Self-adaptive gear shifting method and device based on intelligent decision and automatic transmission

Abstract

The invention discloses a self-adaptive gear shifting method and device based on intelligent decision making and an automatic transmission, and relates to the technical field of automobile transmission and control. According to the vehicle state, the driver intention and the environment working condition, the trained deep learning model is adopted, and an optimal control strategy including the target gear, the optimal gear shifting opportunity, a clutch engagement speed curve and the target oil supplementing amount of an engine is output; and generating a driving instruction according to the optimal control strategy so as to control an execution mechanism to complete a gear shifting action. And the intelligent level of the vehicle transmission is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of automobile transmission and control technology, in particular to an adaptive gear shifting method and device based on intelligent decision-making and an automatic transmission. BACKGROUND

[0002] The statements in this section merely provide background information related to the present application and do not necessarily constitute the prior art.

[0003] Automatic transmission technology is the key to improving the driving comfort and convenience of vehicles. At present, although automatic transmissions such as hydraulic automatic transmissions (AT), dual clutch transmissions (DCT) and continuously variable transmissions (CVT) have excellent performance, their structures are complex, their manufacturing costs are high, and their maintenance costs are high.

[0004] Traditional manual transmissions (MT) have the advantages of simple structure, low cost, high transmission efficiency and driving pleasure, but their operation is cumbersome, especially in heavy traffic, which increases the burden on the driver.

[0005] Automatic manual transmissions (AMT) add an electric control actuator to the MT to achieve automatic gear shifting, which is a low-cost automation solution. However, the transmission control unit (TCU) of the traditional AMT is mostly based on a pre-set gear shifting MAP chart, with a fixed strategy that cannot adapt to different driver styles, real-time road conditions (such as slope and curve) and changes in vehicle load, and generally has problems such as gear shifting jerk, low intelligence, and poor driving experience. SUMMARY

[0006] To solve the above problems, the present application provides an adaptive gear shifting method and device based on intelligent decision-making and an automatic transmission to improve the intelligence level of vehicle transmissions.

[0007] To achieve the above purpose, the present application adopts the following technical solutions: In a first aspect, the present application provides an adaptive gear shifting method based on intelligent decision-making, comprising: Obtaining vehicle state, driver intention and environmental working condition; According to the vehicle state, driver intention and environmental working condition, a trained deep learning model is used to output an optimal control strategy including target gear, best gear shifting timing, clutch engagement speed curve and engine target oiling amount; Generating a driving instruction from the optimal control strategy to control the actuator to complete the gear shifting action.

[0008] As an alternative embodiment, the vehicle state includes engine speed, vehicle speed, torque, clutch position, clutch actuator motor speed and fuel injection amount; the driver intent includes throttle pedal opening, brake pedal opening and steering wheel angle; the environmental condition includes slope, altitude and curvature.

[0009] As an alternative embodiment, the multi-source data including vehicle state, driver intent and environmental condition are extracted for physical features, timing features, clutch features and engine features to form a multi-dimensional feature sequence; the multi-dimensional feature sequence is inputted into the trained deep learning model to output gear probability, shift time, clutch position-time discrete points and fuel injection amount timing sequence.

[0010] As an alternative embodiment, the control strategy obtained based on the deep learning model is corrected and calibrated; including: Target gear correction: unreasonable results are filtered according to physical constraints such as vehicle speed constraint, engine constraint and shift times constraint; Shift timing calibration: adjust the shift timing according to the transmission oil temperature, delay the shift when the transmission oil temperature is less than the minimum oil temperature threshold, and advance the shift when the transmission oil temperature is greater than the maximum oil temperature threshold; at the same time, combined with the brake signal, when the brake pedal opening is greater than the set opening threshold, the shift is suspended; Clutch curve correction: adjust the clutch curve slope according to the current transmission oil temperature, and limit the maximum engagement speed combined with the road adhesion coefficient; Dynamic calibration of fuel injection amount: during upshift, fuel injection is performed according to k1 times the speed difference, and linear attenuation is performed during engagement stage; during downshift, fuel injection is performed according to k2 times the speed difference, and the clutch engagement speed is matched, k2 is greater than 1.

[0011] As an alternative embodiment, the generated optimal control strategy is converted into driving instructions, which are sent to external execution driving mechanisms through a control interface, including shift actuators, clutch actuators and throttle actuators, to control external execution mechanisms to complete shift actions.

[0012] In a second aspect, the present application provides an adaptive shift device based on intelligent decision-making, including: The acquisition module is configured to acquire vehicle state, driver intent and environmental condition; The strategy generation module is configured to output an optimal control strategy including target gear, optimal shift timing, clutch engagement speed curve and engine target fuel injection amount according to vehicle state, driver intent and environmental condition using a trained deep learning model; The shift control module is configured to generate driving instructions from the optimal control strategy to control the execution mechanism to complete the shift action.

[0013] In a third aspect, the present application provides an automatic transmission, comprising: a manual transmission mechanical assembly, and an adaptive shifting device of the second aspect and an execution driving mechanism installed on the manual transmission mechanical assembly, the execution driving mechanism comprising a shifting actuator, a clutch actuator and a throttle actuator; the adaptive shifting device is used for generating an optimal control strategy and converting the optimal control strategy into driving instructions to control the shifting actuator, the clutch actuator and the throttle actuator to complete a shifting action.

[0014] In a fourth aspect, the present application provides an electronic device, comprising a memory and a processor, and computer instructions stored in the memory and running on the processor, when the computer instructions are run by the processor, the method of the first aspect is completed.

[0015] In a fifth aspect, the present application provides a computer readable storage medium for storing computer instructions, when the computer instructions are executed by a processor, the method of the first aspect is completed.

[0016] In a sixth aspect, the present application provides a computer program product, comprising a computer program, when the computer program is executed by a processor, the method of the first aspect is completed.

[0017] Compared with the prior art, the present application has the following beneficial effects: The present application discloses an adaptive shifting method and device based on intelligent decision and an automatic transmission, which deeply integrates AI technology into transmission control, can retain the low-cost advantage of a manual transmission, and can also endow it with adaptive, self-learning and personalized capabilities, thereby forming a new type of high-performance intelligent automatic transmission.

[0018] Through a deep learning model, vehicle state, driver intention and environmental condition data are analyzed in real time, an optimal shifting control strategy is output, and an execution mechanism is controlled to complete an action. The adaptive shifting device of the adaptive shifting method can be independently installed on a manual transmission vehicle. The automatic transmission integrates the device, a manual transmission body and an execution mechanism, solves the problems of shifting jerk and strategy rigidity of a traditional AMT, and provides a low-cost, high-intelligent, high-smooth and self-learning automatic transmission solution, which is suitable for front-mounted and rear-mounted vehicles.

[0019] The advantages of the additional aspects of the present application will be partially given in the following description, partially will become obvious from the following description, or will be understood through the practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0021] Figure 1 This is a flowchart of the adaptive gear shifting method based on intelligent decision-making provided in Embodiment 1 of the present invention; Figure 2 This is a schematic diagram of the adaptive gear shifting principle based on intelligent decision-making provided in Embodiment 1 of the present invention; Figure 3 This is a block diagram of the automatic transmission architecture provided in Embodiment 3 of the present invention. Detailed Implementation

[0022] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0023] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0024] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form as well. Furthermore, it should be understood that the terms “comprising” and “including”, and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0026] Example 1 This embodiment provides an adaptive gear shifting method based on intelligent decision-making, such as... Figures 1-2 As shown, it includes: Acquire vehicle status, driver intent, and environmental conditions; Based on the vehicle status, driver intention and environmental conditions, a trained deep learning model is used to output the optimal control strategy, including the target gear, the best shift timing, the clutch engagement speed curve and the engine target fuel replenishment amount. The optimal control strategy generates drive commands to control the actuator to complete the gear shifting action.

[0027] In this embodiment, multi-source data representing vehicle status, driver intent, and environmental conditions are acquired in real time through the vehicle CAN bus interface and dedicated sensor interface. The vehicle status includes: engine speed, vehicle speed, torque, clutch position, clutch actuator motor speed, and fuel injection quantity. Driver intentions include: accelerator pedal opening, brake pedal opening, and steering wheel angle; Environmental conditions include: slope, or altitude, curvature, etc.

[0028] In this embodiment, a deep learning model, such as a Long Short-Term Memory (LSTM) network or a Deep Reinforcement Learning (DRL) model, takes real-time multi-source data as input, performs millisecond-level analysis and decision-making, and outputs an optimal control strategy including the target gear, the best shift timing, the clutch engagement speed curve, and the engine target fuel replenishment amount.

[0029] Specifically: S1: Preprocess the acquired multi-source data, including outlier handling, missing value imputation, and data standardization. Outlier handling uses the 3σ principle plus sliding window mean filtering to remove instantaneous jump data from sensors. High-frequency data (such as vehicle speed) is imputed using forward linear imputation, while low-frequency data (such as slope) is interpolated using K-nearest neighbor interpolation. Z-score standardization (mean 0, standard deviation 1) is used to process numerical features to eliminate the influence of units.

[0030] S2: Extract features from multi-source data to construct a multi-dimensional feature sequence; specifically including: Physical characteristics: Calculate the speed ratio (engine speed / vehicle speed), torque reserve coefficient (current torque / maximum torque), and gradient resistance coefficient (sin(gradient) × vehicle mass); Temporal characteristics: Extract vehicle speed change rate, accelerator pedal opening integral, and engine speed trend at historical set times; Clutch characteristics: difference between current clutch position and target position, actuator motor speed, and slope of historical engagement curve; Engine characteristics: deviation between current fuel injection quantity and optimal fuel injection quantity, and speed response rate.

[0031] S3: Deep learning model, which takes multi-dimensional feature sequence as input and outputs the probability of each gear, as well as the delay time of shift time relative to the current time, the discrete points of clutch position-time, and the time sequence of fuel replenishment amount; S4: Strategy correction and verification.

[0032] Target gear correction: Filters out unreasonable results based on physical constraints such as vehicle speed, engine, and number of gear shifts; for example, prohibits shifting into 4th gear or higher when the vehicle speed is less than the set speed threshold (e.g., 8km / h), and forces upshifting when the engine speed is greater than the set speed threshold (e.g., 6500rpm); avoids gear shifting greater than or equal to the set number of shifts within 2 consecutive seconds (e.g., twice, to prevent frequent shifting).

[0033] Shift timing calibration: The shift timing is dynamically adjusted according to the transmission oil temperature. When the transmission oil temperature is below the minimum oil temperature threshold, the shift is delayed, and when it is above the maximum oil temperature threshold, the shift is advanced. At the same time, combined with the braking signal, the shift is paused when the brake pedal opening is greater than the set opening threshold. For example, the shift is delayed by 50ms when the temperature is <-10℃, and advanced by 30ms when the temperature is >120℃. If the brake pedal opening is >30%, the shift is paused.

[0034] Clutch curve correction: Adjust the slope of the clutch curve according to the current transmission oil temperature, and limit the maximum engagement speed in combination with the road surface adhesion coefficient; for example, reduce the slope by 30% at low temperatures, and ≤0.5mm / ms on icy and snowy roads.

[0035] Dynamic calibration of oil replenishment: When upshifting, replenish oil at a speed difference of k1 times, with linear decay during engagement, k1 less than 1, such as 0.8; when downshifting, replenish oil at a speed difference of k2 times, synchronously matching the clutch engagement speed, k2 greater than 1, such as 1.2.

[0036] S5: The final output includes the target gear, the optimal shift timing, the clutch engagement speed curve, and the optimal control strategy for the engine target fuel replenishment amount.

[0037] In this embodiment, in learning mode, the driver's gear shifting operation data is recorded to fine-tune and optimize the parameters of the deep learning model, so that the control strategy generated by the deep learning model is closer to the personalized habits of a specific driver.

[0038] In this embodiment, the generated optimal control strategy is converted into drive commands and sent to external execution drive mechanisms, including shift actuators, clutch actuators and throttle actuators, through a control interface to control the external actuators to complete the shifting action.

[0039] In this embodiment, the above method is encapsulated into an independent electronic control unit (ECU) with waterproof and shockproof functions, which interfaces with the vehicle's original system and external actuators through a standardized wiring harness connector to achieve plug-and-play functionality.

[0040] Example 2 This embodiment provides an adaptive gear shifting device based on intelligent decision-making, including: The acquisition module is configured to acquire vehicle status, driver intent, and environmental conditions. The strategy generation module is configured to use a trained deep learning model to output an optimal control strategy, including the target gear, the best shift timing, the clutch engagement speed curve, and the target engine fuel replenishment amount, based on the vehicle status, driver intention, and environmental conditions. The shift control module is configured to generate drive commands from the optimal control strategy to control the actuator to complete the shift action.

[0041] The aforementioned device, as an independent and universal intelligent control core, can be added to enable traditional manual transmissions to acquire highly intelligent automatic shifting functions.

[0042] It should be noted that the above modules correspond to the steps described in Embodiment 1, and the examples and application scenarios implemented by the above modules and the corresponding steps are the same, but are not limited to the content disclosed in Embodiment 1. It should also be noted that the above modules, as part of the system, can be executed in a computer system such as a set of computer-executable instructions.

[0043] Example 3 This embodiment provides an automatic transmission that combines the low cost and high efficiency of a manual transmission with the intelligence, smoothness, and convenience of a high-level automatic transmission.

[0044] like Figure 3 As shown, it includes: a manual transmission mechanical assembly, an actuation drive mechanism mounted on the manual transmission mechanical assembly, and the adaptive shifting device described in Embodiment 2; The actuator includes a shift actuator for controlling gear selection and engagement, a clutch actuator for controlling clutch disengagement and engagement, and a throttle actuator for controlling engine rev-matching during downshifting. The shift actuator and clutch actuator act directly on the shift fork and clutch disengagement mechanism inside the manual transmission mechanical assembly through mechanical connectors; The adaptive shifting device is electrically connected to the drive mechanism and receives signals from vehicle sensors, thus forming a complete automatic transmission with a high degree of artificial intelligence.

[0045] This invention discloses an adaptive shifting method, device, and automatic transmission based on intelligent decision-making. By running a deep learning model, it analyzes vehicle status, driver intent, and environmental condition data in real time, outputs the optimal shifting control strategy, and controls the actuator to complete the action. The adaptive shifting device implementing the adaptive shifting method can be independently installed in manual transmission vehicles, while the automatic transmission integrates the device, the manual transmission body, and the actuator. This solves the problems of shift jerking and rigid strategies in traditional AMTs, providing a low-cost, highly intelligent, highly smooth, and self-learning automatic transmission solution suitable for both OEM and aftermarket vehicles.

[0046] In further embodiments, the following is also provided: An electronic device includes a memory and a processor, as well as computer instructions stored in the memory and running on the processor, wherein the computer instructions, when executed by the processor, perform the method described in Embodiment 1. For brevity, further details are omitted here.

[0047] It should be understood that in this embodiment, the processor can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0048] Memory may include read-only memory and random access memory, and provides instructions and data to the processor. A portion of memory may also include non-volatile random access memory. For example, memory may also store information about the device type.

[0049] A computer-readable storage medium for storing computer instructions, which, when executed by a processor, perform the method described in Embodiment 1.

[0050] The method in Example 1 can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor. The software modules can reside in readily available storage media in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, a detailed description is not provided here.

[0051] A computer program product includes a computer program that, when executed by a processor, implements the method described in Embodiment 1.

[0052] The present invention also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions, such as instructions included in program modules, which execute in a device on a target real or virtual processor to perform the processes / methods described above. Typically, program modules include routines, programs, libraries, objects, classes, components, data structures, etc., that perform specific tasks or implement specific abstract data types. In various embodiments, the functionality of program modules can be combined or divided among program modules as needed. The machine-executable instructions for the program modules can execute within a local or distributed device. In a distributed device, the program modules can reside in both local and remote storage media.

[0053] The computer program code used to implement the methods of the present invention may be written in one or more programming languages. This computer program code may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the computer or other programmable data processing device, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a computer, partially on a computer, as a stand-alone software package, partially on a computer and partially on a remote computer, or entirely on a remote computer or server.

[0054] In the context of this invention, computer program code or related data may be carried by any suitable carrier to enable a device, apparatus, or processor to perform the various processes and operations described above. Examples of carriers include signals, computer-readable media, and the like. Examples of signals may include electrical, optical, radio, sound, or other forms of propagation signals, such as carrier waves, infrared signals, etc.

[0055] Those skilled in the art will recognize that the units and algorithm steps described in connection with the various examples of this embodiment can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention.

[0056] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. An adaptive gear shifting method based on intelligent decision-making, characterized in that, include: Acquire vehicle status, driver intent, and environmental conditions; Based on the vehicle status, driver intention and environmental conditions, a trained deep learning model is used to output the optimal control strategy, including the target gear, the best shift timing, the clutch engagement speed curve and the engine target fuel replenishment amount. The optimal control strategy generates drive commands to control the actuator to complete the gear shifting action.

2. The adaptive gear shifting method based on intelligent decision-making as described in claim 1, characterized in that, Vehicle status includes engine speed, vehicle speed, torque, clutch position, clutch actuator motor speed, and fuel injection quantity; driver intent includes accelerator pedal opening, brake pedal opening, and steering wheel angle; environmental conditions include slope, altitude, and curvature.

3. The adaptive gear shifting method based on intelligent decision-making as described in claim 1, characterized in that, Physical features, temporal features, clutch features, and engine features are extracted from multi-source data including vehicle status, driver intent, and environmental conditions to form a multi-dimensional feature sequence. Using the multi-dimensional feature sequence as input, a trained deep learning model is used to output the probability of each gear, as well as the shift time, the discrete points of clutch position-time, and the time sequence of fuel replenishment.

4. The adaptive gear shifting method based on intelligent decision-making as described in claim 1, characterized in that, The control strategy obtained based on the deep learning model is corrected and calibrated, including: Target gear correction: Filters out unreasonable results based on physical constraints such as vehicle speed constraint, engine constraint, and shift count constraint; Shift timing calibration: Adjust shift timing according to transmission oil temperature. When the transmission oil temperature is below the minimum oil temperature threshold, shifting is delayed; when the oil temperature is above the maximum oil temperature threshold, shifting is advanced. At the same time, combined with the braking signal, shifting is paused when the brake pedal opening is greater than the set opening threshold. Clutch curve correction: Adjust the slope of the clutch curve according to the current transmission oil temperature, and limit the maximum engagement speed in combination with the road surface adhesion coefficient. Dynamic calibration of oil replenishment: When upshifting, replenish oil at a speed difference of k1 times, with linear decay during engagement; when downshifting, replenish oil at a speed difference of k2 times, synchronously matching the clutch engagement speed, with k2 greater than 1.

5. The adaptive gear shifting method based on intelligent decision-making as described in claim 1, characterized in that, The generated optimal control strategy is converted into drive commands and sent to external actuators, including shift actuators, clutch actuators and throttle actuators, through the control interface to control the external actuators to complete the shifting action.

6. An adaptive gear shifting device based on intelligent decision-making, characterized in that, include: The acquisition module is configured to acquire vehicle status, driver intent, and environmental conditions. The strategy generation module is configured to use a trained deep learning model to output an optimal control strategy, including the target gear, the best shift timing, the clutch engagement speed curve, and the target engine fuel replenishment amount, based on the vehicle status, driver intention, and environmental conditions. The shift control module is configured to generate drive commands from the optimal control strategy to control the actuator to complete the shift action.

7. An automatic transmission, characterized in that, include: A manual transmission mechanical assembly, an actuator mounted on the manual transmission mechanical assembly, and an adaptive shifting device as described in claim 6, wherein the actuator includes a shift actuator, a clutch actuator, and a throttle actuator; the adaptive shifting device is used to generate an optimal control strategy and convert the optimal control strategy into drive commands to control the shift actuator, clutch actuator, and throttle actuator to complete the shifting action.

8. An electronic device, characterized in that, It includes a memory and a processor, as well as computer instructions stored in the memory and running on the processor, which, when executed by the processor, perform the method according to any one of claims 1-5.

9. A computer-readable storage medium, characterized in that, Used to store computer instructions, which, when executed by a processor, perform the method described in any one of claims 1-5.

10. A computer program product, characterized in that, Includes a computer program, which, when executed by a processor, implements the method described in any one of claims 1-5.

Images