Gearbox gear self-learning system and method

Abstract

The invention discloses a gearbox gear self-learning system and method, and relates to the field of gearbox control, and the system comprises a gear selection displacement deviation learning module which is used for pushing a gear selection displacement to a limit position by applying a negative gear selection duty ratio, calculating a gear selection displacement offset, and correcting a gear selection value based on the offset; the neutral gear displacement learning module is configured to execute temporary neutral gear position learning and multiple neutral gear position sampling, and averaging is carried out to generate neutral gear self-learning displacement; the gear shifting displacement learning module is used for generating gear shifting self-learning displacement by circularly switching a target gear and recording gear shifting displacement and taking a multi-sampling average value; and the gear selection displacement self-learning module is used for controlling the gear selection displacement to the two ends of the gear shifting position in the gear shifting process and taking an intermediate value, and gear selection self-learning displacement is generated after multiple times of sampling. According to the scheme, the robustness of gear shifting logic can be remarkably enhanced, full automation of the self-learning process is achieved, and a high-reliability solution is provided for intelligent control of a gearbox.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of gearbox control, in particular to a gearbox gear self-learning system and method. BACKGROUND

[0002] The gearbox gear self-learning technology is a core means to improve the shifting precision and reliability of automatic transmission, which eliminates the shifting deviation caused by sensor installation error, mechanical wear or assembly tolerance by learning the displacement parameters in the actual operation of the gearbox.

[0003] The prior art mainly relies on the following methods: static calibration method, which calibrates the gear position by fixed duty cycle signal or preset displacement range when the gearbox is offline; single learning method, which records the last time the displacement value as the reference based on the default N gear position for subsequent gear self-learning. The said methods have the following key problems: the gear selection installation deviation and neutral displacement deviation are not considered, resulting in gear selection failure or gear entry judgment error during self-learning process; the fixed parameters or single sampling data are relied on, which cannot cover the sensor precision error and mechanical size change, resulting in increased shifting failure rate; the method does not combine with actual working conditions for dynamic verification, resulting in disconnection between self-learning results and actual needs; frequent manual intervention or offline calibration is required, increasing data maintenance and vehicle downtime. Therefore, based on the above problems, the present application proposes a gearbox gear self-learning system and method. SUMMARY

[0004] TECHNICAL OBJECTIVE In order to solve the above problems, the purpose of the present application is to provide a gearbox gear self-learning system and method, which aims to solve the shifting failure problem caused by the uncorrected gear selection installation deviation, the default neutral position reference error and the accidental single sampling data in the existing gearbox gear self-learning technology, to improve the precision and robustness of the self-learning process through systematic error compensation mechanism and multi-stage learning optimization strategy, to realize the dynamic adaptation and long-term stability of the shifting logic, and to reduce the demand for manual intervention and maintenance cost.

[0005] TECHNICAL SCHEME In order to achieve the above purpose, the present application provides a gearbox gear self-learning system and method, which calculates the gear selection offset and dynamically corrects the software setting value by driving the displacement to the limit position through negative gear selection duty cycle; determines the reference position by taking the average of the neutral displacement sampling at three different gear selection intermediate positions; records the average of three times of gear entry displacement to generate shifting parameters in the high-low gear cycle switching; optimizes the displacement data by combining timeout monitoring and three times of sampling abnormal value elimination mechanism, and finally feeds back the corrected gear selection displacement, neutral reference and shifting parameters to the execution system in real time, eliminating mechanical assembly error, sensor deviation and accidental interference, ensuring the reliability of self-learning results and the accuracy of shifting action.

[0006] In a first aspect, the present application provides a gearbox gear self-learning system, comprising: a gear selection displacement deviation learning module, configured to push the gear selection displacement to the limit position by applying a negative gear selection duty ratio, calculate the gear selection displacement deviation, and correct the software set gear selection value based on the deviation; a neutral displacement learning module, configured to perform temporary neutral position learning and multiple neutral position sampling, and generate a neutral self-learning displacement by averaging; a gear shift displacement learning module, configured to generate a gear shift self-learning displacement by cyclically switching target gears and recording the gear-in displacement, and averaging the multiple sampling values; a gear selection displacement self-learning module, configured to control the gear selection displacement to both ends of the gear shift position during gear shifting and take the intermediate value, and generate a gear selection self-learning displacement after multiple sampling; an error elimination module, configured to eliminate accidental errors by averaging three or more self-learning data; an execution control unit, configured to adjust the gearbox gear shift logic according to the self-learning result.

[0007] Further, the gear selection displacement deviation learning module determines the leftmost limit position of the gear selection displacement through displacement limit detection, takes the difference between the limit position and the default value of the preset gear selection displacement as the gear selection displacement deviation, and generates a temporary gear selection displacement by superimposing the gear selection value and the deviation in real time.

[0008] Further, the neutral displacement learning module generates a temporary neutral position by hanging gears one and two and recording the average gear shift displacement, and performs neutral displacement sampling at three different gear selection intermediate positions, and obtains the neutral self-learning displacement by averaging three times.

[0009] Further, the gear shift displacement learning module switches from the lowest gear to the highest gear in a step-by-step increasing manner, and then switches in a step-by-step decreasing manner, forming a complete cycle, records the last gear-in displacement of each gear in each cycle, and takes the average of the gear-in displacement in three cycles as the gear shift self-learning displacement.

[0010] Further, the gear selection displacement self-learning module pushes the gear selection displacement to the two end vertices of the current gear shift position, and takes the intermediate value of the displacement data of the two end vertices as a single gear selection displacement self-learning value, and stores and applies the average of three self-learning values.

[0011] Further, the error elimination module records three successful self-learning values during the gear shift displacement and gear selection displacement self-learning process, respectively, and optimizes the final self-learning displacement by removing abnormal values and taking the average.

[0012] Further, the system is provided with a timing threshold in each stage of self-learning, and if the timing threshold is exceeded, the self-learning is determined to fail, and a self-learning process and an abnormal alarm signal are output in real time.

[0013] Further, the system further comprises a gear selection offset correction module, which corrects the offset of the gear selection displacement by constructing a displacement response curve, combining multiple dynamic sampling data, and fitting the deviation between the actual displacement and the theoretical value, and the corrected offset calculation formula is:

[0014] In the formula, is the corrected offset; is the limit position of the gear selection displacement; is a preset gear selection displacement default value; is a nonlinear compensation factor; is an instantaneous slope of the displacement-duty cycle curve at the limit position; is a preset maximum slope threshold.

[0015] By constructing a displacement response curve and introducing a nonlinear compensation factor, the gear selection displacement offset is dynamically corrected, and the influence of the nonlinear characteristics of the mechanical system on the displacement accuracy is effectively overcome. The mechanism can significantly reduce the gear selection position error, improve the robustness of the gear shifting logic, and ensure the dynamic adaptation capability of the self-learning process to the sensor installation deviation and the mechanical assembly error.

[0016] Further, the system further comprises a weighted mean optimization module, which samples the displacement at different gear selection intermediate positions, and gives a dynamic weight based on the displacement distribution variance, and the neutral reference position formula is:

[0017] In the formula, is the neutral reference position; is a normalized weight coefficient; is the i-th sampled neutral displacement value.

[0018] By sampling the displacement at different gear selection intermediate positions and assigning a dynamic weight based on the inverse variance, the interference of local errors on the neutral reference position is suppressed. The algorithm can significantly reduce systematic errors, improve the neutral positioning accuracy and stability, and especially in the case of asymmetric assembly or dynamic working conditions, the anti-interference ability of the reference position is strengthened.

[0019] In a second aspect, the application further provides a gearbox gear self-learning method, which is based on the system of the first aspect and comprises: The corrected gear selection displacement is generated by limit position detection and offset calculation; The neutral reference position is determined based on the mean value of multiple sampling; The shift self-learning displacement is generated by gear cycle switching and displacement recording; The shift self-learning displacement is generated by combining shift position boundary detection and intermediate value calculation; The final displacement parameter is optimized by averaging three or more self-learning data.

[0020] Further, in the neutral displacement learning process, neutral displacement sampling is performed at three different shift intermediate positions respectively, and the average value of the three sampling results is taken as the reference value of the neutral self-learning displacement.

[0021] In a third aspect, the present application also provides a computer device, comprising a management platform and a memory, the management platform being connected to the memory, the memory being used to store a computer program, and the management platform being used to execute the computer program stored in the memory, so that the computer device executes the aforementioned gearbox shift self-learning method.

[0022] In a fourth aspect, the present application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a management platform to implement the aforementioned gearbox shift self-learning method.

[0023] The present application solves the problem of insufficient shift precision caused by sensor installation deviation, mechanical assembly error and accidental single sampling in the prior art by using a phased self-learning process and a multi-source data fusion strategy. Specifically, the dynamic shift deviation correction based on the displacement curve eliminates the influence of friction hysteresis and gear clearance through a non-linear compensation factor; the multi-point weighted average optimization algorithm for neutral displacement uses variance inverse weight to suppress local error; the phased self-learning sequence optimization decouples shift deviation learning, neutral positioning and shift displacement learning into independent steps to avoid error propagation; and the average value of three or more self-learning data combined with the abnormal value elimination mechanism eliminates accidental interference. This system can significantly enhance the robustness of the shift logic, improve the accuracy of the neutral reference and the stability of the shift displacement parameter, while realizing the full automation of the self-learning process, reducing the need for human intervention and maintenance costs, and providing a high-reliability solution for intelligent control of the gearbox.

[0024] Advantages By implementing the above-mentioned gearbox shift self-learning system and method, the following technical effects are achieved: (1) The present application performs shift deviation learning, neutral position learning and shift displacement learning in stages, which decomposes the complex self-learning process into ordered steps to avoid the influence of error accumulation on subsequent stages. This improves the fault tolerance of the self-learning process, reduces the risk of overall process interruption caused by single-stage failure, and enhances the logical rigor of multi-parameter collaborative optimization.

[0025] (2) Through multiple self-learning sampling and taking the mean value, combined with timeout monitoring and abnormal value elimination mechanism, the accidental error in single sampling can be effectively eliminated. It can ensure the long-term stability of the shift displacement and the selection displacement parameters, reduce the parameter fluctuation caused by mechanical vibration, sensor noise or instantaneous jamming, and ensure the repeatability and reliability of the self-learning results.

[0026] (3) The displacement response curve is constructed and the nonlinear compensation factor is introduced to dynamically correct the selection displacement offset, which can effectively overcome the influence of the nonlinear characteristics of the mechanical system on the displacement accuracy. This mechanism can significantly reduce the selection position error and improve the robustness of the shift logic, ensuring the dynamic adaptation ability of the self-learning process to sensor installation deviation and mechanical assembly error.

[0027] (4) Displacement sampling is performed at different selection intermediate positions, and dynamic weights are allocated based on the inverse variance to suppress the interference of local error on the neutral position reference. This algorithm can significantly reduce systematic error, improve the accuracy and stability of neutral positioning, and especially in asymmetric assembly or dynamic working conditions, it can strengthen the anti-interference ability of the reference position. BRIEF DESCRIPTION OF DRAWINGS

[0028] To make the above-mentioned gearbox gear self-learning system and method of the present application more obvious and easy to understand, the drawings needed in the specific embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application, and other drawings can be obtained from these drawings without creative labor for those skilled in the art.

[0029] Figure 1 The figure shows the system principle of the present application. Figure 2 The figure shows the gearbox gear self-learning method flow chart. DETAILED DESCRIPTION

[0030] Example 1: A gearbox gear self-learning system is provided, and the system principle is as follows Figure 1The system is shown to include: a selection shift displacement deviation learning module, configured to push the selection shift displacement to the limit position by applying a negative selection duty ratio, calculate the selection shift displacement offset, and correct the software set selection value based on the offset; a neutral shift displacement learning module, configured to perform temporary neutral position learning and multiple neutral position sampling, and generate a neutral self-learning displacement by averaging; a shift displacement learning module, configured to generate a shift self-learning displacement by switching the target gear position in a loop and recording the gear-in displacement, and taking the average of multiple sampling; a selection shift displacement self-learning module, configured to control the selection shift displacement to both ends of the shift position during the shift process and take the intermediate value, and generate a selection self-learning displacement after multiple sampling; an error elimination module, configured to eliminate accidental errors by averaging three or more self-learning data; and an execution control unit, configured to adjust the gearbox shift logic according to the self-learning result. Details are described as follows.

[0031] The selection shift displacement deviation learning module determines the leftmost limit position of the selection shift displacement through displacement limit detection, takes the difference between the limit position and the default value of the preset selection shift displacement as the selection shift displacement offset, and generates a temporary selection shift displacement by superimposing the selection value and the offset in real time.

[0032] The neutral shift displacement learning module generates a temporary neutral position by hanging gears one and two and recording the average shift displacement, and performs neutral shift displacement sampling at three different selection positions, and obtains a neutral self-learning displacement by averaging three times.

[0033] The shift displacement learning module switches from the lowest gear to the highest gear in a step-by-step increasing manner, and then switches in a step-by-step decreasing manner, forming a complete cycle. In each cycle, the last gear-in displacement of each gear is recorded, and the average of the gear-in displacements in three cycles is taken as the shift self-learning displacement.

[0034] The selection shift displacement self-learning module pushes the selection shift displacement to the two end vertices of the current shift position, and takes the intermediate value of the displacement data of the two end vertices as a single selection shift displacement self-learning value. The average of three self-learning values is stored and applied.

[0035] The error elimination module records three successful self-learning values during the shift displacement and selection shift displacement self-learning processes, respectively, and optimizes the final self-learning displacement by taking the average value after removing abnormal values.

[0036] The system is provided with a timing threshold in each self-learning stage. If the timing threshold is exceeded, the self-learning is determined to fail, and a self-learning process and an abnormal alarm signal are output in real time.

[0037] A gearbox gear self-learning method is also provided, which is based on the aforementioned system, and the flow is as follows Figure 2The shown, including: by limit position detection and offset calculation generation correction gear shift; based on multiple sampling mean determination of neutral reference position; through gear cycle switching and displacement record generation shift self-learning displacement; combined with shift position boundary detection and intermediate value calculation to generate gear selection self-learning displacement; three times or more self-learning data to optimize the average value of the final displacement parameters.

[0038] In the neutral displacement learning process, the neutral displacement sampling is performed at three different gear selection intermediate positions respectively, and the average value of the three sampling results is taken as the reference value of the neutral self-learning displacement.

[0039] Embodiment 2: On the basis of the foregoing embodiment, considering that the traditional calculation method of gear selection displacement offset only relies on the linear difference value of the limit position and the preset value, and does not consider the influence of the nonlinear characteristics of the mechanical system on the displacement, a dynamic gear selection offset correction mechanism based on the displacement curve is added. This mechanism constructs a displacement response curve, combines multiple dynamic sampling data, introduces a nonlinear compensation factor, accurately fits the deviation between the actual displacement and the theoretical value, and realizes dynamic correction.

[0040] The gear selection displacement response data is recorded while applying different duty cycle signals to generate a displacement-duty cycle curve.

[0041] According to the limit position displacement and the preset value, combined with the curve slope and the nonlinear compensation factor, the corrected offset is calculated:

[0042] In the formula, is the corrected offset; is the gear selection displacement limit position; is the preset gear selection displacement default value; is the nonlinear compensation factor; is the instantaneous slope of the displacement-duty cycle curve at the limit position; is the preset maximum slope threshold.

[0043] The calculation formula of the nonlinear compensation factor is:

[0044] In the formula, is the current sampling time; is the system dynamic response time constant.

[0045] is superimposed on the software set value to generate a temporary gear selection displacement instruction.

[0046] ​The verification shows that in the case of obtaining similar average error as the above-mentioned embodiment, the shift position error is reduced from ±1.2mm to ±0.4mm by nonlinear compensation, the shift failure rate is reduced from 8% to 2%, and the displacement standard deviation is reduced by 40% under temperature change. The results show that the dynamic correction mechanism effectively neutralizes the inherent friction hysteresis and gear clearance and other nonlinear disturbances of the mechanical system through the nonlinear compensation factor, so that the actual response of the shift position is more consistent with the theoretical expectation. Compared with the traditional linear difference method, the corrected shift displacement error range is significantly reduced, the adaptability of the shift logic to sensor installation deviation is improved, and the shift failure rate shows a systematic downward trend.

[0047] Example 3: On the basis of the foregoing examples, in order to avoid the problem that the traditional neutral position learning relies on single intermediate position sampling and is easily affected by mechanical assembly asymmetry, a multi-point weighted mean optimization algorithm for neutral displacement is added. The algorithm performs displacement sampling at three different shift intermediate positions, and gives dynamic weights based on displacement distribution variance to suppress the interference of local error on the reference position.

[0048] The neutral displacement sampling is performed at the left, center and right of the shift intermediate position respectively, the displacement values are obtained, and the weight coefficients are calculated according to the variance of three times sampling:

[0049] In the formula, is the weight coefficient; is the variance of the ith neutral displacement sampling; is a smoothing factor to prevent the denominator from being 0.

[0050] The normalized weight formula is:

[0051] In the formula, is the normalized weight coefficient, ensuring that the sum of all sampling weights is 1, ensuring the rationality of weighted average; is the dynamic weight coefficient of the jth neutral displacement sampling.

[0052] The weighted average generates the neutral self-learning displacement, and the neutral reference position formula is:

[0053] In the formula, is the final neutral reference position, which eliminates the local error caused by mechanical assembly asymmetry through weighted average, and improves the position accuracy; is the ith sampled neutral displacement value.

[0054] Assuming that the neutral displacement sampling is performed once in each of the three shift selection positions, the left bias position is 100.3 mm, the center position is 100.0 mm, and the right bias position is 100.5 mm, and the preset weight distribution is that the weight of the left bias position is 0.25, the weight of the center position is 0.50, and the weight of the right bias position is 0.25. The weighted reference position is calculated as follows:

[0055] The reference of the traditional method is:

[0056] The effect of the multi-point weighted mean optimization algorithm of the neutral displacement is shown in Table 1.

[0057] Table 1, effect summary of the multi-point weighted mean optimization algorithm of the neutral displacement Parameter Left bias position Center position Right bias position Single sampling value (mm) 100.3 100.0 100.5 Pre-set weight 0.25 0.50 0.25 Method Reference position (mm) Error (ideal value 100.0 mm) Error reduction ratio Conventional simple average method 100.27 +0.27 mm - Weighted average method 100.20 +0.20 mm 25.9% According to the experimental table, the weighted mean method reduces the reference position error from +0.27 mm of the traditional method to +0.20 mm, with an error reduction of 25.9%. It only needs single sampling and preset weight, without variance calculation, and is suitable for fast self-learning scenarios. By giving higher weight to the center position, the interference of left and right bias positions is directly suppressed. Experimental data show that, by the variance inverse weight distribution strategy, the algorithm effectively suppresses the influence of local assembly error and environmental interference on the neutral reference position. Compared with the traditional single-point sampling or simple average method, the neutral positioning error fluctuation range after the weighted mean optimization is significantly converged, and the repeatability and consistency of the reference position are improved. Especially in the asymmetric assembly or dynamic vibration scene, the algorithm gives higher weight to the low-variance sampling point, and systematically reduces the reference drift risk caused by mechanical asymmetry or instantaneous impact. The experiment further verifies that the algorithm significantly improves the long-term stability of the neutral self-learning result, and provides a reliable reference for the subsequent gear shifting process.

[0058] Those skilled in the art will appreciate that embodiments of the present application can be provided as methods, systems or computer program products. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable non-transitory storage media having computer-usable program code embodied in the medium.

[0059] The present application can provide computer program instructions to the management platform of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the management platform of the computer or other programmable data processing device generate a device for implementing the system.

[0060] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the function specified.

[0061] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified.

Claims

1. A gearbox gear self-learning system, characterized in that: include: a gear selection displacement deviation learning module, configured to push the gear selection displacement to a limit position by applying a negative gear selection duty cycle, calculate the gear selection displacement offset, and correct the gear selection value based on the offset; A neutral displacement learning module is configured to perform temporary neutral position learning and multiple neutral position samplings, and take the average value to generate a neutral self-learning displacement; The gear shift displacement learning module is used to cyclically switch the target gear and record the gear shift displacement, and then take the average value of multiple samplings to generate the gear shift self-learning displacement; The gear selection displacement self-learning module is used to control the gear selection displacement to the two ends of the gear shift position and take the middle value during the gear shift process, and generate the gear selection self-learning displacement after multiple sampling; Error elimination module uses multiple self-learning data to take the average value; Execution control unit, used to adjust the transmission shift logic according to the self-learning results.

2. The system according to claim 1, wherein: The gear selection displacement deviation learning module determines the leftmost limit position of the gear selection displacement through displacement limit detection, takes the difference between the limit position and the preset gear selection displacement default value as the gear selection displacement offset, and superimposes the gear selection value and the offset in real time to generate a temporary gear selection displacement.

3. The system according to claim 1, wherein: The neutral displacement learning module generates a temporary neutral position by shifting first and second gears and recording the average value of the shift displacement, and performs neutral displacement sampling at different intermediate positions of the selected gears, and takes the average value to obtain the neutral self-learning displacement.

4. The system according to claim 1, wherein: The gear shift displacement learning module switches step by step from the lowest gear to the highest gear, and then switches step by step. In each cycle, the last gear shift displacement of each gear is recorded, and the average value of the gear shift displacement is taken as the gear shift self-learning displacement.

5. The system according to claim 1, wherein: The gear selection displacement self-learning module pushes the gear selection displacement to the two end vertices of the current shift position, and takes the middle value as the single gear selection displacement self-learning value based on the displacement data of the two end vertices.

6. The system according to claim 1, wherein: The error elimination module records successful self-learning values ​​during the self-learning process of the shift displacement and the gear selection displacement, and optimizes the final self-learning displacement by averaging the values ​​after eliminating abnormal values.

7. The system according to claim 1, wherein: It also includes a gear selection offset correction module, which constructs a displacement response curve and combines multiple dynamic sampling data to fit the deviation between the actual displacement and the theoretical value. The corrected offset calculation formula is: Where, is the corrected offset; It is the limit position of gear selection displacement; The default value for the preset gear selection displacement; is the nonlinear compensation factor; is the instantaneous slope of the displacement-duty cycle curve at the extreme position; It is the preset maximum slope threshold.

8. The system according to claim 1, wherein: It also includes a weighted mean optimization module, which samples the displacement at different intermediate positions of the selected gear and assigns dynamic weights based on the variance of the displacement distribution. The neutral reference position formula is: Where, It is the neutral reference position; is the normalized weight coefficient; is the neutral displacement value of the i-th sampling.

9. A gearbox gear self-learning method, characterized by: The method is implemented based on the system according to any one of claims 1 to 8: The method comprises: Generate corrected gear selection displacement through extreme position detection and offset calculation; Determine the neutral reference position based on the average of multiple samplings; Generate shift self-learning displacement through gear cycle switching and displacement recording; Combine the shift position boundary detection and intermediate value calculation to generate the gear selection self-learning displacement; The final displacement parameters are optimized by averaging multiple self-learning data.

10. A computer-readable storage medium storing a computer program, wherein: The computer program executes the method according to claim 9 when executed.

Images