Temperature monitoring method, over-temperature protection method, server, vehicle and product

Abstract

The invention provides a temperature monitoring method, an over-temperature protection method, a server, a vehicle and a product, the method is applied to the technical field of vehicles, and the method comprises the following steps: obtaining historical operation data of each vehicle; extracting temperature related parameters and temperature measured values of the wet clutch in the historical operation data; generating a training data set according to the temperature related parameters and the temperature measured values of the wet clutch of each vehicle; and training by using the training data set to obtain a temperature simulation model of the wet clutch, and monitoring the current temperature of the wet clutch based on the trained temperature simulation model. According to the method, the temperature of the wet clutch can be accurately monitored in real time based on an artificial intelligence dynamic neural network model; according to the method, the faults such as ablation damage of clutch hardware caused by overhigh temperature can be effectively avoided, so that a protection method for overtemperature of the wet clutch and a control method for reducing the temperature of the wet clutch are formed, and the safety of vehicle driving and the smoothness of gear shifting are improved.

Description

Technical Field

[0001] The present application relates to the technical field of vehicles, and more particularly, to a temperature monitoring method, an over-temperature protection method, a server, a vehicle, and a product in the field of wet clutches of vehicles. Background Art

[0002] The clutch is an important part of the automotive transmission system. The automatic transmission is divided into two categories: dry and wet dual clutches. The two sets of clutch discs of the wet clutch are sealed in an oil sump and can transmit torque under a long-time slip friction state, which is the preferred configuration of the current automatic transmission. However, the friction pairs of the wet clutch generate heat during frequent engagement, and even phenomena such as ablation, cracks, gluing, warping, and fatigue damage of the friction plates occur, further affecting the vehicle starting and driving performance as well as the shifting characteristics. Therefore, temperature monitoring of the wet clutch is an important task.

[0003] The traditional method usually uses numerical analysis methods or multiple experiments to measure the temperature of the wet clutch. However, in the related art, due to the structural characteristics and working characteristics of the clutch, the cost of actually measuring the clutch temperature through experiments is high and the measurement is difficult; the traditional numerical analysis method is prone to reduce the simulation accuracy due to the cumbersome modeling process and the need for accurate model data and heat transfer parameters to simulate the actual working conditions, resulting in the vehicle being unable to monitor the temperature of the wet clutch in real time and reducing the accuracy of monitoring the clutch temperature. Summary of the Invention

[0004] The present application provides a temperature monitoring method, an over-temperature protection method, a server, a vehicle, and a product. The method can accurately and real-time monitor the temperature of the wet clutch based on the dynamic neural network model of artificial intelligence; it can effectively avoid failures such as ablation and damage of the clutch hardware caused by too high temperature, thereby forming a protection method for the wet clutch when over-temperature and a control method for reducing the temperature of the wet clutch, improving the safety of vehicle driving and the smoothness of shifting.

[0005] In a first aspect, a temperature monitoring method is provided. The method includes: obtaining the historical operation data of each vehicle; extracting the temperature-related parameters and the measured temperature values of the wet clutch in the historical operation data; generating a training data set according to the temperature-related parameters and the measured temperature values of each vehicle; training a temperature simulation model of the wet clutch using the training data set, and monitoring the current temperature of the wet clutch based on the trained temperature simulation model.

[0006] Through the above technical solution, the embodiment of the present application can generate a training data set based on the temperature-related parameters and measured temperature values of each vehicle by using a dynamic neural network model of artificial intelligence to train the temperature simulation model of the wet clutch, so as to accurately and real-time monitor the temperature of the wet clutch; it can effectively avoid faults such as ablation damage of the clutch hardware caused by too high temperature, thereby forming a protection method for over-temperature of the wet clutch and a control method for reducing the temperature of the wet clutch, improving the driving safety of the vehicle and the smoothness of gear shifting.

[0007] In combination with the first aspect, in some possible implementation manners, training the temperature simulation model of the wet clutch by using the training data set includes: iteratively training the temperature simulation model according to the training data set, wherein, in each iterative training process, selecting a target number of training samples from the training data set to train the temperature simulation model, the temperature-related parameters of each vehicle are used as training samples, and the measured temperature value is used as the temperature true value corresponding to the training sample; obtaining the temperature prediction value of each training sample, calculating the error value of each training sample according to the temperature prediction value and the temperature true value of each training sample, and calculating the root mean square error according to the error value of each training sample; if the root mean square error meets the preset error condition, stop the iterative training of the temperature simulation model, otherwise adjust the structural parameters and training parameters of the temperature simulation model and continue training.

[0008] Through the above technical solution, the embodiment of the present application can make the model continuously learn and adjust through iterative training of the model, so as to more accurately simulate the temperature behavior of the wet clutch under different working conditions. This training method allows the model to gradually approach the real situation, improve the prediction accuracy, and thus better reflect the actual temperature change of the clutch.

[0009] In combination with the first aspect and the above implementation manner, in some possible implementation manners, the structural parameters include the number of hidden layers, the number of units in each layer, the unit type, and the activation function. The first layer is defined as a long short-term memory neural network, and the remaining layers are defined as densely connected layers. An activation function is set between layers; the training parameters include at least one of the number of iterations, the learning rate, and the batch size.

[0010] Through the above technical solutions, the embodiments of the present application can improve the model adaptability and prediction accuracy, optimize the training process and the model generalization ability. This technical solution can realize the real-time monitoring and control of the wet clutch temperature without making major modifications to the vehicle hardware, reducing the technical implementation cost. The training and optimization process of the model is completed at the software level, which is convenient for adjustment and optimization and has good versatility for wet clutches of different models. Through real-time and accurate temperature monitoring, when the clutch temperature exceeds the safety threshold, the protection mechanism can be quickly triggered, such as adjusting the coolant flow or reducing the engine torque, effectively preventing hardware damage caused by overheating of the clutch, thus maintaining the driving safety of the vehicle and the long-term stability of the transmission system. At the same time, the power performance and shift smoothness of the vehicle are also guaranteed.

[0011] Combined with the first aspect and the above implementation manners, in some possible implementation manners, each time the structural parameters are adjusted, the number of hidden layers is increased within the first interval based on the first preset step size, and the number of units in each layer is increased within the second interval based on the second preset step size.

[0012] Through the above technical solutions, the embodiments of the present application can improve the model flexibility and adaptability. By dynamically adjusting the number of hidden layers and the number of units in each layer, the model can more flexibly adapt to data and task requirements of different complexities. Increasing the number of hidden layers can improve the expression ability of the model, enabling the model to learn deeper abstract features in the data. Increasing the number of units in each layer enhances the feature learning ability of the model at each level. The combination of the two enables the model to more accurately capture the law of temperature change when facing the complex and changeable wet clutch temperature prediction task, optimize the model performance and training efficiency, promote the model generalization ability, and realize automatic and intelligent parameter tuning.

[0013] Combined with the first aspect and the above implementation manners, in some possible implementation manners, the temperature-related parameters and the measured temperature values of the wet clutch in the historical operation data are extracted, including: performing data interpolation on the historical operation data; performing data correlation analysis on the interpolated historical operation data, and determining the temperature-related parameters of the wet clutch according to the analysis results; performing normalization processing on the temperature-related parameters of the wet clutch and performing denormalization processing on the measured temperature values.

[0014] Through the above technical solutions, the embodiments of the present application can improve the data integrity and continuity, enhance the data correlation analysis, optimize the model input characteristics, ensure the interpretability of the model output, and improve the model generalization ability.

[0015] Second aspect, a method for over-temperature protection is provided, and the method includes: obtaining temperature-related parameters of a wet clutch; inputting the temperature-related parameters into a temperature simulation model, and the temperature simulation model outputs the current temperature of the wet clutch, where the temperature simulation model is obtained based on the temperature monitoring method as described in the above embodiments; if the current temperature exceeds a temperature threshold, controlling the wet clutch to perform an over-temperature protection action.

[0016] According to the above technical solution, in the embodiment of the present application, when the monitored temperature exceeds the preset protection threshold, the system can automatically start the over-temperature protection measure to ensure the driving safety of the vehicle.

[0017] In combination with the first aspect, in some possible implementation manners, controlling the wet clutch to perform an over-temperature protection action includes: obtaining the current coolant flow rate of the wet clutch; if the current coolant flow rate is less than or equal to a flow rate threshold, increasing the coolant flow rate; if the current coolant flow rate is greater than the flow rate threshold, reducing the engine torque.

[0018] Through the above technical solution, the embodiment of the present application can implement over-temperature protection for the wet clutch by adjusting the cooling system to increase the coolant flow rate or adjusting the engine torque, which largely avoids hardware damage caused by clutch overheating, extends the service life of the clutch, reduces the maintenance cost and vehicle downtime caused by high-temperature failures, and ensures the driving safety of the vehicle.

[0019] Third aspect, a server is provided, and the server includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the program to implement the temperature monitoring method as described in the above embodiments.

[0020] Fourth aspect, a vehicle is provided, and the vehicle includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the program as the over-temperature protection method in the above embodiments.

[0021] Fifth aspect, a computer program product is provided, including a computer program or instruction, and when the computer program or instruction is executed, it implements the temperature monitoring method as described in the above embodiments, or the over-temperature protection method as described in the above embodiments. Description of the Drawings

[0022] Figure 1 is a schematic flowchart of the temperature monitoring method provided by the embodiment of the present application;

[0023] Figure 2 is a schematic flowchart of the over-temperature protection method provided by the embodiment of the present application;

[0024] Figure 3It is a schematic flowchart of a temperature monitoring method provided according to an embodiment of the present application;

[0025] Figure 4 It is a schematic flowchart of parameter determination provided according to an embodiment of the present application;

[0026] Figure 5 It is a schematic flowchart of model establishment provided according to an embodiment of the present application;

[0027] Figure 6 It is a schematic flowchart of model detection provided according to an embodiment of the present application;

[0028] Figure 7 It is a schematic flowchart of model temperature control provided according to an embodiment of the present application;

[0029] Figure 8 It is a schematic structural diagram of a server provided according to an embodiment of the present application;

[0030] Figure 9 It is a schematic structural diagram of a vehicle provided according to an embodiment of the present application. Detailed implementation manners

[0031] Next, the technical solutions in the present application will be clearly and elaborately described in conjunction with the accompanying drawings. Among them, in the description of the embodiments of the present application, unless otherwise specified, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of the present application, "a plurality" means two or more than two.

[0032] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as implying or suggesting relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features.

[0033] For traditional multiple tests to measure the temperature of a wet clutch, since heat is generated by the relative friction between the steel sheet and the friction plate of the clutch, the cost of monitoring the clutch temperature through a temperature sensor is high, and there is a certain lag in signal transmission, making it difficult to monitor in real time.

[0034] For traditional numerical analysis methods, the accuracy of temperature simulation strongly depends on the selection of various heat transfer coefficients and temperature correction parameters, the simulation accuracy cannot be guaranteed, and real-time monitoring cannot be achieved.

[0035] The clutch temperature protection method in the related art usually indirectly determines whether to start the clutch temperature control system by monitoring the oil outlet temperature. However, this method has latency and indirectness, and cannot accurately and timely determine the clutch temperature, which easily causes clutch ablation and further leads to safety accidents such as transmission failure.

[0036] Figure 1 It is a schematic flowchart of a temperature monitoring method provided by an embodiment of the present application.

[0037] Exemplarily, as Figure 1 shown, the temperature monitoring method includes the following steps:

[0038] In step S101, historical operation data of each vehicle is obtained.

[0039] Specifically, the embodiment of the present application can obtain the measured wet clutch temperature data under different working conditions, transmit it to the CAN (Controller Area Network) bus, and obtain multiple sets of experimental data with time series.

[0040] For example, different working conditions can be urban driving with frequent starts and stops; high-speed cruising; climbing or heavy loads; rapid acceleration or deceleration; high-temperature environment in summer; continuous gear shifting operations, etc.

[0041] It should be noted that the historical operation data may include: slip friction time, clutch speed, clutch torque, clutch slip friction power, coolant flow rate, coolant temperature, and clutch temperature, etc.

[0042] In step S102, temperature-related parameters and measured temperature values of the wet clutch in the historical operation data are extracted.

[0043] Based on the above embodiments, there are many types of historical operation data obtained. Using all of them as input parameters to simulate the clutch temperature will, on the one hand, weaken the influence of key parameters on the temperature; on the other hand, it will reduce the simulation accuracy. Therefore, it is necessary to first perform data correlation analysis to determine the key parameters affecting the wet clutch temperature, that is, to determine the temperature-related parameters of the wet clutch from the historical operation data and use them as input parameters to be input into the temperature simulation model.

[0044] Specifically, the historical operation data is analyzed through scatter plots and correlation coefficients to confirm the temperature-related parameters. Among them, the types of historical operation data are: slip friction time, clutch speed, clutch torque, clutch slip friction power, coolant flow rate, coolant temperature, clutch temperature, etc.; the input parameters include slip friction time, slip friction power, coolant flow rate, and coolant temperature, and the output parameter is the measured clutch temperature value.

[0045] In the embodiments of the present application, temperature-related parameters and measured temperature values of the wet clutch are extracted from historical operation data, including: performing data interpolation on the historical operation data; performing data correlation analysis on the interpolated historical operation data, and determining the temperature-related parameters of the wet clutch according to the analysis results; performing normalization processing on the temperature-related parameters of the wet clutch, and performing denormalization processing on the measured temperature values.

[0046] Specifically, when the temperature sensor measures, it will be interfered by various factors. Using the method of mathematical statistics, for example, taking the significance level a = 0.05 or the confidence level of 95%, and using the interpolation method to supplement the missing values.

[0047] It should be noted that since there are errors in the measurements of various types of sensors, outliers are removed, and the interpolation method is used to supplement. That is, according to the linear difference between the values before and after the measurement points. For example, for (8, 15, 9, 10), the outlier is 15, remove 15, and insert 8.5).

[0048] Then, the linear function method is used to perform normalization and denormalization processing on the input and output parameters of the model, and the effective data of the model is output.

[0049] Among them, the input parameter is the temperature-related parameter, and the output parameter is the measured temperature value.

[0050] Specifically, the linear function performs normalization and denormalization operations on the data. Using linear function normalization, the input parameter is converted to the range of [0, 1], and its calculation formula is:

[0051]

[0052] Where X norm represents the temperature-related parameter after normalization, X represents the temperature-related parameter before normalization, X min represents the minimum value of the temperature-related parameters, X MAX represents the maximum value of the temperature-related parameters;

[0053] Perform denormalization processing on the output parameter, and its calculation formula is:

[0054] X = X norm (X max - X min ) + X min

[0055] Where X is the measured temperature value after denormalization, X norm is the measured temperature value before denormalization, X max is the maximum value of the measured temperature value before denormalization, X min represents the minimum value of the measured temperature value before denormalization.

[0056] In step S103, a training data set is generated according to the temperature-related parameters and the measured temperature values of each vehicle.

[0057] It should be noted that, in order to ensure the generalization ability of the model, that is, the temperature simulation accuracy of the wet clutch under different working conditions, 60% of the training data set is used for model training.

[0058] In step S104, a temperature simulation model of the wet clutch is trained using the training data set, and the current temperature of the wet clutch is monitored based on the trained temperature simulation model.

[0059] Specifically, the temperature simulation model of the wet clutch established by the dynamic neural network method based on artificial intelligence is placed into the vehicle software control system to monitor the clutch temperature in real time. The clutch working state data uploaded by the vehicle to the background is filtered (generally, actual measurements require filtering. The signal needs to eliminate interference, which is a conventional processing method. The difference method and normalization can be placed in the temperature simulation module without additional processing). The extracted information mainly includes: clutch slip time, slip power, coolant flow rate, and coolant temperature, etc. The signal is transmitted through the CAN bus, input into the temperature simulation model, and the temperature of the clutch is monitored, and the real-time temperature of the clutch is output.

[0060] Thus, in the embodiment of the present application, after the model is established, when predicting the temperature of the wet clutch in real time, the temperature-related parameters of the real-time clutch are directly obtained, which include slip time, slip power, coolant flow rate, and coolant temperature, and then filtering processing is used to remove noise; the clutch temperature simulation model established based on artificial intelligence in the embodiment of the present application greatly reduces the difficulty and analysis period of the test method and the traditional simulation analysis method, and has strong applicability; the technology involved in the embodiment of the present application does not require adding hardware facilities and vehicle costs, the system parameters are easy to adjust, and it has universality for temperature monitoring and temperature control of wet clutches of different models of automatic transmissions.

[0061] In the embodiment of the present application, training the temperature simulation model of the wet clutch using the training data set includes: iteratively training the temperature simulation model according to the training data set. Among them, in each iterative training process, a target number of training samples are selected from the training data set to train the temperature simulation model. The temperature-related parameters of each vehicle are used as training samples, and the measured temperature values are used as the temperature true values corresponding to the training samples; the temperature prediction value of each training sample is obtained, the error value of each training sample is calculated according to the temperature prediction value and the temperature true value of each training sample, and the root mean square error is calculated according to the error value of each training sample; if the root mean square error meets the preset error condition, the iterative training of the temperature simulation model is stopped, otherwise, after adjusting the structural parameters and training parameters of the temperature simulation model, continue training.

[0062] Among them, the remaining layer units of the unit type are defined as long short-term memory neural networks, and one layer is defined as a densely connected layer, which can solve the problem of gradient disappearance or explosion; considering the comprehensive simulation accuracy and efficiency, the activation function between layers is the Relu linear rectifier function as follows:

[0063]

[0064] Among them, x is the value in the neural network signal; α is a relatively small constant; e x is in exponential form.

[0065] The iterative algorithm for model training selects the stochastic gradient descent method, and the key parameters are three parameters: the number of iterations, the learning rate, and the batch size. Among them, the number of iterations is initially set to 100, and the number of iterations is gradually increased on this basis (the number of iterations for different data samples is not the same. For example, it can be increased by 100 each time, and the calculation error of the training model is observed and adjusted appropriately); the learning rate uses "Adaptive learning rate" (only the initial value of the learning rate is set, for example, 0.1, and then this option is selected, and the learning rate will be automatically updated as the model iterates); the batch size is initially calculated and set to 64. If the training error oscillates, this value is increased by a power of 2.

[0066] Among them, the structural parameters include the number of hidden layers, the number of units in each layer, the unit type, and the activation function. The first layer is defined as a long short-term memory neural network, and the remaining layers are defined as densely connected layers. An activation function is set between layers; the training parameters include at least one of the number of iterations, the learning rate, and the batch size.

[0067] Among them, each time the structural parameters are adjusted, the number of hidden layers is increased within the first interval based on the first preset step size, and the number of units in each layer is increased within the second interval based on the second preset step size.

[0068] It should be noted that the first preset step size, the first interval, the second preset step size, and the second region are not specifically limited, and those skilled in the art can set them according to the actual situation.

[0069] For example, in the embodiment of the present application, the number of hidden layers gradually increases between [1, 6]; the number of units in each layer is between [3, 40], which is determined based on an empirical formula as follows:

[0070]

[0071] Among them, n 1 is the number of hidden layer nodes, n is the number of input nodes, m is the number of output nodes, and a is taken as an example in [1, 10].

[0072] It should be noted that the preset values of various parameters and the determination thresholds in the embodiments of the present application can all be adjusted, and its logical method can be applied to wet clutches of different models. In the embodiments of the present application, the root mean square error is taken as an example of 90%.

[0073] It should be noted that model training and model verification can determine the temperature prediction temperature simulation model. However, in order to verify the generalization ability of the temperature simulation model, that is, the temperature prediction accuracy for different data sets, model testing is added.

[0074] Specifically, in order to ensure the generalization ability of the model, that is, the temperature simulation accuracy of the wet clutch under different working conditions, the training data set is divided into a training set, a validation set, and a test set according to a certain ratio. The specific ratio is not limited in the present application. For example, 60% of the training data set is used for model training, 30% is used for model verification, and the remaining 10% is used for model testing. If the errors (root mean square error, absolute error, and relative error) do not meet the requirements, the structural parameters and training parameters of the simulation model need to be readjusted until the temperature simulation accuracy meets the requirements. Among them, the error is the error between the simulated value of the clutch temperature and the measured value. The simulated temperature value refers to the predicted temperature value obtained by inputting the input data in the test set into the model, and the measured value refers to the true temperature value corresponding to the input data that originally exists in the test set. Considering the effects of the three errors comprehensively, the root mean square error is the error characterization of the entire model, the absolute error is the numerical error of each sample point, and the relative error is a percentage. The root mean square error is the error characterization of the overall model. If it is greater than 90%, the model training result is considered good. At the same time, according to the results reflected by the absolute error value and the relative error value, it is judged whether it is necessary to increase the number of samples in the data set or increase the number of iterations, etc.

[0075] In summary, the embodiments of the present application realize the real-time monitoring and control of the temperature of the wet clutch, not only effectively preventing hardware damage caused by overheating, such as ablation, cracks, etc., but also optimizing the starting performance and shifting characteristics of the vehicle, improving the overall driving safety and driving experience. In addition, the system design is flexible, has good adaptability to wet clutches of different models, and does not require additional hardware costs, having significant technical advantages and practical value.

[0076] Figure 2 It is a schematic flowchart of the over-temperature protection method provided by the embodiments of the present application.

[0077] Exemplarily, as Figure 2 shown, the over-temperature protection method may include the following steps:

[0078] In S201, obtain the temperature-related parameters of the wet clutch;

[0079] In S202, temperature-related parameters are input into the temperature simulation model, and the temperature simulation model outputs the current temperature of the wet clutch. Among them, the temperature simulation model is obtained based on the temperature monitoring method of the above embodiment.

[0080] In S203, if the current temperature exceeds the temperature threshold, the wet clutch is controlled to perform an over-temperature protection action.

[0081] Among them, the temperature threshold can be specifically set or calibrated, and no specific limitation is made.

[0082] It can be understood that the embodiment of the present application can accurately monitor the current temperature of the wet clutch in real time through the temperature simulation model, and perform over-temperature protection in time when the current temperature is over-temperature, avoiding damage caused by untimely over-temperature protection of the wet clutch, and improving the service life of the wet clutch.

[0083] In the embodiment of the present application, controlling the wet clutch to perform an over-temperature protection action includes: obtaining the current coolant flow rate of the wet clutch; if the current coolant flow rate is less than or equal to the flow rate threshold, increasing the coolant flow rate; if the current coolant flow rate is greater than the flow rate threshold, reducing the engine torque.

[0084] It should be noted that the size of the flow rate threshold is not specifically limited, and those skilled in the art can set it according to the actual situation.

[0085] Specifically, when the real-time temperature of the clutch monitored by the temperature simulation model exceeds the preset temperature threshold, an over-temperature protection action is taken. First, it is judged whether the current coolant flow rate is the maximum flow rate of the product. If not, the coolant flow rate is increased at a preset coolant flow rate gradient, and the clutch temperature can be reduced by heat exchange; if the current coolant flow rate is the maximum design flow rate of the product, the engine torque is reduced at a preset torque reduction gradient, and the over-temperature protection action is performed by adjusting the vehicle motion state, so as to change the temperature of the wet clutch until the real-time temperature of the wet clutch is lower than the threshold.

[0086] Thus, the embodiment of the present application comprehensively considers vehicle driving safety and power performance based on the over-temperature protection method; the logical method and temperature control method of the embodiment of the present application have strong versatility and are applicable to wet clutches of different models. Subsequently, the temperature simulation model can be optimized to reduce the vehicle design cost.

[0087] Next, a specific embodiment is used to illustrate the temperature monitoring method of the embodiment of the present application, as Figure 3 shown, the specific steps are as follows:

[0088] Step S1, Parameter determination: Obtain the measured temperature data of the wet clutch and determine the input parameters of the temperature simulation model. Among them, the parameters include input parameters and output parameters. The input parameters include slip friction time, rotational speed, torque, slip friction work, coolant flow rate, and coolant temperature, etc. The output parameter is the measured value of the clutch temperature.

[0089] As Figure 4 shown, step S1 specifically includes:

[0090] Step S11, Data acquisition: Obtain the measured temperature data of the wet clutch under different working conditions and transmit it to the CAN bus to obtain multiple sets of experimental data with time series. Among them, the collected data includes but is not limited to slip friction time, rotational speed, torque, slip friction work, coolant flow rate, and coolant temperature, etc. After performing correlation processing on the collected data, key parameters are obtained. The key parameters are input parameters and output parameters. Among them, the input parameters include clutch slip friction time, slip friction power, coolant flow rate, and coolant temperature, etc. The output parameters include the measured value of the clutch temperature;

[0091] Step S12, Data correlation analysis: Based on the large number of types of experimental data obtained in step S11, if all are used as input parameters to simulate the clutch temperature, on the one hand, it will weaken the influence of key parameters on the temperature; on the other hand, it will reduce the simulation accuracy. Therefore, data correlation analysis is required to determine the key parameters that affect the temperature of the wet clutch;

[0092] Step S13, Data preprocessing: Among them, in order to facilitate inputting the input parameters into the temperature simulation model, preprocessing is performed on the input data. The preprocessing methods include but are not limited to mathematical statistics methods, removing outliers, and data normalization.

[0093] Step S2, Model establishment: Establish a temperature simulation model of the wet clutch based on the artificial intelligence dynamic neural network method.

[0094] As Figure 5 shown, step S2 specifically includes:

[0095] Step S21, Obtain the structural parameters of the temperature simulation model;

[0096] Step S22, Train the temperature simulation model, and use 60% of the data in the training dataset for model training;

[0097] Step S23, Verify and test the temperature simulation model. In order to ensure the generalization ability of the model, that is, the temperature simulation accuracy of the wet clutch under different working conditions, 30% of the measured temperature values are used for model verification, and the remaining 10% is used for model testing. Compare the temperature simulation value with the measured temperature value. If the root mean square error meets the requirements, then establish the temperature simulation model.

[0098] Step S3, temperature monitoring: Combine the clutch status data uploaded by the vehicle to the background and input it into the established temperature simulation model to monitor the real-time temperature of the clutch.

[0099] As Figure 6 shown, step S3 specifically includes:

[0100] Step S31, collect data signals through the CAN bus;

[0101] Step S32, the extracted wet clutch temperature-related parameters include but are not limited to: clutch slip time, slip power, coolant flow rate, coolant temperature, etc.;

[0102] Step S33, input it into the established temperature simulation model, monitor the temperature of the clutch, and output the real-time temperature of the clutch.

[0103] Thus, in the embodiment of the present application, after the model is established, when predicting the temperature in real time, directly obtain the temperature-related parameters of the real-time clutch, and then perform filtering processing to remove noise.

[0104] Step S4, temperature control: Determine whether to activate the over-temperature protection action by judging whether the real-time temperature of the clutch exceeds the threshold.

[0105] As Figure 7 shown, step S4 specifically includes:

[0106] Step S41, obtain the current temperature;

[0107] Step S42, when it is judged that the real-time temperature of the clutch monitored by the temperature simulation model exceeds the preset temperature threshold, take the over-temperature protection action,

[0108] Step S43, judge whether the current coolant flow rate exceeds the flow rate threshold,

[0109] Step S44, if not, increase the coolant flow rate at a preset coolant flow rate gradient, and the clutch temperature can be reduced by heat exchange;

[0110] Step S45, if so, reduce the engine torque at a preset torque reduction gradient, and perform the over-temperature protection action by adjusting the vehicle motion state, thereby changing the temperature of the wet clutch,

[0111] Step S46, until the current temperature of the clutch is lower than the temperature threshold.

[0112] In summary, the temperature monitoring and control of the wet clutch established in the embodiments of the present application realizes the real-time monitoring and control of the clutch temperature through steps such as parameter determination, model establishment, temperature monitoring, and temperature control. First, collect the clutch temperature test data (including extreme working conditions such as winter standard and summer standard), and determine the data processing method and key parameters affecting the temperature; then, use the dynamic neural network method based on artificial intelligence to establish, train, verify, and test the clutch temperature simulation model in combination with the measured data; again, load the model into the vehicle software system, and monitor the temperature of the wet clutch in real time according to the driving data uploaded by the vehicle to the background in real time; finally, the temperature control module determines whether the real-time temperature of the clutch exceeds the preset threshold. If it exceeds, cooling measures need to be taken, such as increasing the coolant flow or reducing the engine torque, etc.

[0113] In summary, the embodiments of the present application propose a method for monitoring and controlling the temperature of a wet clutch, which uses artificial intelligence technology, especially the dynamic neural network model, to overcome the limitations of traditional temperature monitoring methods and ensure the safe operation of the wet clutch, including the following key points:

[0114] 1. Wet clutch temperature monitoring and control logic method: This logic method first obtains historical operation data, identifies parameters closely related to the wet clutch temperature, such as slip friction time, slip friction power, coolant flow, etc., and generates a training data set using these data. Then, based on this data set, a highly accurate temperature simulation model is established through iterative training, which can monitor the clutch temperature in real time. Its working principle involves the real-time collection, processing, model prediction of data, and taking corresponding protection measures according to the prediction results.

[0115] 2. Measured data processing method based on different working conditions: Before establishing the model, strict data correlation analysis is carried out on the collected measured data to determine which parameters have the most significant impact on the clutch temperature, so as to reduce redundant inputs and improve the model simulation accuracy. The data preprocessing stage includes data interpolation, outlier removal, and normalization processing to ensure the purity and effectiveness of the model input.

[0116] 3. Construction method of the temperature simulation model: The model uses a long short-term memory neural network as the first layer to process time series data. The subsequent layers are densely connected layers. Through carefully designed structural parameters (such as the number of hidden layers, the number of units, activation functions, etc.) and training parameters (number of iterations, learning rate, batch size, etc.), algorithms such as stochastic gradient descent are used for training to achieve the best simulation effect. During the training process, the model parameters are continuously adjusted until the preset error condition is met to ensure the prediction accuracy of the model.

[0117] 4. Temperature protection mechanism: When the temperature prediction model monitors that the clutch temperature exceeds the preset threshold, the system immediately activates the protection mechanism. First, it determines whether the coolant flow can be increased to lower the temperature. If the current flow has reached the design upper limit, it reduces the engine torque to adjust the vehicle's operating state, effectively reducing the clutch temperature until it returns to the safe range.

[0118] In summary, the embodiments of this application achieve real-time monitoring and control of the wet clutch temperature. It not only effectively prevents hardware damage such as ablation and cracks caused by overheating of the clutch steel sheet and friction plate, but also optimizes the vehicle's starting performance and shifting characteristics, improving the overall driving safety and driving experience. In addition, the system is flexibly designed, has good adaptability to different models of wet clutches, and does not require additional hardware costs, having significant technical advantages and practical value.

[0119] Figure 8 The following is a schematic structural diagram of the server provided by the embodiments of this application. The server may include:

[0120] A memory 801, a processor 802, and a computer program stored on the memory 801 and executable on the processor 802.

[0121] When the processor 802 executes the program, it implements the temperature monitoring method provided in the above embodiments.

[0122] Further, the server further includes:

[0123] A communication interface 803 for communication between the memory 801 and the processor 802.

[0124] The memory 801 is used to store a computer program executable on the processor 802.

[0125] The memory 801 may include a high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk memory.

[0126] If the memory 801, the processor 802, and the communication interface 803 are implemented independently, the communication interface 803, the memory 801, and the processor 802 can be interconnected via a bus to complete communication with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 only a thick line is used to represent it in Figure 8 , but it does not mean that there is only one bus or one type of bus.

[0127] Optionally, in a specific implementation, if the memory 801, the processor 802, and the communication interface 803 are integrated on a single chip, the memory 801, the processor 802, and the communication interface 803 can complete communication with each other through an internal interface.

[0128] The processor 802 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0129] Figure 9 It is a schematic structural diagram of a vehicle provided for the embodiments of the present application. The vehicle may include:

[0130] A memory 901, a processor 902, and a computer program stored on the memory 901 and executable on the processor 902.

[0131] When the processor 902 executes the program, it implements the over-temperature protection method provided in the above embodiments.

[0132] Further, the vehicle further includes:

[0133] A communication interface 903 for communication between the memory 901 and the processor 902.

[0134] The memory 901 is used to store a computer program executable on the processor 902.

[0135] The memory 901 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0136] If the memory 901, the processor 902, and the communication interface 903 are implemented independently, the communication interface 903, the memory 901, and the processor 902 can be interconnected via a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity of representation, Figure 9 only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0137] Optionally, in specific implementation, if the memory 901, the processor 902, and the communication interface 903 are integrated on a single chip, the memory 901, the processor 902, and the communication interface 903 can communicate with each other via an internal interface.

[0138] The processor 902 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0139] The embodiments of the present application also provide a computer program product, including a computer program or instructions, which when executed, implement the temperature monitoring method or the over-temperature protection method of the above embodiments.

[0140] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In the description of the present application, "a plurality of" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0141] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0142] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A temperature monitoring method, characterized in that: The method comprises: Obtain historical operation data of each vehicle; Extracting temperature-related parameters and actual temperature values ​​of the wet clutch from the historical operation data; generating a training data set according to the temperature-related parameters and the temperature measured values ​​of the wet clutches of each vehicle; The training data set is used to train a temperature simulation model of the wet clutch, and the current temperature of the wet clutch is monitored based on the trained temperature simulation model.

2. The method according to claim 1, characterized in that The method of obtaining the temperature simulation model of the wet clutch by training the training data set includes: Iteratively training the temperature simulation model according to the training data set, wherein in each iterative training process, a target number of training samples are selected from the training data set to train the temperature simulation model, the temperature-related parameters of each vehicle are used as training samples, and the temperature measured values ​​are used as the true temperature values ​​corresponding to the training samples; Obtain a temperature prediction value for each training sample, calculate an error value for each training sample based on the temperature prediction value and the true temperature value of each training sample, and calculate a root mean square error based on the error value of each training sample; if the root mean square error meets a preset error condition, stop iterative training of the temperature simulation model; otherwise, continue training after adjusting the structural parameters and training parameters of the temperature simulation model.

3. The method according to claim 2, characterized in that The structural parameters include the number of hidden layers, the number of units in each layer, the unit type and the activation function. The first layer is defined as a long short-term memory neural network, and the remaining layers are defined as densely connected layers. The activation function is set between the layers; the training parameters include at least one of the number of iterations, the learning rate and the batch size.

4. The method according to claim 3, characterized in that Each time the structural parameters are adjusted, the number of hidden layers is increased within a first interval based on a first preset step size, and the number of units per layer is increased within a second interval based on a second preset step size.

5. The method according to claim 1, characterized in that Extracting temperature-related parameters and actual temperature values ​​of the wet clutch in the historical operation data includes: Performing data interpolation on the historical operation data; Performing data correlation analysis on the historical operating data after data interpolation, and determining temperature-related parameters of the wet clutch according to the analysis results; The temperature-related parameters of the wet clutch are normalized, and the measured temperature values ​​are denormalized.

6. An over-temperature protection method, characterized in that: The method comprises: Obtain temperature-related parameters of the wet clutch; Inputting the temperature-related parameters into a temperature simulation model, the temperature simulation model outputting the current temperature of the wet clutch, wherein the temperature simulation model is obtained based on the temperature monitoring method according to any one of claims 1 to 5; If the current temperature exceeds the temperature threshold, the wet clutch is controlled to perform an over-temperature protection action.

7. The method according to claim 6, characterized in that The controlling the wet clutch to perform an over-temperature protection action includes: obtaining a current coolant flow rate of the wet clutch; If the current coolant flow rate is less than or equal to the flow rate threshold, increasing the coolant flow rate; If the current coolant flow rate is greater than the flow rate threshold, the engine torque is reduced.

8. A server, characterized in that: The server includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the program to implement the temperature monitoring method according to any one of claims 1 to 5.

9. A vehicle, characterized in that: The vehicle comprises: a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor executes the program to implement the over-temperature protection method according to claim 6 or 7.

10. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed, the temperature monitoring method described in any one of claims 1 to 5, or the over-temperature protection method described in claim 6 or 7 is implemented.

Images