Self-learning method and device of automatic transmission, vehicle and storage medium

Abstract

The invention relates to the technical field of transmission device control, in particular to a self-learning method and device of an automatic transmission, a vehicle and a storage medium. The method comprises the steps that learnable signals of the automatic transmission are collected, and then whether the driving style of a driver meets a first preset change condition or not is judged; and when the driving style meets the first preset change condition, the automatic transmission is controlled to enter a self-learning mode, the preset number of times serves as the self-learning number of times, and after the use number of times of the clutch reaches the self-learning number of times, a learning strategy is executed according to the learnable signal to conduct self-learning. Therefore, the problems that the automatic transmission logic is difficult to adjust quickly and the driving requirement of a user is difficult to meet due to the fact that the automatic transmission self-learning triggering threshold in the related technology is gradually increased along with the increase of the use frequency of the clutch and self-learning can be started only after the clutch accumulates certain use frequency when the driving scene dynamically changes are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of transmission control, in particular to a self-learning method and device of an automatic transmission, a vehicle and a storage medium. BACKGROUND

[0002] With the development of vehicle automation control technology, automatic transmission emerges as the times require. It is the core component responsible for power scheduling in the vehicle power system, replacing manual transmission manual shifting operation, and automatically matching the engine speed, torque and wheel travel demand through the built-in control unit and transmission mechanism.

[0003] In related technologies, after the automatic transmission is shipped, it will quickly adapt to the operation habits of the first driver through two self-learning, and subsequent self-learning adaptation will be triggered gradually according to the increase of the use frequency of the clutch, but the trigger threshold will gradually increase with the increase of the use frequency of the clutch - only hundreds of times of clutch use are required in the early stage, and thousands of times of clutch use are required in the later stage.

[0004] However, in related technologies, since the trigger threshold of the self-learning of the automatic transmission gradually increases with the increase of the use frequency of the clutch, when the driving scene dynamically changes, the self-learning can be started only after the clutch accumulates a certain use frequency, which leads to the difficulty in quickly adjusting the logic of the automatic transmission, the driving experience of gear shifting jerk and poor power connection, and the difficulty in meeting the driving needs of users, which needs to be solved urgently. SUMMARY

[0005] The present application provides a self-learning method and device of an automatic transmission, a vehicle and a storage medium to solve the problem that the trigger threshold of the self-learning of the automatic transmission in related technologies gradually increases with the increase of the use frequency of the clutch, and the self-learning can be started only after the clutch accumulates a certain use frequency when the driving scene dynamically changes, which leads to the difficulty in quickly adjusting the logic of the automatic transmission, the driving experience of gear shifting jerk and poor power connection, and the difficulty in meeting the driving needs of users.

[0006] The first aspect embodiment of the present application provides a self-learning method of an automatic transmission, comprising the following steps: collecting learnable signals of the automatic transmission; determining whether the driving style of the driver meets a first preset change condition according to the learnable signals; when the driving style meets the first preset change condition, controlling the automatic transmission to enter a self-learning mode, taking a preset number of times as a self-learning number of times, and performing a learning strategy according to the learnable signals to perform self-learning after the use frequency of the clutch reaches the self-learning number of times.

[0007] According to the above technical means, the embodiments of the present application provide comprehensive data support for driving style judgment by collecting multi-dimensional learnable signals, ensure accurate identification of driving style changes, and then trigger the self-learning mode when the driving style meets the first certain change condition, and take a certain number as the threshold of the self-learning number, effectively shorten the start-up period of self-learning after the driving style changes, and at the same time, execute the learning strategy based on the learnable signal to ensure the pertinence and accuracy of the self-learning process, so that the automatic transmission can quickly adjust the control parameters such as gear shifting logic and power engagement force, accurately meet the driving style requirements, and significantly improve the gear shifting smoothness, power response timeliness and driving experience consistency.

[0008] Optionally, in an embodiment of the present application, it further includes: judging whether the current driving environment meets the second preset change condition according to the learnable signal; when the current driving environment meets the second preset change condition, controlling the automatic transmission to enter the self-learning mode, determining the self-learning number by half of the current self-learning number, and performing self-learning according to the learnable signal after the use number of the clutch reaches the self-learning number.

[0009] According to the above technical means, the embodiments of the present application trigger the self-learning mode when the driving environment changes, and determine the threshold of the self-learning number by half of the current self-learning number, which reduces the start-up difficulty and significantly shortens the response period of environment adaptation, and at the same time, by performing self-learning according to the learnable signal, the pertinence of parameter adjustment is ensured, so that the transmission can quickly adapt to the power demand difference in different environments, and significantly improve the driving smoothness and power output stability in complex scenarios.

[0010] Optionally, in an embodiment of the present application, the determination of the self-learning number by half of the current self-learning number includes: judging whether the half value is greater than or equal to the preset number; when it is greater than or equal to the preset number, taking the half value as the self-learning number; and when it is less than the preset number, taking the preset number as the self-learning number.

[0011] According to the above technical means, the embodiments of the present application determine the self-learning number of the driving environment change by the half value and a certain number, which not only continues the core advantage of fast adaptation in the driving environment change scenario, but also makes up for the system operation risk that may be caused by simply halving the threshold, and further improves the adaptation accuracy, operation stability and actual application reliability of the self-learning function of the automatic transmission.

[0012] Optionally, in an embodiment of the present application, it further includes: detecting the gear shifting impact degree within a preset time length; in the case that the gear shifting impact degree meets the preset learning failure condition, rolling back at least one target parameter with a preset control strategy, and recording the failure sample data to optimize the learning strategy.

[0013] According to the above technical means, the embodiment of the application can quickly avoid the driving frustration caused by the increase of the gear shift impact degree by detecting the gear shift impact degree, judging whether a certain learning failure condition is met, and then rolling back the target parameter when the certain failure condition is met, thereby guaranteeing the driving smoothness and safety, avoiding the continuous negative impact of invalid learning on the driving experience, recording the failure sample data, continuously improving the learning strategy, reducing the learning failure probability in the same scene, and continuously improving the adaptation accuracy and reliability of the self-learning function.

[0014] Optionally, in an embodiment of the application, the collecting the learnable signal of the automatic transmission comprises: collecting a speed signal of an engine; collecting a throttle opening degree signal of an accelerator pedal; collecting a torque signal of the engine; collecting a vehicle speed signal of the vehicle; collecting an altitude signal of the environment; collecting a brake signal of a brake pedal; and generating the learnable signal according to the speed signal, the throttle opening degree signal, the torque signal, the vehicle speed signal, the altitude signal and the brake signal.

[0015] According to the above technical means, the embodiment of the application can generate a learnable signal by integrating multi-dimensional key signals, on the one hand, to ensure the accurate characterization of the driving style, the driving environment and the vehicle operating state, to provide a reliable data basis for the judgment of the driving style change, to avoid misjudgment or omission caused by one-sided signals, and on the other hand, to provide rich adjustment basis for the self-learning strategy, so that the transmission can accurately match the actual driving demand when performing self-learning, thereby significantly improving the adaptability and reliability of the self-learning result, and further optimizing the driving experience such as gear shift smoothness and power connection fluency.

[0016] The second aspect embodiment of the application provides a self-learning device of an automatic transmission, comprising: a collection module configured to collect a learnable signal of the automatic transmission; a first judgment module configured to judge whether a driving style of a driver meets a first preset change condition according to the learnable signal; and a first learning module configured to control the automatic transmission to enter a self-learning mode when the driving style meets the first preset change condition, to set a preset number of times as a self-learning number of times, and to execute a learning strategy according to the learnable signal to perform self-learning after a number of times of use of a clutch reaches the self-learning number of times.

[0017] According to the above technical means, the embodiments of the present application provide comprehensive data support for driving style judgment by collecting multi-dimensional learnable signals, ensure accurate identification of driving style changes, and then trigger the self-learning mode when the driving style meets the first certain change condition, and take a certain number as the threshold of the self-learning number, effectively shorten the start-up period of self-learning after the driving style changes, and at the same time, execute the learning strategy based on the learnable signal to ensure the pertinence and accuracy of the self-learning process, so that the automatic transmission can quickly adjust the shift logic, power engagement strength and other control parameters, accurately meet the driving style requirements, and significantly improve the shift smoothness, power response timeliness and driving experience consistency.

[0018] Optionally, in an embodiment of the present application, it further includes: a second judgment module for judging whether the current driving environment meets a second preset change condition according to the learnable signal; and a second learning module for controlling the automatic transmission to enter the self-learning mode when the current driving environment meets the second preset change condition, determining the self-learning number by half of the current self-learning number, so as to perform self-learning according to the learnable signal after the use number of the clutch reaches the self-learning number.

[0019] According to the above technical means, the embodiments of the present application trigger the self-learning mode when the driving environment changes, and determine the threshold of the self-learning number by half of the current self-learning number, which reduces the start-up difficulty and significantly shortens the response period of environment adaptation, and at the same time, performs self-learning according to the learnable signal to ensure the pertinence of parameter adjustment, so that the transmission can quickly adapt to the power demand difference in different environments, and significantly improve the driving smoothness and power output stability in complex scenarios.

[0020] Optionally, in an embodiment of the present application, the second learning module includes: a judgment unit for judging whether the half value is greater than or equal to the preset number; a first determination unit for taking the half value as the self-learning number when it is greater than or equal to the preset number; and a second determination unit for taking the preset number as the self-learning number when it is less than the preset number.

[0021] According to the above technical means, the embodiments of the present application determine the self-learning number of the driving environment change by the half value and a certain number, which not only continues the core advantage of fast adaptation in the driving environment change scenario, but also makes up for the system operation risk that may be caused by simply halving the threshold, and further improves the adaptation accuracy, operation stability and actual application reliability of the self-learning function of the automatic transmission.

[0022] Optionally, in an embodiment of the present application, further comprising: a detection module configured to detect a gear shift shock degree within a preset time period; and an optimization module configured to, in a case where the gear shift shock degree meets a preset learning failure condition, roll back at least one target parameter according to a preset control strategy, and record failure sample data, so as to optimize the learning strategy.

[0023] According to the above technical means, by detecting the gear shift shock degree, it is determined whether a certain learning failure condition is met, and then the target parameter is rolled back when the certain failure condition is met, so that the driving jerk caused by the increase of the gear shift shock degree can be quickly avoided, the driving smoothness and safety are ensured, the continuous negative impact of invalid learning on the driving experience is avoided, and the failure sample data is recorded, so that the learning strategy can be continuously improved, the learning failure probability in the same type of scene is reduced, and the adaptation accuracy and reliability of the self-learning function are continuously improved.

[0024] Optionally, in an embodiment of the present application, the collection module comprises: a first collection unit configured to collect a speed signal of an engine; a second collection unit configured to collect a throttle opening degree signal of an accelerator pedal; a third collection unit configured to collect a torque signal of the engine; a fourth collection unit configured to collect a vehicle speed signal of a vehicle; a fifth collection unit configured to collect an altitude signal of an environment; a sixth collection unit configured to collect a brake signal of a brake pedal; and a generation unit configured to generate the learnable signal according to the speed signal, the throttle opening degree signal, the torque signal, the vehicle speed signal, the altitude signal, and the brake signal.

[0025] According to the above technical means, by integrating the multi-dimensional key signals to generate the learnable signal, on the one hand, the driving style, the driving environment, and the vehicle running state are accurately described, and a reliable data basis is provided for the judgment of the driving style change, so as to avoid misjudgment or omission caused by one-sided signals, and on the other hand, the self-learning strategy can be provided with rich adjustment basis, so that the transmission can accurately match the actual driving demand when performing self-learning, the adaptation and reliability of the self-learning result are significantly improved, and the driving experience such as gear shift smoothness and power connection fluency is optimized.

[0026] An embodiment of the third aspect of the present application provides a vehicle, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the program to implement the self-learning method of the automatic transmission as described in the above embodiments.

[0027] An embodiment of the fourth aspect of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the self-learning method of the automatic transmission as described above.

[0028] The fifth aspect embodiment of the present application provides a computer program product comprising a computer program which, when executed, implements the self-learning method of the automatic transmission as described above.

[0029] The embodiments of the present application provide comprehensive data support for driving style judgment by collecting multi-dimensional learnable signals, ensure accurate identification of driving style changes, and then trigger the self-learning mode when the driving style meets the first certain change condition, and take a certain number as the threshold of the self-learning number, effectively shorten the start-up period of self-learning after the driving style changes, and at the same time, execute the learning strategy based on the learnable signal to ensure the pertinence and accuracy of the self-learning process, so that the automatic transmission can quickly adjust the shift logic, power engagement strength and other control parameters, accurately meet the driving style requirements, and significantly improve the shift smoothness, power response timeliness and driving experience consistency. Therefore, the problem that the self-learning trigger threshold of the automatic transmission of the related art gradually increases with the increase of the use number of the clutch, and the self-learning needs to wait for the clutch to accumulate a certain use number to start when the driving scene dynamically changes, resulting in difficulty in quickly adjusting the automatic transmission logic, causing driving experience of gear shift jerk and poor power engagement, and difficulty in meeting the driving requirements of users, is solved.

[0030] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0031] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, including the accompanying drawings, in which: Figure 1 A flowchart of a self-learning method of an automatic transmission according to an embodiment of the present application is provided. Figure 2 A principle flowchart of a self-learning method of an automatic transmission according to an embodiment of the present application is provided. Figure 3 A block schematic diagram of a self-learning device of an automatic transmission according to an embodiment of the present application is provided. Figure 4 A structural schematic diagram of a vehicle according to an embodiment of the present application is provided.

[0032] Reference Signs: 30 - self-learning device of an automatic transmission; 100 - acquisition module, 200 - first judgment module, 300 - first learning module; 401 - memory, 402 - processor, 403 - communication interface. DETAILED DESCRIPTION

[0033] Embodiments of the present application are described below in detail, examples of which are shown in the drawings, wherein the same or similar notations represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are intended to explain the present application, and cannot be understood as a limitation of the present application.

[0034] The self-learning method, device, vehicle and storage medium of the automatic transmission of the embodiments of the present application are described below with reference to the accompanying drawings. The automatic transmission self-learning trigger threshold of the related art mentioned in the background art gradually increases with the increase of the number of uses of the clutch. When the driving scene changes dynamically, the self-learning needs to be started after the clutch accumulates a certain number of uses, which leads to the problem that it is difficult to quickly adjust the automatic transmission logic, resulting in a driving experience of gear shift jerk, poor power connection, and difficulty in meeting the driving needs of users. The present application provides a self-learning method of an automatic transmission. In the method, multi-dimensional learnable signals are collected to provide comprehensive data support for driving style judgment, ensuring accurate identification of driving style changes. Then, when it is determined that the driving style meets the first certain change condition, the self-learning mode is triggered, and a certain number of times are used as the threshold of the self-learning number, effectively shortening the start period of self-learning after the driving style changes. At the same time, learning strategies are executed based on learnable signals to ensure the pertinence and accuracy of the self-learning process, so that the automatic transmission can quickly adjust the control parameters such as gear shift logic and power connection strength, accurately meet the driving style requirements, and significantly improve the gear shift smoothness, power response timeliness and driving experience consistency. Thus, the problem that the automatic transmission self-learning trigger threshold of the related art gradually increases with the increase of the number of uses of the clutch, and the self-learning needs to be started after the clutch accumulates a certain number of uses when the driving scene changes dynamically, leading to the problem that it is difficult to quickly adjust the automatic transmission logic, resulting in a driving experience of gear shift jerk, poor power connection, and difficulty in meeting the driving needs of users, is solved.

[0035] Specifically, Figure 1 A flowchart of a self-learning method of an automatic transmission according to an embodiment of the present application is provided.

[0036] As Figure 1 shown, the self-learning method of the automatic transmission includes the following steps: In step S101, learnable signals of the automatic transmission are collected.

[0037] In the embodiment of the present application, the automatic transmission can be understood as a mechanical and electronic integrated device in the power transmission system of the automobile, which is used to replace manual gear shifting operation, and through the built-in transmission control unit, gear set, clutch and other transmission mechanisms and various signal acquisition sensors, the engine operating parameters, driver operation instructions and vehicle driving state signals are received in real time, and the transmission ratio is automatically adjusted according to the preset control logic and self-learning algorithm to realize the accurate matching of the engine power and the wheel driving demand.

[0038] The embodiment of the present application will be described in detail below.

[0039] Specifically, in one embodiment of the present application, the learnable signal of the automatic transmission is collected, including: collecting the speed signal of the engine; collecting the throttle opening degree signal of the accelerator pedal; collecting the torque signal of the engine; collecting the vehicle speed signal of the vehicle; collecting the altitude signal of the environment; collecting the brake signal of the brake pedal; and generating the learnable signal according to the speed signal, the throttle opening degree signal, the torque signal, the vehicle speed signal, the altitude signal and the brake signal.

[0040] In the embodiment of the present application, the speed signal can be understood as an electrical signal collected by an engine speed sensor, which represents the number of reciprocating movements of the engine piston per minute, and is used to reflect the running frequency and power output basic state of the engine, and is directly related to the working load and power output potential of the engine, which is not limited in the present application.

[0041] The throttle opening degree signal can be understood as an electrical signal collected by an accelerator pedal position sensor, which represents the amplitude, rate and duration of the accelerator pedal being stepped on, and is used to reflect the power demand intention of the driver (such as aggressive acceleration or gentle driving), which is not limited in the present application.

[0042] The torque signal can be understood as an electrical signal calculated by an engine control unit or collected by a torque sensor, which represents the size of the engine output traction force, and is used to reflect the actual power output capability of the engine, which is related to the driving scenes such as starting, climbing and accelerating, which is not limited in the present application.

[0043] The vehicle speed signal can be understood as an electrical signal collected by a vehicle wheel speed sensor or a vehicle speed sensor, which represents the driving distance of the vehicle per unit time, and is used to reflect the actual driving state of the vehicle (such as start-stop, constant speed cruising, acceleration driving, etc.), which is not limited in the present application.

[0044] The altitude signal can be understood as a signal collected by an altitude sensor, a GPS module or an air pressure sensor, which represents the altitude of the geographical position where the vehicle is located, and is used to reflect the environmental parameters such as air pressure and air density of the external driving environment (high altitude environment will affect the engine power output efficiency), which is not limited in the present application.

[0045] The brake signal can be understood as an electrical signal collected by the brake pedal position sensor, representing the amplitude, frequency and triggering timing of the brake pedal being stepped on, for reflecting the driver's braking operation habit and safety control intention, which is not specifically limited in the present application.

[0046] The learnable signal can be understood as a comprehensive feature signal formed after multi-source data fusion and integration processing based on the collected speed signal, throttle opening signal, torque signal, vehicle speed signal, altitude signal and brake signal.

[0047] In actual execution, the engine speed signal, accelerator pedal throttle opening signal, engine torque signal, vehicle speed signal, environmental altitude signal and brake pedal brake signal can be collected in the embodiments of the present application to cover the driver's operation behavior (throttle and brake operation), power system output state (speed and torque), vehicle driving state (vehicle speed) and external environmental characteristics (altitude), and then through integration and data fusion processing of multi-source heterogeneous signals, the learnable signal capable of comprehensively and accurately depicting the actual driving scene and operation habit is generated.

[0048] The embodiments of the present application generate learnable signals by integrating multi-dimensional key signals, which on the one hand ensures accurate depiction of driving style, driving environment and vehicle operating state, provides a reliable data basis for judgment of driving style change, avoids misjudgment or missed judgment due to one-sided signals, and on the other hand can provide rich adjustment basis for self-learning strategy, so that the transmission can accurately match the actual driving demand when executing self-learning, significantly improving the adaptability and reliability of the self-learning result, and further optimizing the shift smoothness, power connection fluency and other driving experiences.

[0049] In step S102, it is judged according to the learnable signal whether the driving style of the driver meets a first certain change condition.

[0050] In the embodiments of the present application, the driving style can be understood as a set of driving behavior characteristics formed by the driver in the long-term driving process, which has stability and consistency, and can be reflected by the parameters in the learnable signal representing the driver's operation intention and power demand, which can include but is not limited to the pedal stepping amplitude, rate and duration characteristics of the accelerator pedal, the triggering frequency, force and timing characteristics of the brake pedal, and the demand rhythm of the vehicle power response, etc., which is not specifically limited in the present application.

[0051] In addition, the first certain change condition can be understood as a quantitative judgment standard preset to determine whether the current driving style has changed significantly compared with the reference driving style, which can be a difference threshold between the reference driving style characteristic model constructed based on historical learnable signals and the current driving style characteristic parameters, which is not specifically limited in the present application.

[0052] In actual implementation, the embodiment of the present application can first establish and store the baseline driving style feature model of the driver (such as the quantitative range of core features such as the throttle operation amplitude and speed, the brake frequency and force, and the power demand response rhythm) according to the historical learnable signals, and then obtain the feature parameters of the current driving style through feature extraction and quantitative processing of the current learnable signals, and perform multi-dimensional comparison and analysis of the current feature parameters and the baseline driving style feature model, calculate the difference degree (such as the throttle opening change rate difference, the brake trigger frequency deviation, etc.) of the core feature dimensions, and when the difference degree reaches a certain difference degree threshold (that is, the determination standard set by the first certain change condition, and the instantaneous deviation interference caused by accidental operation has been excluded), it is determined that the driving style meets the first certain change condition, otherwise it is determined that it does not meet.

[0053] In step S103, when the driving style meets the first certain change condition, the automatic transmission is controlled to enter the self-learning mode, and a certain number of times are taken as the self-learning number of times, so that after the number of uses of the clutch reaches the self-learning number of times, the learning strategy is executed according to the learnable signals to perform self-learning.

[0054] In the embodiment of the present application, the self-learning mode can be understood as the working mode of the automatic transmission switched after the driving style meets the first certain change condition or the driving environment meets the second certain change condition. This mode discards the design of increasing the trigger threshold with the increase of the learning number of times in related self-learning, and takes a fixed number of times as the self-learning start determination basis. By calling the real-time collected learnable signals, the core control parameters such as shift timing, power connection force, and transmission ratio matching logic are adjusted to quickly adapt to the new driving style or new driving environment.

[0055] The certain number of times can be understood as a pre-set fixed quantitative value for triggering self-learning, which does not change with factors such as the historical self-learning number of times of the automatic transmission and the cumulative total amount of clutch use. For example, 50 times, which is not limited in the present application.

[0056] The self-learning number of times can be understood as a threshold of the cumulative number of clutch uses required to start the self-learning process after the automatic transmission enters the self-learning mode, which is not limited in the present application.

[0057] The learning strategy can be understood as a targeted parameter adjustment scheme based on the learnable signals, which can include but is not limited to the calculation, optimization and update rules of core control parameters such as shift timing, power connection force, and transmission ratio matching logic, which is not limited in the present application.

[0058] In actual execution, after confirming that the current driving style meets the first certain change condition compared with the benchmark driving style, the embodiment of the application automatically triggers the automatic transmission to enter the self-learning mode, takes a certain number as the threshold of the self-learning number, and counts the clutch usage number in real time through the transmission control unit; when the clutch usage number accumulates to the threshold of the self-learning number, the learnable signal currently collected including the driving operation feature, the vehicle running state and the environmental parameter is called to execute the learning strategy for self-learning.

[0059] The embodiment of the application effectively shortens the start period of self-learning after the driving style changes by triggering the self-learning mode when the driving style changes and taking a certain number as the threshold of the self-learning number, and ensures the pertinence and accuracy of the self-learning process by executing the learning strategy based on the learnable signal, so that the automatic transmission can quickly adjust the control parameters such as the shift logic and the power engagement strength, accurately meet the driving style requirements, and further significantly improve the shift smoothness, power response timeliness and driving experience consistency.

[0060] Further, in an embodiment of the application, it further includes: judging whether the current driving environment meets the second certain change condition according to the learnable signal; when the current driving environment meets the second certain change condition, controlling the automatic transmission to enter the self-learning mode, determining the self-learning number from the half value of the current self-learning number, so as to perform self-learning according to the learnable signal when the clutch usage number reaches the self-learning number.

[0061] In the embodiment of the application, the second certain change condition can be understood as a quantitative determination standard preset by judging whether the current driving environment changes significantly compared with the benchmark driving environment, which can be a difference threshold between the benchmark driving environment feature model constructed based on the historical learnable signal and the current driving environment feature parameter, and the application does not make specific limitation.

[0062] In actual execution, the embodiment of the application can establish and store the benchmark driving environment feature model according to the historical learnable signal, and then obtain the feature parameters (such as altitude, road condition, slope, etc.) of the current driving environment by performing feature extraction and quantitative processing on the current learnable signal, and compare the current feature parameters with the benchmark driving environment feature model to determine whether the second certain change condition (i.e. the quantitative determination standard of substantial change of the environment) is met, when the driving environment meets the second certain change condition, the automatic transmission is controlled to enter the self-learning mode, the threshold of the self-learning number is determined from the half value of the current self-learning number, and the clutch usage number is counted in real time through the transmission control unit, so that when the clutch usage number accumulates to the threshold of the self-learning number, self-learning is performed according to the learnable signal.

[0063] The embodiment of the application reduces the starting difficulty, greatly shortens the response cycle of environment adaptation, and ensures the pertinence of parameter adjustment by self-learning according to the learnable signal, so that the transmission can quickly adapt to the power demand difference in different environments, and significantly improves the driving smoothness and power output stability in complex scenarios.

[0064] Specifically, in one embodiment of the application, determining the self-learning number from the half value of the current self-learning number includes: determining whether the half value is greater than or equal to a certain number; when the half value is greater than or equal to the certain number, the half value is taken as the self-learning number; and when the half value is less than the certain number, the certain number is taken as the self-learning number.

[0065] In actual execution, the embodiment of the application first obtains the half value of the current self-learning number by calculation, and then quantitatively compares the half value with the certain number. When the half value is greater than or equal to the certain number, the half value is determined as the threshold of the self-learning number, so as to ensure the quick adaptation response in the environment change scenario. When the half value is less than the certain number, the certain number is determined as the threshold of the self-learning number, so as to avoid frequent starting of the self-learning mode due to too low triggering threshold. For example, when the calculated half value is 48 times and the certain number is 50 times, 48 < 50, and 50 times is the self-learning number.

[0066] The embodiment of the application determines the self-learning number of the driving environment change by the half value and the certain number, which not only continues the core advantage of quick adaptation in the driving environment change scenario, but also makes up for the system operation risk that may be caused by simply halving the threshold, and further improves the adaptation accuracy, operation stability and actual application reliability of the self-learning function of the automatic transmission.

[0067] Optionally, in one embodiment of the application, it further includes: detecting the gear shifting impact degree within a certain time period; and in the case that the gear shifting impact degree meets certain learning failure conditions, rolling back at least one target parameter with a certain control strategy, and recording failure sample data to optimize the learning strategy.

[0068] In the embodiment of the application, the certain time period can be understood as a fixed time interval set for evaluating the self-learning effect after the automatic transmission completes the self-learning process. The time period setting can cover various typical gear shifting scenarios (such as starting, accelerating, cruise switching, etc.), so as to ensure that comprehensive and objective gear shifting performance data can be collected, and the application does not make specific limitations.

[0069] The shift shock degree can be understood as a quantitative index of instantaneous shock intensity generated by a change in power transmission connection state during the execution of a shift operation of the automatic transmission. The shift shock degree can be converted from physical signals such as torque fluctuation, speed mutation, and vehicle body vibration during the shift operation, and is used to reflect the smoothness level of the shift operation.

[0070] The certain learning failure condition can be understood as a quantitative determination criterion for determining whether the self-learning effect meets the standard. The certain learning failure condition can include, but is not limited to, a condition that the shift shock degree is higher than a reference value before self-learning, and a condition that the shock degree is not significantly improved compared with the reference value. The application does not make specific limitations.

[0071] The certain control strategy can be understood as a preset execution rule system for rolling back the target parameters after the self-learning is determined to fail. The certain control strategy explicitly indicates the priority order, rollback range, and execution process of the parameter rollback. Differentiated rollback logic can be developed according to the influence of the parameters on the shift performance (for example, the shift timing parameter has a higher priority than the auxiliary adjustment parameter). The application does not make specific limitations.

[0072] The target parameter can be understood as a core control parameter that directly affects the shift performance and is adjusted during the self-learning process of the automatic transmission to adapt to the driving style or environmental changes. The target parameter can include, but is not limited to, shift timing, power connection strength, transmission ratio matching coefficient, and clutch engagement speed. The application does not make specific limitations.

[0073] In actual execution, the embodiments of the application first detect the shift shock degree within a certain time period after the self-learning is completed, and then determine the shift shock degree according to certain learning failure conditions (such as the shift shock degree being higher than the reference value before learning, and no significant improvement). The target parameters (such as shift timing and power connection strength) that affect the shift performance are rolled back according to the certain control strategy to quickly restore the basic shift performance of the transmission. At the same time, the data (including driving environment, operation characteristics, adjustment parameters, and shock degree detection results) of the self-learning process are recorded to form a failure sample, which provides real scene data support for algorithm iteration of the learning strategy.

[0074] The embodiments of the application can quickly avoid the driving frustration caused by the increase in the shift shock degree, protect the driving smoothness and safety, and avoid the continuous negative impact of invalid learning on the driving experience by detecting the shift shock degree, determining whether the certain learning failure condition is met, and then rolling back the target parameters when the certain failure condition is met. At the same time, the failure sample data is recorded, which can promote the continuous improvement of the learning strategy, reduce the learning failure probability in subsequent similar scenarios, and continuously improve the adaptation accuracy and reliability of the self-learning function.

[0075] The principle of the self-learning method of the automatic transmission according to an embodiment of the present application is described below by taking a specific example.

[0076] Figure 2 The principle flowchart of the self-learning method of the automatic transmission according to an embodiment of the present application is shown in FIG. 2.

[0077] Step S201: Collecting learnable signals of the automatic transmission.

[0078] In the embodiment of the present application, the engine speed signal, the throttle opening signal, the engine torque signal, the vehicle speed signal, the altitude signal, and the brake pedal signal can be collected by EMS, ESP, T-BOX, GPS, etc.

[0079] Step S202: Determining whether the driving style and the driving environment are changed.

[0080] In the embodiment of the present application, based on the learnable signals, it is determined whether the driving style and the driving environment are changed. When it is determined that the driving style meets a first certain change condition, the automatic transmission is controlled to enter a self-learning mode, and step S203 is performed. When it is determined that the driving environment meets a second certain change condition, the automatic transmission is controlled to enter the self-learning mode, and step S204 is performed.

[0081] Step S203: Taking a certain number of times as a self-learning number of times, so as to perform self-learning according to the learnable signals when the number of times of using the clutch reaches the self-learning number of times.

[0082] In the embodiment of the present application, the certain number of times can be 50 times. Therefore, 50 times are taken as the self-learning number of times, and then self-learning is performed according to the learnable signals when the number of times of using the clutch reaches 50 times.

[0083] Step S204: Determining the self-learning number of times from a half value of a current self-learning number of times, so as to perform self-learning according to the learnable signals when the number of times of using the clutch reaches the self-learning number of times.

[0084] In the embodiment of the present application, the half value of the current self-learning number of times can be 48 times. However, 48 times is less than the first number of times 50 times. Therefore, 50 times are taken as the self-learning number of times, and then self-learning is performed according to the learnable signals when the number of times of using the clutch reaches 50 times.

[0085] Step S205: Determining whether a certain learning failure condition is met.

[0086] Wherein, the embodiment of the application detects the gear shift impact degree within a certain time period after the automatic transmission performs self-learning. If the gear shift impact degree is lower than that before self-learning, it indicates that the learning is effective, and the learning result can be consolidated. If the gear shift impact degree is higher than that before self-learning or there is no obvious improvement (i.e. a certain learning failure condition is met), it indicates that the learning is ineffective, and the target parameter can be rolled back, and the failure sample data is recorded to optimize the learning strategy.

[0087] According to the self-learning method of the automatic transmission provided in the embodiment of the application, multi-dimensional learnable signals are collected to provide comprehensive data support for driving style judgment, ensure accurate identification of driving style changes, and then trigger the self-learning mode when it is determined that the driving style meets the first certain change condition, and a certain number of times are taken as the threshold of the self-learning number of times, effectively shortening the start period of self-learning after the driving style changes. At the same time, the learning strategy is executed based on the learnable signals to ensure the pertinence and accuracy of the self-learning process, so that the automatic transmission can quickly adjust the control parameters such as gear shift logic and power connection strength, accurately meet the driving style requirements, and significantly improve the gear shift smoothness, power response timeliness and driving experience consistency. Thus, the problem that the automatic transmission self-learning trigger threshold in the related art gradually increases with the increase of the number of clutch uses, and the self-learning cannot be started until the clutch accumulates a certain number of uses when the driving scene dynamically changes, resulting in difficulty in quickly adjusting the automatic transmission logic, gear shift jerk, poor driving experience of power connection, and difficulty in meeting the user's driving requirements is solved.

[0088] Secondly, the self-learning device of the automatic transmission according to the embodiment of the application is described with reference to the accompanying drawings.

[0089] Figure 3 A block schematic diagram of the self-learning device of the automatic transmission according to the embodiment of the application is provided.

[0090] As Figure 3 shown, the self-learning device of the automatic transmission 30 includes an acquisition module 100, a first judgment module 200 and a first learning module 300.

[0091] The acquisition module 100 is configured to acquire learnable signals of the automatic transmission.

[0092] The first judgment module 200 is configured to determine whether the driving style of the driver meets the first preset change condition according to the learnable signals.

[0093] The first learning module 300 is configured to control the automatic transmission to enter a self-learning mode when the driving style meets the first preset change condition, take a preset number of times as the self-learning number of times, and perform a learning strategy according to the learnable signals to perform self-learning when the number of uses of the clutch reaches the self-learning number of times.

[0094] Optionally, in an embodiment of the present application, further comprising: a second determining module and a second learning module.

[0095] The second determining module is configured to determine whether the current driving environment meets a second preset change condition according to the learnable signal.

[0096] The second learning module is configured to control the automatic transmission to enter a self-learning mode when the current driving environment meets the second preset change condition, determine a self-learning number of times according to a half value of the current self-learning number of times, and perform self-learning according to the learnable signal when the number of times of using the clutch reaches the self-learning number of times.

[0097] Optionally, in an embodiment of the present application, the second learning module comprises: a judging unit, a first determining unit and a second determining unit.

[0098] The judging unit is configured to determine whether the half value is greater than or equal to a preset number of times.

[0099] The first determining unit is configured to take the half value as the self-learning number of times when the half value is greater than or equal to the preset number of times.

[0100] The second determining unit is configured to take the preset number of times as the self-learning number of times when the half value is less than the preset number of times.

[0101] Optionally, in an embodiment of the present application, further comprising: a detecting module and an optimizing module.

[0102] The detecting module is configured to detect a shift shock degree within a preset time length.

[0103] The optimizing module is configured to roll back at least one target parameter according to a preset control strategy and record failed sample data to optimize a learning strategy when the shift shock degree meets a preset learning failure condition.

[0104] Optionally, in an embodiment of the present application, the collecting module 100 comprises: a first collecting unit, a second collecting unit, a third collecting unit, a fourth collecting unit, a fifth collecting unit, a sixth collecting unit and a generating unit.

[0105] The first collecting unit is configured to collect a speed signal of the engine.

[0106] The second collecting unit is configured to collect a throttle opening degree signal of the accelerator pedal.

[0107] The third collecting unit is configured to collect a torque signal of the engine.

[0108] The fourth collecting unit is configured to collect a vehicle speed signal of the vehicle.

[0109] A fifth acquisition unit is configured to acquire an altitude signal of an environment in which the vehicle is located.

[0110] A sixth acquisition unit is configured to acquire a brake signal of a brake pedal.

[0111] A generation unit is configured to generate a learnable signal according to the rotation speed signal, the accelerator opening degree signal, the torque signal, the vehicle speed signal, the altitude signal, and the brake signal.

[0112] It should be noted that the foregoing description of the self-learning method of the automatic transmission also applies to the self-learning device of the automatic transmission of this embodiment, which will not be described here again.

[0113] The self-learning device of the automatic transmission provided in the embodiments of the present application collects multi-dimensional learnable signals to provide comprehensive data support for driving style judgment, ensures accurate identification of driving style changes, and then triggers the self-learning mode when the driving style meets the first certain change condition, and takes a certain number of times as the threshold of the self-learning number of times, effectively shortens the start period of self-learning after the driving style changes, and at the same time, executes the learning strategy based on the learnable signal to ensure the pertinence and accuracy of the self-learning process, so that the automatic transmission can quickly adjust the control parameters such as shift logic and power engagement strength, accurately meet the driving style requirements, and significantly improve the shift smoothness, power response timeliness, and driving experience consistency. Thus, the problem that the automatic transmission self-learning trigger threshold in the related art gradually increases with the increase of the number of clutch uses, and the self-learning needs to wait for the clutch to accumulate a certain number of uses when the driving scene dynamically changes, which leads to the problem that it is difficult to quickly adjust the automatic transmission logic, resulting in a driving experience of gear shift jerk, poor power engagement, and difficulty in meeting the user's driving requirements.

[0114] Figure 4 A structural schematic diagram of a vehicle according to an embodiment of the present application is provided. The vehicle can include: The memory 401, the processor 402, and the computer program stored in the memory 401 and executable on the processor 402.

[0115] The processor 402 implements the self-learning method of the automatic transmission provided in the above embodiments when executing the program.

[0116] Further, the vehicle further includes: The communication interface 403 is configured to communicate between the memory 401 and the processor 402.

[0117] The memory 401 is configured to store the computer program executable on the processor 402.

[0118] The memory 401 can include a high-speed RAM memory and can also include a non-volatile memory, such as at least one disk memory.

[0119] If the memory 401, the processor 402 and the communication interface 403 are implemented independently, the communication interface 403, the memory 401 and the processor 402 can be connected to each other through a bus and complete communication between each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For convenience of representation, Figure 4 In the figure, only one thick line is used to represent the bus, but it does not mean that there is only one bus or only one type of bus.

[0120] Optionally, in a specific implementation, if the memory 401, the processor 402 and the communication interface 403 are integrated on a chip, the memory 401, the processor 402 and the communication interface 403 can complete communication between each other through an internal interface.

[0121] The processor 402 can be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement one or more embodiments of the present application.

[0122] The embodiments of the present application also provide a computer readable storage medium, having stored thereon a computer program, which, when executed by a processor, implements the self-learning method of the automatic transmission as above.

[0123] The embodiments of the present application also provide a computer program product, comprising a computer program, which, when executed by a processor, implements the self-learning method of the automatic transmission as above.

[0124] In the description of the application, reference to "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" means that a particular feature, structure, material, or characteristic being described is included in at least one embodiment or example of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment or example. Furthermore, the described specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples. In addition, the usage of "N" means at least two, for example, two, three or the like, unless explicitly stated otherwise.

[0125] Furthermore, the terms "first", "second", or the like, are used merely as a designation of certain elements or features, and do not imply or connote relative importance or a specific order of categorization thereof. Accordingly, features described as "first" or "second" can be explicitly or implicitly included in at least one of the features. In the description of the application, the meaning of "N" is at least two, for example, two, three, etc., unless explicitly specified otherwise.

[0126] Any process or method descriptions or blocks in flow charts or otherwise described herein represent embodiments which can be managed as one or more modules, segments, or portions of code which include one or more executable instructions for implementing specific logic functions or steps, and alternate implementations are possible. In some embodiments, the processes and methods described can be executed by one or more apparatuses or devices, either directly or after conversion to another language. Alternate implementations are possible.

[0127] The logic and / or steps represented in the flowcharts and / or described herein, for example, can be considered as a sequence of executable instructions, and can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor- containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For purposes of this specification, a "computer-readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer-readable medium can be a product of the manufacturing and / or processing. The computer-readable medium can include, but is not limited to, the following: an electronic connection (an electronic device with one or N wires), a portable computer diskette (a magnetic device), a RAM (random access memory), a ROM (read-only memory), an EPROM (erasable programmable ROM) or a Flash memory, an optical fiber, and a portable CD ROM. In addition, the computer-readable medium can even be paper or another suitable medium upon which the program can be printed, because the program can be electronically captured, via the optically scanning of the paper or other medium, then compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and stored in the computer memory.

[0128] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the above embodiments, the N steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware and in another embodiment, the hardware can be implemented using any or a combination of the following technologies, which are all well known in the art: a discrete logic circuit having logic gates for implementing logic functions on data signals, an application specific integrated circuit having appropriate combinational logic gates, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0129] Those of skill in the art would understand that the steps carried out in the above-mentioned embodiments can be implemented by programs instructing relevant hardware to complete all or part of the steps, and the programs can be stored in a computer-readable storage medium. When the programs are executed, they include one or a combination of the steps of the method embodiments.

[0130] In addition, each of the functional units in the various embodiments of the present application can be integrated in one processing module, or each of the units can be physically present separately, or two or more units can be integrated in one module. The integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0131] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. A self-learning method for an automatic transmission, characterized in that, Includes the following steps: Acquire learnable signals from the automatic transmission; Based on the learnable signal, determine whether the driver's driving style meets the first preset change condition; If the driving style meets the first preset change condition, the automatic transmission is controlled to enter the self-learning mode, so as to use the preset number of times as the self-learning number, so that after the number of times the clutch is used reaches the self-learning number, a learning strategy is executed according to the learnable signal to perform self-learning.

2. The method according to claim 1, characterized in that, Also includes: Based on the learnable signal, determine whether the current driving environment meets the second preset change condition; If the current driving environment meets the second preset change condition, the automatic transmission is controlled to enter the self-learning mode. The number of self-learning times is determined by half of the current number of self-learning times, so that after the number of times the clutch is used reaches the number of self-learning times, self-learning is performed according to the learnable signal.

3. The method according to claim 2, characterized in that, Determining the number of self-learning iterations from half the current number of self-learning iterations includes: Determine whether the half value is greater than or equal to the preset number; If the number of times is greater than or equal to the preset number, then half of the value is taken as the number of times the self-learning is performed. If the number of times is less than the preset number, then the preset number is used as the number of times for self-learning.

4. The method according to claim 1, characterized in that, Also includes: Detect the shift shock within a preset time period; If the shift shock meets the preset learning failure condition, at least one target parameter is rolled back using a preset control strategy, and the failure sample data is recorded to optimize the learning strategy.

5. The method according to claim 1, characterized in that, The learnable signals acquired from the automatic transmission include: Collect engine speed signals; Acquire the throttle opening signal from the accelerator pedal; Collect the torque signal of the engine; Collect vehicle speed signals; Collect altitude signals from the surrounding environment; Collect braking signals from the brake pedal; The learnable signal is generated based on the speed signal, the throttle opening signal, the torque signal, the vehicle speed signal, the altitude signal, and the braking signal.

6. A self-learning device for an automatic transmission, characterized in that, include: The acquisition module is used to acquire learnable signals from the automatic transmission; The first judgment module is used to determine whether the driver's driving style meets the first preset change condition based on the learnable signal. The first learning module is used to control the automatic transmission to enter a self-learning mode if the driving style meets the first preset change condition, so as to use a preset number of times as the self-learning number of times, and to execute a learning strategy to perform self-learning according to the learnable signal after the number of times the clutch is used reaches the self-learning number of times.

7. The apparatus according to claim 6, characterized in that, Also includes: The second judgment module is used to determine whether the current driving environment meets the second preset change condition based on the learnable signal. The second learning module is used to control the automatic transmission to enter the self-learning mode if the current driving environment meets the second preset change condition. The self-learning number is determined by half of the current self-learning number, so that self-learning is performed according to the learnable signal after the number of times the clutch is used reaches the self-learning number.

8. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the self-learning method for an automatic transmission as described in any one of claims 1-5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the self-learning method for the automatic transmission as described in any one of claims 1-5.

10. A computer program product, comprising a computer program, characterized in that, The computer program is executed to implement the self-learning method for the automatic transmission as described in any one of claims 1-5.

Images