Dog clutch new energy gearbox shift performance prediction method and system
By combining a BP neural network prediction model with transmission physical parameters and shift performance testing, the impact problem caused by the lack of synchronization function of the dog clutch in new energy transmissions is solved, achieving accurate shift performance prediction and performance monitoring, which is suitable for new energy vehicles.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GETRAG JIANGXI TRANSMISSION
- Filing Date
- 2022-11-17
- Publication Date
- 2026-06-16
AI Technical Summary
In new energy vehicle transmissions, the lack of synchronization function in the dog-tooth clutch causes shocks due to speed differences, affecting durability and overall vehicle shifting performance.
By employing a BP neural network prediction model, combined with gearbox physical parameters and shift performance tests, and through dimensionality reduction and information redundancy removal, a time series of shift performance evaluation indicators is constructed to predict the shift performance of the dog clutch.
It achieves accurate prediction of the shifting performance of new energy vehicle transmissions, simplifies the model structure, is suitable for widespread application, predicts potential problems in advance, and improves overall vehicle performance.
Smart Images
Figure CN115773878B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of automotive technology, and in particular to a method and system for predicting the shifting performance of a new energy transmission with a dog-tooth clutch. Background Technology
[0002] In the automotive technology field, with the continuous development of new energy technologies, multi-speed hybrid or multi-speed pure electric transmissions have been attracting much attention from OEMs and end customers due to their superior power and economy. Among these, the dog clutch is a crucial component of the transmission. Its simple structure, convenient control, and excellent performance and cost advantages make it a promising candidate for application in new energy automatic transmissions.
[0003] However, because the dog clutch itself lacks a synchronization function, the motor needs to adjust its speed before shifting to reduce the speed difference between the two ends of the dog clutch to the desired value before shifting. Due to the instability of the software control and the existence of the speed difference, a certain impact can easily occur when the two ends of the dog clutch make contact. This impact is greatly affected by the torque and speed fluctuations during the shifting process. A large impact can damage the dog clutch, thereby affecting its durability and causing a deterioration in the overall vehicle shifting performance.
[0004] Therefore, in view of the shortcomings of the existing technology, it is necessary to provide a method that can predict the shifting process of a dog-tooth clutch. Summary of the Invention
[0005] Based on this, the purpose of the present invention is to provide a method and system for predicting the shifting performance of a new energy transmission with a dog clutch, so as to provide a method for predicting the performance of the dog clutch during the shifting process.
[0006] The first aspect of this invention proposes a method for predicting the shifting performance of a new energy vehicle transmission with a dog-tooth clutch, the method comprising:
[0007] The target gearbox is acquired, and the physical parameters of the gearbox corresponding to the current target gearbox are determined. The target gearbox includes a dog clutch.
[0008] The target gearbox is subjected to a shift performance test based on the physical parameters of the gearbox to obtain several corresponding test parameters, and the corresponding shift performance evaluation index is calculated based on the several test parameters.
[0009] A corresponding BP neural network prediction model is constructed based on the BP neural network and the shift performance evaluation index, and the shift performance of the target transmission is predicted based on the BP neural network prediction model.
[0010] The beneficial effects of this invention are as follows: First, a target gearbox is acquired, and its physical parameters are determined. Then, based on these physical parameters, the gearbox's shift performance is tested to obtain several corresponding test parameters. Principal component analysis is then used to calculate the corresponding shift performance evaluation index based on these test parameters. Finally, a corresponding BP neural network prediction model is constructed based on the BP neural network and the shift performance evaluation index. This model is then used to predict the shift performance of the target gearbox. This method allows for dimensionality reduction of key shift performance parameters and removal of information redundancy, constructing a time series of shift performance evaluation indicators and simplifying the structure of the BP neural network prediction model. Simultaneously, based on the time series of shift performance evaluation indicators and combined with the BP neural network, a corresponding BP neural network prediction model can be established. This model can be updated in real-time based on actual test results, enabling accurate prediction of the shift performance of gearboxes in new energy vehicles with dog-tooth transmissions. This achieves advance prediction functionality and is suitable for widespread promotion and use.
[0011] Preferably, the target transmission includes a shift hub, and the step of performing a shift performance test on the target transmission based on the transmission's physical parameters to obtain several corresponding test parameters includes:
[0012] The signal recognition points and shift hub angles generated by the shift hub at different stages of the shifting process of the target gearbox are identified, and the shifting process of the target gearbox is divided into the disengagement stage and the engagement stage based on the signal recognition points and the shift hub angle.
[0013] Several test signals generated by the target transmission during the disengagement and engagement phases are collected sequentially, and several corresponding test parameters are obtained based on the test signals.
[0014] Preferably, the step of calculating the corresponding shift performance evaluation index based on the plurality of test parameters includes:
[0015] Based on the aforementioned test parameters, a corresponding feature vector is constructed, and based on the feature vector, a corresponding feature matrix is constructed.
[0016] The feature matrix is linearly combined using principal component analysis, and the coefficient fusion index of the eigenvector corresponding to the largest eigenvalue in the linear combination is defined as the shift performance evaluation index.
[0017] Preferably, the step of constructing the corresponding BP neural network prediction model based on the BP neural network and the shift performance evaluation index includes:
[0018] The BP neural network is constructed through a preset program, and the shift performance evaluation index is selected into the BP neural network at equal intervals to construct the initial model of the BP neural network.
[0019] The initial BP neural network model is iteratively updated to generate the BP neural network prediction model.
[0020] Preferably, the method further includes:
[0021] Historical data of the full life cycle characteristic parameters of the target transmission are obtained, and the complete shift performance evaluation index of the target transmission during the full life cycle is calculated based on the historical data.
[0022] Calculate the target index value corresponding to the moment when the complete shift performance evaluation index is completely ineffective, and generate a prediction threshold corresponding to the target gearbox according to the target index value in a preset ratio;
[0023] Determine whether the shift performance evaluation index generated by the real-time prediction of the target gearbox reaches the prediction threshold.
[0024] If it is determined that the shift performance evaluation index generated by the real-time prediction of the target transmission reaches the prediction threshold, then it is determined that the current performance of the target transmission has begun to decline.
[0025] A second aspect of this invention provides a predictive system for the shifting performance of a new energy transmission with a dog-tooth clutch, the system comprising:
[0026] An acquisition module is used to acquire a target gearbox and determine the physical parameters of the gearbox corresponding to the current target gearbox, wherein the target gearbox includes a dog clutch;
[0027] The testing module is used to perform shift performance testing on the target transmission based on the transmission's physical parameters, to obtain several corresponding test parameters, and to calculate the corresponding shift performance evaluation index based on the several test parameters.
[0028] The prediction module is used to construct a corresponding BP neural network prediction model based on the BP neural network and the shift performance evaluation index, and to predict the shift performance of the target transmission based on the BP neural network prediction model.
[0029] In the aforementioned new energy transmission shifting performance prediction system with a dog-tooth clutch, the testing module is specifically used for:
[0030] The signal recognition points and shift hub angles generated by the shift hub at different stages of the shifting process of the target gearbox are identified, and the shifting process of the target gearbox is divided into the disengagement stage and the engagement stage based on the signal recognition points and the shift hub angle.
[0031] Several test signals generated by the target transmission during the disengagement and engagement phases are collected sequentially, and several corresponding test parameters are obtained based on the test signals.
[0032] In the aforementioned new energy transmission shifting performance prediction system with a dog-tooth clutch, the testing module is also specifically used for:
[0033] Based on the aforementioned test parameters, a corresponding feature vector is constructed, and based on the feature vector, a corresponding feature matrix is constructed.
[0034] The feature matrix is linearly combined using principal component analysis, and the coefficient fusion index of the eigenvector corresponding to the largest eigenvalue in the linear combination is defined as the shift performance evaluation index.
[0035] In the aforementioned new energy transmission shifting performance prediction system with a dog-tooth clutch, the prediction module is specifically used for:
[0036] The BP neural network is constructed through a preset program, and the shift performance evaluation index is selected into the BP neural network at equal intervals to construct the initial model of the BP neural network.
[0037] The initial BP neural network model is iteratively updated to generate the BP neural network prediction model.
[0038] The aforementioned new energy vehicle transmission shift performance prediction system with a dog-tooth clutch further includes a judgment module, which is specifically used for:
[0039] Historical data of the full life cycle characteristic parameters of the target transmission are obtained, and the complete shift performance evaluation index of the target transmission during the full life cycle is calculated based on the historical data.
[0040] Calculate the target index value corresponding to the moment when the complete shift performance evaluation index is completely ineffective, and generate a prediction threshold corresponding to the target gearbox according to the target index value in a preset ratio;
[0041] Determine whether the shift performance evaluation index generated by the real-time prediction of the target gearbox reaches the prediction threshold.
[0042] If it is determined that the shift performance evaluation index generated by the real-time prediction of the target transmission reaches the prediction threshold, then it is determined that the current performance of the target transmission has begun to decline.
[0043] A third aspect of the present invention provides a computer, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the shift performance prediction method for a new energy transmission with a dog-tooth clutch as described above.
[0044] The fourth aspect of this invention provides a storage medium storing a computer program that, when executed by a processor, implements the shift performance prediction method for a new energy transmission with a dog-tooth clutch as described above.
[0045] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description
[0046] Figure 1 A flowchart of the method for predicting the shift performance of a new energy transmission with a dog-tooth clutch provided in the first embodiment of the present invention;
[0047] Figure 2 The diagram shows the structural block diagram of the new energy transmission shifting performance prediction system with a dog-tooth clutch provided in the sixth embodiment of the present invention.
[0048] The following detailed description, in conjunction with the accompanying drawings, will further illustrate the present invention. Detailed Implementation
[0049] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Several embodiments of the invention are illustrated in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
[0050] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there may be an intervening component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there may be an intervening component. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.
[0051] Unless otherwise defined, 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. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.
[0052] Please see Figure 1 The diagram illustrates a method for predicting the shifting performance of a new energy vehicle transmission with a dog-tooth clutch, provided in the first embodiment of the present invention. This method can reduce the dimensionality of key parameters related to shifting performance and remove information redundancy, constructing a time series of shifting performance evaluation indicators and simplifying the structure of the BP neural network prediction model. Simultaneously, based on the time series of shifting performance evaluation indicators and combined with a BP neural network, a corresponding BP neural network prediction model can be established. This BP neural network prediction model can be updated in real time according to actual test results, thereby enabling accurate prediction of the shifting performance of the transmission in a new energy vehicle with a dog-tooth clutch. This achieves the function of advance prediction and is suitable for widespread promotion and use.
[0053] Specifically, the method for predicting the shift performance of a new energy transmission with a dog-tooth clutch provided in this embodiment includes the following steps:
[0054] Step S10: Obtain the target gearbox and determine the physical parameters of the gearbox corresponding to the current target gearbox, wherein the target gearbox includes a dog clutch;
[0055] Specifically, in this embodiment, it should first be noted that the method for predicting the shifting performance of a new energy transmission with a dog clutch provided in this embodiment is specifically applied to a hybrid transmission equipped with a dog clutch. It is used to predict the shifting performance of the hybrid transmission equipped with a dog clutch in order to understand the performance of the hybrid transmission equipped with a dog clutch in real time during operation. The dog clutch is not limited to a clutch, but is also used in the shifting structure.
[0056] Therefore, in this step, it should be noted that in order to accurately achieve the prediction effect, this step will first obtain a target transmission, namely the hybrid transmission with the dog clutch installed mentioned above. Furthermore, it will obtain the various physical parameters of the hybrid transmission with the dog clutch installed. Specifically, the physical parameters of the transmission may include physical parameters such as the speed ratio and the moment of inertia of each rotating component.
[0057] Step S20: Perform a shift performance test on the target transmission based on the transmission's physical parameters to obtain several corresponding test parameters, and calculate the corresponding shift performance evaluation index based on the several test parameters.
[0058] Furthermore, in this embodiment, it should be noted that after obtaining the required target gearbox and its corresponding physical parameters through the above steps, this step will further perform a corresponding shift performance test on the current target gearbox based on the obtained physical parameters of the gearbox, so as to obtain several corresponding test parameters.
[0059] Based on this, the shift performance evaluation index corresponding to the current target gearbox is calculated according to the test parameters obtained in real time.
[0060] Step S30: Construct a corresponding BP neural network prediction model based on the BP neural network and the shift performance evaluation index, and predict the shift performance of the target transmission based on the BP neural network prediction model.
[0061] Finally, it should be noted in this step that after obtaining the shift performance evaluation index through the above steps, this step will further construct the required BP neural network prediction model based on the pre-set BP neural network and the currently obtained real-time shift performance evaluation index. On this basis, the corresponding shift performance of the current target transmission can be predicted by simply using this BP neural network prediction model.
[0062] In practice, the process involves acquiring the target gearbox and determining its physical parameters. Further, based on these physical parameters, a shift performance test is conducted on the target gearbox to obtain several corresponding test parameters. These test parameters are then used to calculate corresponding shift performance evaluation indicators. Finally, a BP neural network prediction model is constructed based on the BP neural network and the shift performance evaluation indicators. This model is then used to predict the shift performance of the target gearbox. This method allows for dimensionality reduction of key shift performance parameters, removal of information redundancy, and the construction of a time series of shift performance evaluation indicators, simplifying the structure of the BP neural network prediction model. Simultaneously, based on the time series of shift performance evaluation indicators and combined with the BP neural network, a corresponding BP neural network prediction model can be established. This model can be updated in real-time based on actual test results, enabling accurate prediction of the shift performance of gearboxes in new energy vehicles with dog-tooth transmissions. This advance prediction function is suitable for widespread adoption and use.
[0063] It should be noted that the above implementation process is only to illustrate the feasibility of this application, but it does not mean that the shift performance prediction method of the new energy transmission with a dog clutch in this application has only the above-mentioned single implementation process. On the contrary, as long as the shift performance prediction method of the new energy transmission with a dog clutch in this application can be implemented, it can be included in the feasible implementation scheme of this application.
[0064] In summary, the shift performance prediction method for new energy vehicle transmissions with dog-tooth clutches provided in the above embodiments of the present invention can reduce the dimensionality of key parameters of various shift performance aspects and remove information redundancy, constructing a time series of shift performance evaluation indicators and simplifying the structure of the BP neural network prediction model. Simultaneously, based on the time series of shift performance evaluation indicators and combined with the BP neural network, a corresponding BP neural network prediction model can be established. This BP neural network prediction model can be updated in real time according to actual test results, thereby achieving accurate prediction of the shift performance of transmissions in new energy vehicles with dog-tooth clutches, realizing the function of advance prediction, and is suitable for widespread promotion and use.
[0065] The second embodiment of the present invention also provides a method for predicting the shift performance of a new energy vehicle transmission with a dog clutch. The difference between the method for predicting the shift performance of a new energy vehicle transmission with a dog clutch provided in this embodiment and the method for predicting the shift performance of a new energy vehicle transmission with a dog clutch provided in the first embodiment is as follows:
[0066] In this embodiment, it should be noted that the target gearbox includes a shift hub, and the step of performing a shift performance test on the target gearbox based on the gearbox's physical parameters to obtain several corresponding test parameters includes:
[0067] The signal recognition points and shift hub angles generated by the shift hub at different stages of the shifting process of the target gearbox are identified, and the shifting process of the target gearbox is divided into the disengagement stage and the engagement stage based on the signal recognition points and the shift hub angle.
[0068] Several test signals generated by the target transmission during the disengagement and engagement phases are collected sequentially, and several corresponding test parameters are obtained based on the test signals.
[0069] Specifically, in this embodiment, it should be noted that this embodiment is based on a three-dimensional vibration acceleration sensor, a hybrid transmission with a dog clutch, a functional test bench, and an ETAS data acquisition device. The hybrid transmission with a dog clutch is bolted to the mating surface of the engine housing. The output end of this hybrid transmission assembly is mounted on the drive motor shaft of the test bench via a flange and corresponding bolts. The test bench provides power for speed or torque control to the output end of the hybrid transmission. The aforementioned three-dimensional vibration sensor is glued to the bottom housing of the hybrid transmission assembly with the dog clutch to collect vibrations generated by the transmission housing during gear shifting. Specifically, the transmission control unit signals and the data from the three-dimensional vibration sensor are transmitted to a computer via the aforementioned ETAS data acquisition device for collection, recording, and storage in real time.
[0070] Furthermore, the signal recognition points and shift hub angles generated by the shift hub in the current hybrid transmission with a dog clutch at different stages of the current target transmission shift process are identified, and the shift process of the target transmission is divided into the disengagement stage and the engagement stage based on the signal recognition points and the shift hub angle.
[0071] Furthermore, several test signals generated by the current target transmission during the aforementioned disengagement and engagement phases are sequentially collected, and several corresponding test parameters are obtained based on these test signals.
[0072] It should be noted that the signals to be collected in this embodiment include gearbox housing vibration signal, current gear signal, target gear signal, shift hub angle signal, input shaft speed signal, output shaft speed signal, drive motor torque signal, and shift hub status signal. The corresponding test parameters obtained are: shift noise, disengagement torque, disengagement time, engagement torque, engagement time, actual speed difference between the two ends of the dog tooth, maximum input shaft speed gradient, maximum engagement power, engagement energy, and drive motor compensation torque.
[0073] The method for obtaining shift noise is as follows: the vibration acceleration signal of the gearbox housing during shifting is converted into a decibel value. The average value within the time window from 0.15s to 0.05s during the peak noise time is calculated as the ambient background noise. The difference between the peak value and the background noise is calculated to represent the shift noise.
[0074] The method for obtaining the disengagement torque is as follows: calculate the torque caused by the disengagement of the dog clutch at the input shaft end during the disengagement phase.
[0075] The method for obtaining the disengagement time is as follows: calculate the time taken from disengaging the dog clutch to reaching neutral.
[0076] The method for obtaining the shift torque is as follows: calculate the torque generated at the input shaft end during the shift phase from the pre-contact of the dog clutch to the completion of the shift by entering the tooth groove;
[0077] Torque calculation formula: M = alpha * J - M_motor
[0078] Where alpha represents the angular acceleration of the input shaft; J represents the equivalent inertia at the input shaft; and M_motor represents the torque of the shift motor converted to the input shaft.
[0079] The shifting time is obtained by calculating the time taken from the pre-contact of the dog-tooth clutch to its entry into the gear slot to complete the shift.
[0080] The method for obtaining the actual speed difference between the two ends of the dog tooth is to calculate the speed difference between the two ends of the dog tooth clutch at the moment of pre-contact during gear engagement.
[0081] The method for obtaining the maximum speed gradient of the input shaft is as follows: calculate the maximum angular acceleration of the input shaft speed during the process from the moment of pre-contact of the dog clutch during gear shifting to the moment it enters the tooth groove to complete the gear shift.
[0082] The maximum power for gear shifting is obtained by calculating the maximum power of the dog clutch from the moment of pre-contact during gear shifting until it enters the gear slot and completes the shift. The calculation formula is as follows:
[0083] P max =max(M*ω)
[0084] Where M represents the torque caused at the input shaft during the gear shifting process, and ω represents the angular velocity of the input shaft.
[0085] The method for obtaining the gear shift energy is as follows: calculate the energy generated by the dog clutch during the gear shift collision pre-contact moment until it enters the gear groove to complete the gear shift. The calculation formula is as follows:
[0086]
[0087] Where T_start represents the pre-contact moment of the gear shift collision, and T_end represents the moment of entering the gear slot and completing the gear shift.
[0088] The method for obtaining the drive motor compensation torque is as follows: calculate the maximum torque of the drive motor from the moment of pre-contact during gear shifting to the moment of entering the gear slot and completing the gear shift.
[0089] It should be noted that the method provided in the second embodiment of the present invention has the same implementation principle and some technical effects as the first embodiment. For the sake of brevity, any parts not mentioned in this embodiment can be referred to the corresponding content provided in the first embodiment.
[0090] In summary, the shift performance prediction method for new energy vehicle transmissions with dog-tooth clutches provided in the above embodiments of the present invention can reduce the dimensionality of key parameters of various shift performance aspects and remove information redundancy, constructing a time series of shift performance evaluation indicators and simplifying the structure of the BP neural network prediction model. Simultaneously, based on the time series of shift performance evaluation indicators and combined with the BP neural network, a corresponding BP neural network prediction model can be established. This BP neural network prediction model can be updated in real time according to actual test results, thereby achieving accurate prediction of the shift performance of transmissions in new energy vehicles with dog-tooth clutches, realizing the function of advance prediction, and is suitable for widespread promotion and use.
[0091] The third embodiment of the present invention also provides a method for predicting the shift performance of a new energy vehicle transmission with a dog clutch. The difference between the method for predicting the shift performance of a new energy vehicle transmission with a dog clutch provided in this embodiment and the method for predicting the shift performance of a new energy vehicle transmission with a dog clutch provided in the first embodiment is as follows:
[0092] Furthermore, in this embodiment, it should be noted that the steps for calculating the corresponding shift performance evaluation index based on the aforementioned test parameters include:
[0093] Based on the aforementioned test parameters, a corresponding feature vector is constructed, and based on the feature vector, a corresponding feature matrix is constructed.
[0094] The feature matrix is linearly combined using principal component analysis, and the coefficient fusion index of the eigenvector corresponding to the largest eigenvalue in the linear combination is defined as the shift performance evaluation index.
[0095] Specifically, in this embodiment, it should be noted that after obtaining several test parameters through the above steps, this embodiment will further calculate the current several test parameters to construct a corresponding feature vector for each gear shift:
[0096] x i =[x i1 x i2 , ..., x i10 ]
[0097] Where i represents the number of gear shifts, and further, by summing the feature vectors of all tested gear shift processes, a gear shift feature matrix is constructed:
[0098]
[0099] element x in X ij Let j represent the physical quantity of the i-th gear shift.
[0100] Furthermore, in this embodiment, the above X is linearly combined through principal component transformation:
[0101]
[0102] Make the coefficient l ij satisfy:
[0103] (1)
[0104] (2) Linear combination y i With y i (i≠j) are mutually unrelated;
[0105] (3) Make y1 = x1, x2, ..., x p The maximum variance of all linear combinations, where y2 is x1, x2, ..., x1, which are uncorrelated with y1. p The linear combination with the largest set variance; y p For y1, y2, ..., y p-1 Unrelated x1, x2, ..., x p The one with the largest variance among all linear combinations.
[0106] The obtained principal component information is the i-th eigenvalue λ of the covariance matrix of the original feature information X. i The corresponding eigenvector l i =(l 1i , l 2i , ..., l pi ) represents a linear combination of coefficients. The coefficient fusion index of the eigenvector corresponding to the largest eigenvalue is taken as the evaluation index for shift performance, thus achieving the evaluation of shift performance.
[0107] It should be noted that the method provided in the second embodiment of the present invention has the same implementation principle and some technical effects as the first embodiment. For the sake of brevity, any parts not mentioned in this embodiment can be referred to the corresponding content provided in the first embodiment.
[0108] In summary, the shift performance prediction method for new energy vehicle transmissions with dog-tooth clutches provided in the above embodiments of the present invention can reduce the dimensionality of key parameters of various shift performance aspects and remove information redundancy, constructing a time series of shift performance evaluation indicators and simplifying the structure of the BP neural network prediction model. Simultaneously, based on the time series of shift performance evaluation indicators and combined with the BP neural network, a corresponding BP neural network prediction model can be established. This BP neural network prediction model can be updated in real time according to actual test results, thereby achieving accurate prediction of the shift performance of transmissions in new energy vehicles with dog-tooth clutches, realizing the function of advance prediction, and is suitable for widespread promotion and use.
[0109] The fourth embodiment of the present invention also provides a method for predicting the shift performance of a new energy vehicle transmission with a dog clutch. The difference between the method for predicting the shift performance of a new energy vehicle transmission with a dog clutch provided in this embodiment and the method for predicting the shift performance of a new energy vehicle transmission with a dog clutch provided in the first embodiment is as follows:
[0110] In addition, in this embodiment, it should be noted that the steps of constructing the corresponding BP neural network prediction model based on the BP neural network and the shift performance evaluation index include:
[0111] The BP neural network is constructed through a preset program, and the shift performance evaluation index is selected into the BP neural network at equal intervals to construct the initial model of the BP neural network.
[0112] The initial BP neural network model is iteratively updated to generate the BP neural network prediction model.
[0113] Specifically, in this embodiment, it should be noted that the BP neural network provided in this embodiment sequentially includes an input layer, a hidden layer, and an output layer. It should be pointed out that the input and output layers are configured to take the time intervals of the aforementioned shift performance evaluation time series indicators as E(E1, E2, E3) as values. 1+t E 1+2t , ..., E 1+nt E 1+(n+1)t ).
[0114] Where t represents the time interval. The index at time 1+(n+1)t is used as the final output, and the indices at the first n time intervals are used as input. A nonlinear function is established using normalization. This function passes through 10 hidden layers in sequence, and Bayesian regularization and gradient descent are used to quickly find the weight w and the deviation b between each layer. Bayesian regularization and gradient descent are present in each hidden layer. Each layer needs to perform calculations to find the weight w and the deviation b of the current layer and input the results into the next layer for further calculations. This process continues until k layers (k=10 in this embodiment) have been processed, and the result of the BP neural network prediction model is obtained.
[0115] Based on this, the output of the above BP neural network prediction model is compared with the actual shift performance index. If the mean square error is within 0.01, it indicates that the output is effective and reliable. If the mean square error of the predicted value of the BP neural network prediction model does not meet the requirements, the output will be passed back layer by layer and retrained. At the same time, the weights w between each layer and the deviation b of the current layer are adjusted. This process is repeated until the output score of the BP neural network prediction model with a mean square error within 0.01 is obtained.
[0116] It should be noted that the method provided in the second embodiment of the present invention has the same implementation principle and some technical effects as the first embodiment. For the sake of brevity, any parts not mentioned in this embodiment can be referred to the corresponding content provided in the first embodiment.
[0117] In summary, the shift performance prediction method for new energy vehicle transmissions with dog-tooth clutches provided in the above embodiments of the present invention can reduce the dimensionality of key parameters of various shift performance aspects and remove information redundancy, constructing a time series of shift performance evaluation indicators and simplifying the structure of the BP neural network prediction model. Simultaneously, based on the time series of shift performance evaluation indicators and combined with the BP neural network, a corresponding BP neural network prediction model can be established. This BP neural network prediction model can be updated in real time according to actual test results, thereby achieving accurate prediction of the shift performance of transmissions in new energy vehicles with dog-tooth clutches, realizing the function of advance prediction, and is suitable for widespread promotion and use.
[0118] The fifth embodiment of the present invention also provides a method for predicting the shift performance of a new energy vehicle transmission with a dog clutch. The difference between the method for predicting the shift performance of a new energy vehicle transmission with a dog clutch provided in this embodiment and the method for predicting the shift performance of a new energy vehicle transmission with a dog clutch provided in the first embodiment is as follows:
[0119] In addition, it should be noted in this embodiment that the above method also includes:
[0120] Historical data of the full life cycle characteristic parameters of the target transmission are obtained, and the complete shift performance evaluation index of the target transmission during the full life cycle is calculated based on the historical data.
[0121] Calculate the target index value corresponding to the moment when the complete shift performance evaluation index is completely ineffective, and generate a prediction threshold corresponding to the target gearbox according to the target index value in a preset ratio;
[0122] Determine whether the shift performance evaluation index generated by the real-time prediction of the target gearbox reaches the prediction threshold.
[0123] If it is determined that the shift performance evaluation index generated by the real-time prediction of the target transmission reaches the prediction threshold, then it is determined that the current performance of the target transmission has begun to decline.
[0124] Specifically, in this embodiment, it should be noted that by setting a prediction threshold, the shift performance evaluation index of the target gearbox can be monitored in real time and effectively. When it is determined that the shift performance evaluation index generated by the real-time prediction of the current target gearbox reaches the current prediction threshold, it is immediately determined that the performance of the current target gearbox is declining, thereby immediately reminding the staff to check the gearbox to eliminate potential safety hazards.
[0125] It should be noted that the method provided in the second embodiment of the present invention has the same implementation principle and some technical effects as the first embodiment. For the sake of brevity, any parts not mentioned in this embodiment can be referred to the corresponding content provided in the first embodiment.
[0126] In summary, the shift performance prediction method for new energy vehicle transmissions with dog-tooth clutches provided in the above embodiments of the present invention can reduce the dimensionality of key parameters of various shift performance aspects and remove information redundancy, constructing a time series of shift performance evaluation indicators and simplifying the structure of the BP neural network prediction model. Simultaneously, based on the time series of shift performance evaluation indicators and combined with the BP neural network, a corresponding BP neural network prediction model can be established. This BP neural network prediction model can be updated in real time according to actual test results, thereby achieving accurate prediction of the shift performance of transmissions in new energy vehicles with dog-tooth clutches, realizing the function of advance prediction, and is suitable for widespread promotion and use.
[0127] Please see Figure 2 The figure shows a new energy transmission shifting performance prediction system with a dog-tooth clutch provided in the sixth embodiment of the present invention. The system includes:
[0128] The acquisition module 12 is used to acquire the target gearbox and determine the physical parameters of the gearbox corresponding to the current target gearbox, wherein the target gearbox includes a dog clutch;
[0129] The test module 22 is used to perform shift performance tests on the target transmission based on the transmission physical parameters, so as to obtain several corresponding test parameters and calculate the corresponding shift performance evaluation index based on the several test parameters.
[0130] The prediction module 32 is used to construct a corresponding BP neural network prediction model based on the BP neural network and the shift performance evaluation index, and to predict the shift performance of the target gearbox based on the BP neural network prediction model.
[0131] In the aforementioned new energy transmission shifting performance prediction system with a dog-tooth clutch, the test module 22 is specifically used for:
[0132] The signal recognition points and shift hub angles generated by the shift hub at different stages of the shifting process of the target gearbox are identified, and the shifting process of the target gearbox is divided into the disengagement stage and the engagement stage based on the signal recognition points and the shift hub angle.
[0133] Several test signals generated by the target transmission during the disengagement and engagement phases are collected sequentially, and several corresponding test parameters are obtained based on the test signals.
[0134] In the aforementioned new energy transmission shifting performance prediction system with a dog-tooth clutch, the test module 22 is also specifically used for:
[0135] Based on the aforementioned test parameters, a corresponding feature vector is constructed, and based on the feature vector, a corresponding feature matrix is constructed.
[0136] The feature matrix is linearly combined using principal component analysis, and the coefficient fusion index of the eigenvector corresponding to the largest eigenvalue in the linear combination is defined as the shift performance evaluation index.
[0137] In the aforementioned new energy transmission shifting performance prediction system with a dog-tooth clutch, the prediction module 32 is specifically used for:
[0138] The BP neural network is constructed through a preset program, and the shift performance evaluation index is selected into the BP neural network at equal intervals to construct the initial model of the BP neural network.
[0139] The initial BP neural network model is iteratively updated to generate the BP neural network prediction model.
[0140] In the aforementioned new energy transmission shift performance prediction system with a dog-tooth clutch, the new energy transmission shift performance prediction system with a dog-tooth clutch further includes a judgment module 42, which is specifically used for:
[0141] Historical data of the full life cycle characteristic parameters of the target transmission are obtained, and the complete shift performance evaluation index of the target transmission during the full life cycle is calculated based on the historical data.
[0142] Calculate the target index value corresponding to the moment when the complete shift performance evaluation index is completely ineffective, and generate a prediction threshold corresponding to the target gearbox according to the target index value in a preset ratio;
[0143] Determine whether the shift performance evaluation index generated by the real-time prediction of the target gearbox reaches the prediction threshold.
[0144] If it is determined that the shift performance evaluation index generated by the real-time prediction of the target transmission reaches the prediction threshold, then it is determined that the current performance of the target transmission has begun to decline.
[0145] The seventh embodiment of the present invention provides a computer, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the shift performance prediction method for a new energy transmission with a dog-tooth clutch as provided in the above embodiments.
[0146] The eighth embodiment of the present invention provides a storage medium storing a computer program thereon, which, when executed by a processor, implements the shift performance prediction method for a new energy transmission with a dog-tooth clutch as provided in the above embodiments.
[0147] In summary, the shift performance prediction method and system for new energy vehicle transmissions with dog-tooth clutches provided in the above embodiments of the present invention can reduce the dimensionality of key parameters of various shift performance parameters and remove information redundancy, constructing a time series of shift performance evaluation indicators and simplifying the structure of the BP neural network prediction model. Simultaneously, based on the time series of shift performance evaluation indicators and combined with the BP neural network, a corresponding BP neural network prediction model can be established. This BP neural network prediction model can be updated in real time according to actual test results, thereby achieving accurate prediction of the shift performance of transmissions in new energy vehicles with dog-tooth clutches, realizing the function of advance prediction, and is suitable for widespread promotion and use.
[0148] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.
[0149] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.
[0150] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.
[0151] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.
[0152] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.
[0153] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.
Claims
1. A method for predicting the shifting performance of a new energy gearbox with dog clutch, characterized in that, The method includes: Obtain the target transmission and determine the transmission physical parameters corresponding to the current target transmission; The target gearbox is subjected to a shift performance test based on the physical parameters of the gearbox to obtain several corresponding test parameters, and the corresponding shift performance evaluation index is calculated based on the several test parameters. A corresponding BP neural network prediction model is constructed based on the BP neural network and the shift performance evaluation index, and the shift performance of the target transmission is predicted based on the BP neural network prediction model. The target transmission includes a shift hub, and the step of performing a shift performance test on the target transmission based on the transmission's physical parameters to obtain several corresponding test parameters includes: The signal recognition points and shift hub angles generated by the shift hub at different stages of the shifting process of the target gearbox are identified, and the shifting process of the target gearbox is divided into the disengagement stage and the engagement stage based on the signal recognition points and the shift hub angle. Several test signals generated by the target transmission during the disengagement and engagement phases are collected sequentially, and several corresponding test parameters are obtained based on the test signals. The step of calculating the corresponding shift performance evaluation index based on the test parameters includes: Based on the aforementioned test parameters, a corresponding feature vector is constructed, and based on the feature vector, a corresponding feature matrix is constructed. The feature matrix is linearly combined using principal component analysis, and the coefficient fusion index of the eigenvector corresponding to the largest eigenvalue in the linear combination is defined as the shift performance evaluation index.
2. The method according to claim 1, wherein the method is characterized by: The steps for constructing the corresponding BP neural network prediction model based on the BP neural network and the shift performance evaluation index include: The BP neural network is constructed through a preset program, and the shift performance evaluation index is selected at equal intervals into the BP neural network to construct the initial model of the BP neural network. The initial BP neural network model is iteratively updated to generate the BP neural network prediction model.
3. The dog clutch new energy transmission gear shifting performance prediction method according to claim 1, characterized in that: The method further includes: Historical data of the full life cycle characteristic parameters of the target transmission are obtained, and the complete shift performance evaluation index of the target transmission during the full life cycle is calculated based on the historical data. Calculate the target index value corresponding to the moment when the complete shift performance evaluation index is completely ineffective, and generate a prediction threshold corresponding to the target gearbox according to the target index value in a preset ratio; Determine whether the shift performance evaluation index generated by the real-time prediction of the target gearbox reaches the prediction threshold. If it is determined that the shift performance evaluation index generated by the real-time prediction of the target transmission reaches the prediction threshold, then it is determined that the current performance of the target transmission has begun to decline.
4. A new energy gearbox shift performance prediction system with dog clutch, characterized in that, For implementing the method for predicting the shift performance of a new energy transmission with a dog-tooth clutch as described in any one of claims 1 to 3, the system comprises: An acquisition module is used to acquire a target transmission and determine the transmission physical parameters corresponding to the current target transmission, wherein the target transmission includes a shift hub; The testing module is used to perform shift performance testing on the target transmission based on the transmission's physical parameters, to obtain several corresponding test parameters, and to calculate the corresponding shift performance evaluation index based on the several test parameters. The prediction module is used to construct a corresponding BP neural network prediction model based on the BP neural network and the shift performance evaluation index, and to predict the shift performance of the target transmission based on the BP neural network prediction model.
5. A computer comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method for predicting the shifting performance of a new energy transmission with a dog-tooth clutch as described in any one of claims 1 to 3.
6. A storage medium having stored thereon a computer program, characterized in that When executed by the processor, the program implements the method for predicting the shift performance of a new energy transmission with a dog-tooth clutch as described in any one of claims 1 to 3.