ratio is obtained based on the turbine speed difference.

[0058] In some possible embodiments, the oil filling pressure update module is specifically used for:

[0059] The first product value is obtained based on the oil filling ratio and the basic value of the oil filling pressure;

[0060] The sum of the first product value, the target acceleration factor, and the cumulative filling pressure is taken as the target filling pressure value.

[0061] In some possible embodiments, the self-learning module is specifically used for:

[0062] Determine whether the shift speed difference is greater than the calibrated shift speed difference corresponding to the target operating condition;

[0063] If it is determined that the shift speed difference is greater than or equal to the calibrated shift speed difference, then the self-learning convergence of the target operating condition is determined.

[0064] In some possible embodiments, the self-learning module is further configured to:

[0065] The convergence count for the target operating condition is updated based on the historical convergence count to obtain the current convergence count.

[0066] In some possible embodiments, the self-learning module is further configured to:

[0067] Determine whether the current convergence count is greater than the preset convergence count;

[0068] If it is determined that the current convergence count is less than the preset convergence count, then return to the step of monitoring the vehicle.

[0069] In some possible embodiments, the self-learning module is further configured to:

[0070] Determine whether the driving cycle duration of the vehicle is greater than a preset duration;

[0071] If it is determined that the driving cycle duration of the vehicle is greater than the preset duration, then all self-learning converged working conditions from the start time of the driving cycle on the vehicle to the current time are obtained.

[0072] The first and second working conditions are determined from the self-learning convergence working conditions;

[0073] The target filling pressure value for the unlearned operating condition is determined based on the first operating condition and the second operating condition; the unlearned operating condition is the operating condition that has not been monitored from the start of the vehicle driving cycle to the current time.

[0074] The target filling pressure value of the unlearned working condition is used to update the filling pressure value of the unlearned working condition.

[0075] In some possible embodiments, the self-learning module is further configured to:

[0076] Based on the obtained current required torque and target filling pressure value corresponding to the first working condition, the current required torque and target filling pressure value corresponding to the second working condition, and the calibration required torque and calibration filling pressure value corresponding to the unlearned working condition, the self-learning offset corresponding to the unlearned working condition is obtained.

[0077] The current filling pressure value of the unlearned working condition is obtained based on the self-learning offset and the calibration filling pressure value corresponding to the unlearned working condition.

[0078] Thirdly, another embodiment of this application also provides an electronic device, including at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform any of the methods provided in the first aspect embodiment of this application.

[0079] Fourthly, another embodiment of this application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for causing a computer to perform any of the methods provided in the first aspect of this application.

[0080] Other features and advantages of this application will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0081] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0082] Figure 1 This is a schematic diagram of the overall process of a self-learning method provided in an embodiment of this application;

[0083] Figure 2 A schematic diagram illustrating the relationship between the shift direction and the shift speed difference in a self-learning method provided in this application embodiment;

[0084] Figure 3 A flowchart illustrating a self-learning method provided in this application for determining the target filling pressure value of a vehicle based on filling ratio, acceleration factor, cumulative filling pressure, and basic filling pressure value;

[0085] Figure 4 This is a schematic representation of the correspondence between the basic value of the filling pressure and the current required torque and the current transmission temperature in a self-learning method provided in this application embodiment.

[0086] Figure 5 A schematic diagram illustrating the process of obtaining the oil filling ratio based on the current required torque, current transmission temperature, and accelerator pedal opening degree in a self-learning method provided in this application embodiment;

[0087] Figure 6 This is a schematic representation of the relationship between turbine speed difference and oil filling ratio in a self-learning method provided in an embodiment of this application.

[0088] Figure 7 A schematic diagram illustrating the self-learning convergence process of a self-learning method for determining target operating conditions, provided in an embodiment of this application;

[0089] Figure 8 A schematic diagram illustrating the process of updating the oil filling pressure value of an unlearned working condition using a self-learning method provided in this application embodiment;

[0090] Figure 9 A schematic diagram illustrating a self-learning method provided in this application for determining the target filling pressure value of an unlearned working condition based on a first working condition and a second working condition;

[0091] Figure 10 A schematic diagram of an apparatus for a self-learning method provided in an embodiment of this application;

[0092] Figure 11 This is a schematic diagram of an electronic device that provides a self-learning method according to an embodiment of this application. Detailed Implementation

[0093] To better understand the technical solution of this application, the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0094] It should be understood that the described embodiments are merely some, not all, of the embodiments in this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0095] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. The singular forms “a,” “the,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0096] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0097] The inventors discovered that in certain multi-speed automatic gasoline vehicles equipped with multi-plate clutches, the gear shifting process requires establishing hydraulic pressure to drive the piston until the multi-plate clutches are fully engaged, ultimately completing the gear shift. Specifically, the shifting process in a parking space mainly refers to shifting from N to D, D to N, N to R, and R to N while stationary. The shifting from a non-drive gear to a drive gear primarily involves an oil filling process, while the shifting from a drive gear to a non-drive gear primarily involves an oil unloading process.

[0098] During the filling process, the oil pressure pushes the piston to move. The clutch only starts to engage after the oil chamber is full. At this time, the turbine speed starts to drop from the steady-state speed until it becomes zero. The speed at which the filling oil pressure is built up will directly affect the magnitude of the speed fluctuation and the time for shifting gears, thus affecting the overall vehicle perception.

[0099] In related technologies, during the self-learning process of shifting gears in a parking space, if the shifting time is too long, the base oil filling pressure value will increase; if the shifting time is too short or the speed fluctuates greatly, the base oil filling pressure value will decrease. However, this self-learning method has a long self-learning time and converges slowly when there are many operating conditions of the whole vehicle, which leads to low self-learning efficiency.

[0100] To address the aforementioned problems, this application provides a self-learning method, apparatus, device, and storage medium to solve these issues. The inventive concept of this application can be summarized as follows: Monitoring a vehicle; if a shifting operation is triggered, acquiring parameter information corresponding to the shifting operation; determining the shifting speed difference corresponding to the shifting operation based on the parameter information; determining whether the self-learning of the target operating condition corresponding to the shifting operation has converged based on the shifting speed difference; if not converged, determining the target oil filling pressure value corresponding to the vehicle based on the shifting speed difference; and updating the vehicle's current oil filling pressure based on the target oil filling pressure value.

[0101] In this embodiment of the application, the convergence of the self-learning of the target operating condition is determined based on the shift speed difference. If the self-learning of the target operating condition is not converged, the shift time can be reduced by updating the current fuel pressure of the vehicle.

[0102] For ease of understanding, the self-learning method provided by the embodiments of this application will be described in detail below with reference to the accompanying drawings:

[0103] like Figure 1 The diagram shown is a schematic representation of the overall process of a self-learning method provided in an embodiment of this application, wherein:

[0104] In step 101: The vehicle is monitored. If it is determined that a shifting operation has been triggered, the parameter information corresponding to the shifting operation is obtained.

[0105] In this embodiment of the application, when the user triggers the shifting operation, the parameter information in the vehicle at the time the shifting operation occurs will be obtained.

[0106] In some possible embodiments, the parameter information in the vehicle includes, but is not limited to: current required torque, current transmission temperature, accelerator pedal opening degree, current turbocharger speed, and current engine speed. The current required torque is calculated based on the accelerator pedal opening degree, and the calculation process is the same as in related technologies, so it will not be repeated here. The current transmission sensor, accelerator pedal opening degree, current turbocharger speed, and current engine speed are all directly obtained through their respective sensors.

[0107] In step 102: Determine the shift speed difference corresponding to the shifting operation based on parameter information.

[0108] In this embodiment, considering that the vehicle fills or unfills oil during the shifting process, and that the filling pressure affects the turbocharger speed, the turbocharger speed varies with different filling pressures. Therefore, the shift speed difference can be determined based on the current turbocharger speed in the parameter information, and then the convergence of the vehicle's self-learning can be determined based on this shift speed difference. When the vehicle's self-learning converges, the filling pressure of the target operating condition corresponding to the shifting operation will be at an optimal value. That is, the filling pressure during self-learning convergence will reduce the fluctuation of the vehicle's turbocharger speed, reduce the overall perception of the vehicle, and shorten the shifting time.

[0109] In some possible embodiments, the shift speed difference corresponding to the shifting operation is determined based on parameter information. Specifically, this can be implemented by using the difference between the current engine speed and the current turbine speed as the shift speed difference. The unit of the current engine speed is revolutions per minute (rpm), and the unit of the current turbine speed is also rpm; therefore, they can be directly subtracted, and the difference is the shift speed difference.

[0110] In step 103: Determine whether the self-learning of the target working condition corresponding to the shifting operation has converged based on the shifting speed difference.

[0111] In this embodiment, the shift speed difference can be compared with the calibrated shift speed difference corresponding to the shifting operation to determine whether the self-learning of the target working condition has converged.

[0112] It is understandable that the calibrated shift speed difference is different for different shifting operations. The calibrated shift speed difference can be obtained by looking up a table based on the shifting direction corresponding to the shifting operation.

[0113] For example: Figure 2 As shown, if the shifting operation is from N to D, the shifting direction is 0, and the calibrated shifting speed difference is xx; if the shifting operation is from D to N, the shifting direction is 1, and the calibrated shifting speed difference is yy; if the shifting operation is from N to R, the shifting direction is 2, and the calibrated shifting speed difference is zz; if the shifting operation is from R to N, the shifting direction is 3, and the calibrated shifting speed difference is rr.

[0114] In some possible embodiments, the self-learning of the target working condition corresponding to the shifting operation is determined based on the shifting speed difference. Specifically, it can be implemented as follows: determine whether the shifting speed difference is greater than the calibrated shifting speed difference corresponding to the target working condition; if the shifting speed difference is greater than or equal to the calibrated shifting speed difference, then the self-learning of the target working condition is determined to be converged.

[0115] In this embodiment of the application, when it is determined that the shift speed difference is greater than the calibrated shift speed difference corresponding to the target operating condition, it indicates that the vehicle's oil pressure is sufficient to overcome the vehicle's inertial force. At this time, the clutch reaches the kisspoint, meaning that the clutch begins to gradually engage the gear that needs to be shifted, and the self-learning convergence of the target operating condition is determined. When it is determined that the shift speed difference is less than or equal to the calibrated shift speed difference corresponding to the target operating condition, it is determined that the self-learning of the target operating condition has not converged. Therefore, it is necessary to continue to execute subsequent steps to update the vehicle's current oil pressure, thereby reducing the shift time.

[0116] In step 104: If convergence is not achieved, the target filling pressure value corresponding to the vehicle is determined based on the shift speed difference, and the current filling pressure of the vehicle is updated according to the target filling pressure value.

[0117] In this embodiment of the application, when it is determined that the self-learning of the target working condition has not converged, it is necessary to determine the target oil filling pressure value corresponding to the vehicle and update the current oil filling pressure value so as to shorten the shifting time when shifting gears in the same working condition next time.

[0118] In some possible embodiments, the target fuel filling pressure value corresponding to the vehicle is determined based on the shift speed difference, specifically as follows: Figure 3 The steps shown are as follows:

[0119] In step 301: Determine the target working condition corresponding to the transfer and gear shifting operation based on the parameter information.

[0120] In the embodiments of this application, the calibration values ​​and historical data corresponding to different working conditions are different. Therefore, the target working condition corresponding to the shifting operation is first determined.

[0121] In some possible embodiments, the specific values ​​of the parameter information corresponding to different working conditions are different. Therefore, different parameter information ranges can be set for different working conditions. When determining the working condition, the target working condition corresponding to the shifting operation can be determined based on the range in which the parameter information falls.

[0122] For example, the parameter information includes: current required torque, current transmission temperature, and current engine speed. The parameter range for operating condition 1 includes: required torque range of 150 Nm - 200 Nm, transmission temperature range of 30°C - 40°C, and engine speed range of 2200 rpm - 2500 rpm; the parameter range for operating condition 2 includes: required torque range of 201 Nm - 250 Nm, transmission temperature range of 41°C - 50°C, and engine speed range of 2501 rpm - 3000 rpm.

[0123] If the current required torque is determined to be 175 Nm, the current transmission temperature range is 35℃, and the current engine speed is 2400 rpm, then the target operating condition can be determined as operating condition 1.

[0124] In step 302: Determine the target acceleration factor and cumulative filling pressure corresponding to the target operating condition.

[0125] In this embodiment, an acceleration factor is introduced to accelerate the convergence speed of self-learning. During self-learning, if the base filling pressure is insufficient, it indicates that the filling piston is not yet able to overcome the idle stroke, meaning the clutch is not fully engaged. If a turbine speed difference still exists after multiple self-learning sessions, an acceleration factor needs to be set to prevent the entire self-learning process from becoming too long. This application considers that before convergence, i.e., before the clutch reaches the kiss-point, the values ​​obtained from the table during each learning process are relative values, and each learning session fails to reach the kiss-point (i.e., indicating insufficient filling pressure). Therefore, the previously learned values ​​need to be used as a base and superimposed on the current target base pressure value. Setting a cumulative filling pressure can make the self-learning process faster. It is understood that the methods for determining the target acceleration factor and the cumulative filling pressure value are the same for different operating conditions, as explained below.

[0126] In some possible embodiments, determining the target acceleration factor corresponding to the target operating condition can be specifically implemented as follows: obtaining the historical acceleration factor corresponding to the target operating condition; and accumulating the historical acceleration factors to obtain the target acceleration factor.

[0127] In this embodiment of the application, the historical acceleration factor corresponding to the target operating condition is the target acceleration factor corresponding to the same operating condition as the target operating condition before the target operating condition.

[0128] For example: The target operating condition is operating condition 1, which occurs for the fifth time. The target acceleration factor corresponding to the first occurrence of operating condition 1 is the acceleration factor calibration value, denoted as A. The target acceleration factor corresponding to the second occurrence of operating condition 1 is: acceleration factor calibration value + the target acceleration factor corresponding to the first operating condition 1, i.e., A + A = 2A. The target acceleration factor corresponding to the third occurrence of operating condition 1 is: acceleration factor calibration value + the target acceleration factor corresponding to the first operating condition 1 + the target acceleration factor corresponding to the second operating condition 1 = A + A + 2A = 4A. The target acceleration factor corresponding to the fourth occurrence of operating condition 1 is: acceleration factor calibration value + the target acceleration factor corresponding to the first operating condition 1 + the target acceleration factor corresponding to the second operating condition 1 + the target acceleration factor corresponding to the third operating condition 1 = A + A + 2A + 4A = 8A. The target acceleration factor corresponding to the fifth occurrence of operating condition 1 (the target operating condition) is: acceleration factor calibration value + the target acceleration factor corresponding to the first operating condition 1 + the target acceleration factor corresponding to the second operating condition 1 + the target acceleration factor corresponding to the third operating condition 1 + the target acceleration factor corresponding to the fourth operating condition 1 = ... A+A+2A+4A+8A=16A.

[0129] In some possible embodiments, the target filling pressure baseline value corresponding to the target operating condition is determined, which can be implemented by: obtaining the historical filling pressure value corresponding to the target operating condition; and accumulating the historical filling pressure values ​​to obtain the target filling pressure baseline value.

[0130] In this embodiment of the application, the historical filling pressure value corresponding to the target operating condition is the target filling pressure value corresponding to the same operating condition as the target operating condition before the target operating condition.

[0131] For example: The target operating condition is operating condition 1, and operating condition 1 occurs for the fifth time. The baseline value of the target filling pressure corresponding to the first occurrence of operating condition 1 is the calibrated value of the filling pressure, denoted as B. The baseline value of the target filling pressure corresponding to the second occurrence of operating condition 1 is: the calibrated value of the filling pressure + the baseline value of the target filling pressure corresponding to the first operating condition 1, which is B + B = 2B. The baseline value of the target filling pressure corresponding to the third occurrence of operating condition 1 is: the calibrated value of the filling pressure + the baseline value of the target filling pressure corresponding to the first operating condition 1 + the baseline value of the target filling pressure corresponding to the second operating condition 1 = B + B + 2B = 4B. The fourth occurrence of operating condition 1... The corresponding target acceleration factor is: calibrated oil filling pressure + base value of target oil filling pressure for the first working condition 1 + base value of target oil filling pressure for the second working condition 1 + base value of target oil filling pressure for the third working condition 1 = B + B + 2B + 4B = 8B. The base value of target oil filling pressure for the fifth working condition 1 (target working condition) is: calibrated oil filling pressure + base value of target oil filling pressure for the first working condition 1 + base value of target oil filling pressure for the second working condition 1 + base value of target oil filling pressure for the third working condition 1 + base value of target oil filling pressure for the fourth working condition 1 = B + B + 2B + 4B + 8B = 16B.

[0132] In step 303: the basic value of the filling pressure is obtained based on the current required torque and the current gearbox temperature.

[0133] In this embodiment, to ensure the accuracy of the determined target filling pressure value, different baseline filling pressure values ​​are set for different situations. The baseline filling pressure value can be obtained by looking up a table based on the current required torque and the current gearbox temperature.

[0134] For example: a table constructed by comparing the baseline filling pressure with the current required torque and the current transmission temperature, as shown below. Figure 4 As shown, the current required torque is determined to be 175 Nm, and the current gearbox temperature range is 35℃. Therefore, the basic value of the filling pressure can be determined as P0.

[0135] In step 304: the oil filling ratio is obtained based on the current required torque, the current transmission temperature, and the accelerator pedal opening degree.

[0136] In this embodiment, a filling ratio is set to accelerate the initial self-learning process. For example, if the difference in engine speed during the first gear shift is large, a larger filling ratio is obtained, resulting in a larger filling pressure value. By setting the filling ratio, the filling pressure value can quickly approach the convergence point, thereby shortening the self-learning time.

[0137] In some possible embodiments, the oil filling ratio is determined based on the current required torque, the current transmission temperature, and the accelerator pedal opening degree. Specifically, this can be implemented as follows:Figure 5 The steps shown are as follows:

[0138] In step 501: the target shift time corresponding to the target operating condition is obtained based on the current transmission temperature and accelerator pedal opening degree.

[0139] In this embodiment, the specific implementation method for obtaining the target shift time based on the current gearbox temperature and accelerator pedal opening degree is the same as that in related technologies, and will not be described again here.

[0140] In step 502: the target turbo speed is obtained based on the current required torque and the target shift time.

[0141] In this embodiment of the application, after obtaining the current required torque and the target shift time, the ratio between the current required torque and the target shift time is used as the target turbine speed.

[0142] In step 503: the turbine speed difference is obtained based on the difference between the target turbine speed and the current turbine speed.

[0143] In this embodiment of the application, the turbine speed difference = |target turbine speed - current turbine speed|.

[0144] In step 504: the oil filling ratio is obtained based on the turbine speed difference.

[0145] In this embodiment of the application, a relationship table between turbine speed difference and oil filling ratio is pre-constructed. After obtaining the oil filling ratio, the oil filling ratio can be determined by looking up the table.

[0146] For example, the relationship between turbine speed difference and oil filling ratio is shown in the table below. Figure 6 As shown, if the turbine speed difference is determined to be 100 rpm, then the oil filling ratio can be determined to be M1.

[0147] In step 305: the target filling pressure value is obtained based on the target acceleration factor, cumulative filling pressure, basic filling pressure value, and filling ratio.

[0148] In some possible embodiments, the target filling pressure value is obtained based on the target acceleration factor, the cumulative filling pressure, the base value of the filling pressure, and the filling ratio. Specifically, it can be implemented as follows: a first product value is obtained based on the filling ratio and the base value of the filling pressure; the sum of the first product value, the target acceleration factor, and the cumulative filling pressure is used as the target filling pressure value.

[0149] In this embodiment of the application, Formula 1 can be used to determine the target filling pressure value:

[0150] Target filling pressure value = magnification Base oil filling pressure + target acceleration factor + cumulative oil filling pressure, (Formula 1)

[0151] In this embodiment of the application, after obtaining the target filling pressure, the current filling pressure of the vehicle can be updated according to the target filling pressure to ensure the stability of the vehicle during subsequent shifting and gear shifting, and to shorten the time of shifting and gear shifting.

[0152] In some possible embodiments, if it is determined that the self-learning for the target operating condition has not converged, after determining the target filling pressure value and updating the current filling pressure value, it is determined that the self-learning has been completed once. However, the self-learning for the target operating condition has not ended, and it is necessary to return to step 101. If it is determined that the shifting operation corresponding to the target operating condition has been triggered again during the vehicle monitoring process, then it is determined again according to... Figure 1 The steps in the process determine whether the self-learning for the target working condition has converged. If it has not converged, it needs to be done again based on... Figure 3 The steps in the process update the current oil filling pressure value and continue to return to step 101 until the self-learning converges for the target operating condition.

[0153] In some other possible embodiments, if the self-learning convergence of the target operating condition is determined, then it is necessary to implement, as follows: Figure 7 The steps shown are as follows:

[0154] In step 701: the convergence count of the target working condition is updated based on the historical convergence count to obtain the current convergence count.

[0155] In this embodiment of the application, the historical convergence count is the number of times the self-learning converged under the target operating condition. The current convergence count can be obtained by adding one to the historical convergence count.

[0156] For example, if the current convergence count corresponding to the last self-learning convergence of the target working condition was 8, then for the current target working condition, the historical convergence count was 8 and the current convergence count was 9.

[0157] In step 702: Determine whether the current convergence count is greater than the preset convergence count.

[0158] In step 703: If it is determined that the current convergence count is less than the preset convergence count, then return to the step of monitoring the vehicle.

[0159] In this embodiment, to ensure the accuracy of the target filling pressure value corresponding to the target operating condition, a convergence count is set. When the convergence count exceeds a preset number, the self-learning of the target operating condition is stopped; otherwise, execution continues. Figure 1 The steps are shown.

[0160] In some possible embodiments, considering that some operating conditions may not be triggered during a single driving cycle of the vehicle, there may be operating conditions that have not undergone self-learning during a single driving cycle, i.e., unlearned operating conditions. In order to cover all operating conditions, a method can be adopted... Figure 8 The method shown updates the filling pressure value for unlearned operating conditions, wherein:

[0161] In step 801: Determine whether the driving cycle duration of the vehicle is greater than the preset duration.

[0162] In this embodiment of the application, in order to improve the accuracy of the filling pressure value corresponding to each working condition, when the driving cycle duration is longer than the preset duration, the converged working condition can be used to calculate the filling pressure value of the unlearned working condition.

[0163] The preset duration is set by technicians based on their experience.

[0164] In step 802: If it is determined that the driving cycle duration of the vehicle is greater than the preset duration, then all self-learning convergence conditions from the start time of the vehicle driving cycle to the current time are obtained.

[0165] In step 803: the first working condition and the second working condition are determined from the self-learning converged working conditions.

[0166] In this embodiment of the application, in order to ensure the accuracy of the oil filling pressure value of the determined unlearned working condition, all working conditions that have been self-learned and converged from the start of the driving cycle to the present can be obtained, and sorted from high to low according to the convergence number of each self-learned and converged working condition. The first one in the sequence is selected as the first working condition, and the second one in the sequence is selected as the second working condition.

[0167] For example: The driving conditions that the vehicle has self-learned and converged from the start of the driving cycle to the current time include: Condition 1, Condition 2, Condition 3, Condition 4, Condition 5, and Condition 6. Condition 1 has converged 5 times, Condition 2 7 times, Condition 3 3 times, Condition 4 4 times, Condition 5 3 times, and Condition 6 2 times. Therefore, the sequence obtained by sorting each condition from highest to lowest convergence count is: Condition 2, Condition 1, Condition 4, Condition 2, Condition 5, and Condition 6, where Condition 2 is the first condition and Condition 1 is the second condition.

[0168] In step 804: the target filling pressure value of the unlearned working condition is determined based on the first working condition and the second working condition; the unlearned working condition is the working condition that has not been monitored from the start of the vehicle driving cycle to the current time.

[0169] In the embodiments of this application, after obtaining the first working condition and the second working condition, the current oil filling pressure value of the unlearned working condition can be obtained by using a two-point self-learning method.

[0170] In some possible embodiments, the target filling pressure value for the unlearned operating condition is determined based on the first operating condition and the second operating condition. Specifically, this can be implemented as follows: Figure 9 The steps shown are as follows:

[0171] In step 901: Based on the current required torque and target filling pressure value corresponding to the first working condition, the current required torque and target filling pressure value corresponding to the second working condition, and the calibration required torque and calibration filling pressure value corresponding to the unlearned working condition, the self-learning offset corresponding to the unlearned working condition is obtained.

[0172] The target filling pressure value mentioned above is the filling pressure value corresponding to the self-learning convergence of the first and second working conditions.

[0173] In this embodiment of the application, after obtaining the current required torque and current filling pressure values ​​corresponding to the first and second operating conditions, respectively, the offset of the unlearned operating condition can be obtained using Formula 2, wherein:

[0174] , (Formula 2)

[0175] in, This is the offset for the unlearned operating condition. Unlearned working conditions The corresponding calibrated filling pressure value, The target filling pressure value corresponding to the first operating condition. The target filling pressure value corresponding to the second operating condition. This represents the current required torque for the second operating condition. This represents the current required torque corresponding to the first operating condition. Unlearned working conditions The corresponding rated torque requirement.

[0176] In step 902: the target filling pressure value of the unlearned working condition is obtained based on the self-learning offset and the calibration filling pressure value corresponding to the unlearned working condition.

[0177] In this embodiment of the application, after obtaining the self-learning offset corresponding to the unlearned working condition, the sum of the self-learning offset and the calibrated filling pressure value can be used as the target filling pressure value for the unlearned working condition.

[0178] In step 805: The current filling pressure value of the unlearned working condition is updated using the target filling pressure value of the unlearned working condition.

[0179] In this embodiment of the application, after obtaining the target filling pressure value for the unlearned working condition, the target filling pressure value is used to update the current filling pressure value.

[0180] In some possible embodiments, in order to further improve the accuracy of the target filling pressure value for unlearned operating conditions, after obtaining the target filling pressure value, a pre-set basic filling pressure safety margin value can be added to the target filling pressure value to obtain the final filling pressure value.

[0181] Based on the same inventive concept, after introducing a self-learning method provided by the embodiments of this application, as follows: Figure 10 As shown, the following describes a self-learning device 1000 provided in an embodiment of this application. The device includes:

[0182] The monitoring module 10001 is used to monitor the vehicle. If it is determined that a shifting operation has been triggered, the module obtains the parameter information corresponding to the shifting operation.

[0183] The shift speed difference determination module 10002 is used to determine the shift speed difference corresponding to the shifting operation based on the parameter information.

[0184] The self-learning module 10003 is used to determine whether the self-learning of the target working condition corresponding to the shifting speed difference has converged.

[0185] The oil filling pressure update module 10004 is used to determine the target oil filling pressure value corresponding to the vehicle based on the shift speed difference if convergence is not achieved; and to update the current oil filling pressure of the vehicle according to the target oil filling pressure value.

[0186] In some possible embodiments, the parameter information includes: current required torque, current transmission temperature, accelerator pedal opening degree, and current turbo speed. The oil pressure update module 10004 is specifically used for:

[0187] The target operating condition corresponding to the warehouse transfer and gear shifting operation is determined based on the parameter information.

[0188] Determine the target acceleration factor and cumulative filling pressure corresponding to the target operating condition;

[0189] The basic value of the filling pressure is obtained based on the current required torque and the current gearbox temperature.

[0190] The oil filling ratio is obtained based on the current required torque, the current transmission temperature, and the accelerator pedal opening degree.

[0191] The target filling pressure value is obtained based on the target acceleration factor, the cumulative filling pressure, the base value of the filling pressure, and the filling ratio.

[0192] In some possible embodiments, the oil filling pressure update module 10004 is specifically used for:

[0193] The target shift time corresponding to the target operating condition is obtained based on the current transmission temperature and the accelerator pedal opening degree.

[0194] The target turbo speed is obtained based on the current required torque and the target shift time.

[0195] The turbine speed difference is obtained based on the difference between the target turbine speed and the current turbine speed;

[0196] The oil filling ratio is obtained based on the turbine speed difference.

[0197] In some possible embodiments, the oil filling pressure update module 10004 is specifically used for:

[0198] The first product value is obtained based on the oil filling ratio and the basic value of the oil filling pressure;

[0199] The sum of the first product value, the target acceleration factor, and the cumulative filling pressure is taken as the target filling pressure value.

[0200] In some possible embodiments, the self-learning module 10003 is specifically used for:

[0201] Determine whether the shift speed difference is greater than the calibrated shift speed difference corresponding to the target operating condition;

[0202] If it is determined that the shift speed difference is greater than or equal to the calibrated shift speed difference, then the self-learning convergence of the target operating condition is determined.

[0203] In some possible embodiments, the self-learning module 10003 is further configured to:

[0204] The convergence count for the target operating condition is updated based on the historical convergence count to obtain the current convergence count.

[0205] In some possible embodiments, the self-learning module 10003 is further configured to:

[0206] Determine whether the current convergence count is greater than the preset convergence count;

[0207] If it is determined that the current convergence count is less than the preset convergence count, then return to the step of monitoring the vehicle.

[0208] In some possible embodiments, the self-learning module 10003 is further configured to:

[0209] Determine whether the driving cycle duration of the vehicle is greater than a preset duration;

[0210] If it is determined that the driving cycle duration of the vehicle is greater than the preset duration, then all self-learning converged working conditions from the start time of the vehicle driving cycle to the current time are obtained.

[0211] The first and second working conditions are determined from the self-learning convergence working conditions;

[0212] The target filling pressure value for the unlearned operating condition is determined based on the first operating condition and the second operating condition; the unlearned operating condition is the operating condition that has not been monitored from the start of the vehicle driving cycle to the current time.

[0213] The target filling pressure value of the unlearned working condition is used to update the filling pressure value of the unlearned working condition.

[0214] In some possible embodiments, the self-learning module 10003 is further configured to:

[0215] Based on the obtained current required torque and target filling pressure value corresponding to the first working condition, the current required torque and target filling pressure value corresponding to the second working condition, and the calibration required torque and calibration filling pressure value corresponding to the unlearned working condition, the self-learning offset corresponding to the unlearned working condition is obtained.

[0216] The current filling pressure value of the unlearned working condition is obtained based on the self-learning offset and the calibration filling pressure value corresponding to the unlearned working condition.

[0217] Corresponding to the above embodiments, this application also provides an electronic device. Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. The electronic device 1100 may include a processor 1101, a memory 1102, and a communication unit 1103. These components communicate through one or more buses. Those skilled in the art will understand that the structure of the electronic device shown in the figure does not constitute a limitation on the embodiment of the present invention. It may be a bus topology or a star topology, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0218] The communication unit 1103 is used to establish a communication channel, enabling the electronic device to communicate with other devices. It receives user data from other devices or sends user data to other devices.

[0219] The processor 1101 serves as the control center of the electronic device, connecting various parts of the device via interfaces and lines. It executes software programs and / or modules stored in the memory 1102, and calls data stored in the memory to perform various functions and / or process data. The processor can be composed of integrated circuits (ICs), such as a single packaged IC or multiple packaged ICs with the same or different functions connected together. For example, the processor 1101 may consist only of a central processing unit (CPU). In this embodiment, the CPU may have a single processing core or include multiple processing cores.

[0220] The memory 1102 is used to store the execution instructions of the processor 1101. The memory 1102 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), power-off erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0221] When the execution instructions in memory 1102 are executed by processor 1101, the electronic device 1100 is able to perform operations. Figure 1 Some or all of the steps in the illustrated embodiments.

[0222] In a specific implementation, the present invention also provides a computer storage medium, wherein the computer storage medium may store a program, which, when executed, may include some or all of the steps of the self-learning method provided by the present invention in various embodiments. The storage medium may be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0223] Those skilled in the art will clearly understand that the techniques in the embodiments of the present invention can be implemented using software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solutions in the embodiments of the present invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or certain parts of the embodiments of the present invention.

[0224] The same or similar parts between the various embodiments in this specification can be referred to mutually. In particular, the device embodiments and terminal embodiments are basically similar to the method embodiments, so the description is relatively simple, and the relevant parts can be referred to the description in the method embodiments.

Claims

1. A self-learning method, characterized in that, Applied to vehicles, the method includes: The vehicle is monitored, and if it is determined that a shifting operation has been triggered, the parameter information corresponding to the shifting operation is obtained. The shift speed difference corresponding to the shifting operation is determined based on the parameter information. Whether the self-learning of the target working condition corresponding to the shifting operation has converged is determined based on the shifting speed difference. If convergence is not achieved, the target filling pressure value corresponding to the vehicle is determined based on the shift speed difference; and the current filling pressure of the vehicle is updated according to the target filling pressure value. The parameter information includes: current required torque, current transmission temperature, accelerator pedal opening degree, and current turbo speed. Determining the target fuel injection pressure value corresponding to the vehicle based on the shift speed difference includes: The target operating condition corresponding to the warehouse transfer and gear shifting operation is determined based on the parameter information. Determine the target acceleration factor and cumulative filling pressure corresponding to the target operating condition; The basic value of the filling pressure is obtained based on the current required torque and the current gearbox temperature. The oil filling ratio is obtained based on the current required torque, the current transmission temperature, and the accelerator pedal opening degree. The target filling pressure value is obtained based on the target acceleration factor, the cumulative filling pressure, the base value of the filling pressure, and the filling ratio.

2. The method according to claim 1, characterized in that, The process of obtaining the fill ratio based on the current required torque, the current transmission temperature, and the accelerator pedal opening degree includes: The target shift time corresponding to the target operating condition is obtained based on the current transmission temperature and the accelerator pedal opening degree. The target turbo speed is obtained based on the current required torque and the target shift time. The turbine speed difference is obtained based on the difference between the target turbine speed and the current turbine speed; The oil filling ratio is obtained based on the turbine speed difference.

3. The method according to claim 1, characterized in that, The step of obtaining the target filling pressure value based on the target acceleration factor, the cumulative filling pressure, the base value of the filling pressure, and the filling ratio includes: The first product value is obtained based on the oil filling ratio and the basic value of the oil filling pressure; The sum of the first product value, the target acceleration factor, and the cumulative filling pressure is taken as the target filling pressure value.

4. The method according to claim 1, characterized in that, The step of determining whether the self-learning of the target working condition corresponding to the shifting operation based on the shifting speed difference has converged includes: Determine whether the shift speed difference is greater than the calibrated shift speed difference corresponding to the target operating condition; If it is determined that the shift speed difference is greater than or equal to the calibrated shift speed difference, then the self-learning convergence of the target operating condition is determined.

5. The method according to claim 4, characterized in that, After determining the self-learning convergence of the target working condition, the method further includes: The convergence count for the target operating condition is updated based on the historical convergence count to obtain the current convergence count.

6. The method according to claim 5, characterized in that, The method further includes: Determine whether the current convergence count is greater than the preset convergence count; If it is determined that the current convergence count is less than the preset convergence count, then return to the step of monitoring the vehicle.

7. The method according to claim 6, characterized in that, The method further includes: Determine whether the driving cycle duration of the vehicle is greater than a preset duration; If it is determined that the driving cycle duration of the vehicle is greater than the preset duration, then all self-learning converged working conditions from the start time of the vehicle driving cycle to the current time are obtained. The first and second working conditions are determined from the self-learning convergence working conditions; The target filling pressure value for the unlearned operating condition is determined based on the first operating condition and the second operating condition; the unlearned operating condition is the operating condition that has not been monitored from the start of the vehicle driving cycle to the current time. The target filling pressure value of the unlearned working condition is used to update the filling pressure value of the unlearned working condition.

8. The method according to claim 7, characterized in that, The determination of the target filling pressure value for the unlearned operating condition based on the first operating condition and the second operating condition includes: Based on the obtained current required torque and target filling pressure value corresponding to the first working condition, the current required torque and target filling pressure value corresponding to the second working condition, and the calibration required torque and calibration filling pressure value corresponding to the unlearned working condition, the self-learning offset corresponding to the unlearned working condition is obtained. The current filling pressure value of the unlearned working condition is obtained based on the self-learning offset and the calibration filling pressure value corresponding to the unlearned working condition.

9. A self-learning device, characterized in that, Applied to vehicles, the device includes: The monitoring module is used to monitor the vehicle. If it is determined that a shifting operation has been triggered, the module obtains the parameter information corresponding to the shifting operation. The shift speed difference determination module is used to determine the shift speed difference corresponding to the shift operation based on the parameter information. The self-learning module is used to determine whether the self-learning of the target working condition corresponding to the shifting operation has converged based on the shifting speed difference. The oil filling pressure update module is used to determine the target oil filling pressure value corresponding to the vehicle based on the shift speed difference if convergence is not achieved; and to update the current oil filling pressure of the vehicle according to the target oil filling pressure value. The parameter information includes: current required torque, current transmission temperature, accelerator pedal opening degree, and current turbo speed. The oil pressure update module is specifically used for: The target operating condition corresponding to the warehouse transfer and gear shifting operation is determined based on the parameter information. Determine the target acceleration factor and cumulative filling pressure corresponding to the target operating condition; The basic value of the filling pressure is obtained based on the current required torque and the current gearbox temperature. The oil filling ratio is obtained based on the current required torque, the current transmission temperature, and the accelerator pedal opening degree. The target filling pressure value is obtained based on the target acceleration factor, the cumulative filling pressure, the base value of the filling pressure, and the filling ratio.

10. An electronic device, characterized in that, It includes a memory for storing computer program instructions and a processor for executing the program instructions, wherein when the computer program instructions are executed by the processor, the electronic device is triggered to perform the method of any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method according to any one of claims 1-8.

Images