Temperature prediction method and device for vehicle window motor, electronic equipment and medium
By using target operating data and prediction models in the window motor for temperature prediction and adjustment, the maintenance cost and user experience issues under the traditional thermal protection mechanism are solved, and more efficient and safe thermal management is achieved.
Patent Information
- Application Number
- CN202411374823.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-29
- Publication Date
- 2025-01-24
AI Technical Summary
Traditional window motor thermal protection relies on simple temperature-controlled sensors and passive response mechanisms, resulting in increased maintenance costs and decreased user experience.
By obtaining the target operation data of the window motor, the input target prediction model is entered for temperature prediction, and the window motor is adjusted based on the predicted temperature data to achieve real -time temperature prediction and thermal management.
Improve the accuracy and safety of the temperature prediction of the window motor, reduce the cost of maintenance, and improve the user experience.
Smart Images
Figure CN119357579A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of vehicle technology, and in particular to a temperature prediction method and device, electronic equipment, and medium for a vehicle window motor. Background Art
[0002] With the increasing intelligence of automobiles, window motors are one of the key components that are frequently operated in vehicles. Their thermal management has become a key factor in ensuring vehicle comfort and safety. The existing thermal protection of window motors is achieved through hardware thermal protection. There are currently two main technical solutions for window motor thermal protection: (1) Counting method: The window motor operation time is counted by a counter. When the counter reaches a certain threshold, the motor thermal protection is activated; (2) Temperature sensor: A temperature sensor is installed to directly detect the motor temperature. When the temperature is too high, the power supply is disconnected to protect the motor.
[0003] In summary, traditional temperature monitoring relies on simple temperature control sensors and passive response mechanisms, resulting in increased maintenance costs and reduced user experience. Summary of the invention
[0004] In view of the above problems, a temperature prediction method and device for a vehicle window motor, an electronic device, and a medium are proposed to overcome the above problems or at least partially solve the above problems, including:
[0005] A temperature prediction method for a vehicle window motor, the method comprising:
[0006] Obtaining target operating data of a window motor of a vehicle;
[0007] Inputting the target operation data into a target prediction model, so that the target prediction model predicts the motor temperature of the vehicle based on the target operation data, and outputs first predicted temperature data of the window motor;
[0008] The window motor is adjusted based on the first predicted temperature data.
[0009] Optionally, adjusting the window motor based on the first predicted temperature data includes:
[0010] When the first predicted temperature data is greater than or equal to a first preset temperature threshold, the window motor is adjusted based on the first predicted temperature data.
[0011] Optionally, adjusting the window motor based on the first predicted temperature data includes:
[0012] determining a target motor operating mode from a plurality of preset motor operating modes of the vehicle based on the first predicted temperature data;
[0013] The window motor is adjusted according to the target motor operation mode.
[0014] Optionally, it also includes:
[0015] When the first predicted temperature data is greater than or equal to a first preset temperature threshold, an early warning signal is generated to remind an associated user.
[0016] Optionally, adjusting the window motor based on the first predicted temperature data includes:
[0017] When the first predicted temperature data is greater than or equal to a second preset temperature threshold, the window motor is controlled to stop running.
[0018] Optionally, the training process of the target prediction model includes:
[0019] Acquire actual temperature data and actual operation data of various window motors, and generate a sample set and a test set based on the actual temperature data and the actual operation data;
[0020] Inputting the actual operation data in the sample set into the initial prediction model to perform temperature prediction, and outputting second predicted temperature data;
[0021] Adjusting the model parameters of the initial prediction model based on the actual temperature data in the sample set and the second predicted temperature data;
[0022] Using the test set to perform model evaluation on the prediction model after adjusting the model parameters, and generating a model error of the prediction model;
[0023] When the model error is less than or equal to the preset model error, the prediction model after adjusting the model parameters is used as the trained target prediction model.
[0024] Optionally, before inputting the target operation data into the target prediction model, the method further includes:
[0025] The target operation data is normalized.
[0026] A temperature prediction device for a vehicle window motor, the device comprising:
[0027] A target operation data acquisition module, used to acquire target operation data of a vehicle window motor;
[0028] A first temperature prediction module, configured to input the target operation data into a target prediction model, so that the target prediction model predicts the motor temperature of the vehicle based on the target operation data, and outputs first predicted temperature data of the window motor;
[0029] A vehicle window motor adjustment module is used to adjust the vehicle window motor based on the first predicted temperature data.
[0030] An electronic device comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the temperature prediction method of a vehicle window motor as described above when executed by the processor.
[0031] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the temperature prediction method of a vehicle window motor as described above is implemented.
[0032] The embodiments of the present invention have the following advantages:
[0033] In an embodiment of the present invention, target operating data of a window motor of a vehicle is obtained; the target operating data is input into a target prediction model, so that the target prediction model predicts the motor temperature of the vehicle based on the target operating data, and outputs first predicted temperature data of the window motor; the window motor is adjusted based on the first predicted temperature data, thereby achieving real-time prediction of the temperature change of the window motor within a period of time in the future. The prediction through the target prediction model can provide prediction accuracy. At the same time, based on the operating data of the window motor, even when the vehicle has no temperature sensor or the temperature sensor is inaccurate, the window motor can be detected to improve the safety of the motor. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] In order to more clearly illustrate the technical solution of the present invention, the accompanying drawings required for use in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.
[0035] Figure 1a is a flow chart of steps of a temperature prediction method for a vehicle window motor provided by an embodiment of the present invention;
[0036] Figure 1b This is a schematic diagram of an LSTM model structure provided by an embodiment of the present invention;
[0037] Figure 1c It is a schematic diagram of a multi-layer LSTM model structure provided by an embodiment of the present invention;
[0038] Figure 2 is a flowchart of another method for predicting the temperature of a window motor provided by an embodiment of the present invention;
[0039] Figure 3It is a schematic diagram of a process of temperature prediction based on LSMN model provided by one embodiment of the present invention;
[0040] Figure 4 It is a schematic diagram of the structure of a temperature prediction device for a vehicle window motor provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0041] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0042] Reference Figure 1a , shows a flow chart of the steps of a temperature prediction method for a window motor provided by an embodiment of the present invention, which may specifically include the following steps:
[0043] Step S101, obtaining target operation data of a vehicle window motor;
[0044] In actual applications, the window motor in a vehicle is a frequently operated component. When the temperature of the window motor is too high, it may cause the motor performance to decline, damage, or even cause safety hazards. In an embodiment of the present invention, the target operating data of the window motor is obtained to predict the window motor temperature.
[0045] The target operation data may include but are not limited to: any one or more of the window motor operation time data, the window motor operation frequency data, the window motor operation current data, and the window motor voltage data. In the embodiment of the present invention, the target operation data may be real-time operation data.
[0046] In one example, one or more sensors for collecting operating data of the window motor may be disposed in the vehicle, and the sensors are then used to collect target operating data of the window motor.
[0047] For example, a voltmeter and an ammeter may be pre-configured in the vehicle. The voltmeter may be used to measure the voltage data of the window motor, and the ammeter may be used to measure the current data of the window motor.
[0048] Step S102, inputting the target operation data into the target prediction model, so that the target prediction model predicts the motor temperature of the vehicle based on the target operation data, and outputs first predicted temperature data of the window motor;
[0049] After obtaining the target operation data, the target operation data can be input into the trained target prediction model to perform temperature prediction for a period of time in the future.
[0050] In one embodiment of the present invention, the target operation data of the window motor may include multiple types of data, and the amount of data of each type of data is different. In order to solve the problem of inconsistent order of magnitude of each data, the target operation data may be normalized before being input into the target prediction model. The normalization process may uniformly convert data of different orders of magnitude into data within a fixed range, such as between 0 and 1. During the normalization process, the normalization formula for each target operation data is:
[0051]
[0052] Where X norm is the target operation data after normalization, X is the target operation data before normalization, and X min is the minimum value in the target running data, X max The maximum value in the target run data.
[0053] In one embodiment of the present invention, the target prediction model is a trained model, the input data of the model is the operating data of the window motor, and the output data is the predicted temperature of the window motor. The model type of the target prediction model can be a neural network model, for example, an LSTM model. The target prediction model learns the correlation between the operating data of the window motor and the predicted temperature through training.
[0054] In one embodiment of the present invention, the training process of the target prediction model includes the following sub-steps:
[0055] Sub-step S11, obtaining actual temperature data and actual operation data of various window motors, and generating a sample set and a test set based on the actual temperature data and the actual operation data;
[0056] In practical applications, the actual temperature data and actual operation data of the window motor under various motor experiments can be collected, where the temperature data corresponds one-to-one with the actual operation data, and then a sample set and a test set are generated. For example, 80% of the collected data can be extracted as sample set data, and 20% of the data can be extracted as test set data.
[0057] In an embodiment of the present invention, by collecting actual temperature data and actual operation data of the window motor under various motor experiments for target prediction model training, the influence of different motor experiments on temperature prediction can be avoided, the accuracy of temperature prediction can be improved, and the trained model can be applied to a wide range of applications.
[0058] Sub-step S12, inputting the actual operation data in the sample set into the initial prediction model to perform temperature prediction, and outputting second predicted temperature data;
[0059] After generating the sample set, an initial prediction model can be selected, including selecting the model type, initial model parameters, iteration end conditions, etc. of the initial prediction model, and the actual operating data in the sample set is input into the selected initial prediction model for temperature prediction to obtain second predicted temperature data.
[0060] In an embodiment of the present invention, the initial prediction model can be an LSTM model. The algorithm principle of the LSTM model is as follows: Long Short-Term Memory (LSTM) is a special recurrent neural network (RNN) suitable for processing and predicting time series data. LSTM can effectively solve the gradient vanishing and gradient explosion problems of RNN in long time series data processing by introducing memory units and gating mechanisms, and can maintain and utilize key information over a long time span, thereby performing well in time series prediction. The network structure of the LSTM model includes an input gate, a forget gate, a cell state, an output gate, and a hidden state.
[0061] Sub-step S13, adjusting the model parameters of the initial prediction model based on the actual temperature data in the sample set and the second predicted temperature data;
[0062] After obtaining the second predicted temperature data, the error can be calculated by combining the actual temperature data and the second predicted temperature data, and then the mean square error (MSE) is calculated based on the error. The mean square error is used as the loss function, and the model parameters are adjusted through back propagation and gradient descent optimization algorithms to minimize the prediction error. The hyperparameters of the model, such as the number of LSTM layers, the number of hidden units, and the learning rate, are optimized through grid search or random search methods.
[0063] Sub-step S14, using the test set to perform model evaluation on the prediction model after adjusting the model parameters, and generating a model error of the prediction model;
[0064] Through sub-steps S12 and S13, a round of iterations of the initial prediction model can be performed. After a round of iterations, the prediction model obtained by the iteration can be evaluated. Specifically, the prediction model can be evaluated using data in the test set, and the model error of the prediction model after iteration is calculated, where model error = number of inaccurate predictions / total number of test sets.
[0065] Sub-step S15, when the model error is less than or equal to the preset model error, the prediction model after adjusting the model parameters is used as the trained target prediction model.
[0066] Among them, the preset model error can be set according to actual needs.
[0067] When the model error of the prediction model of this iteration is greater than the preset model error, S12 is executed to perform a new round of model training. When the model error of the prediction model of this iteration is less than or equal to the preset model error, the model training is terminated and the prediction model generated by the last iteration is output.
[0068] like Figure 1b As shown in FIG. 1 , a schematic diagram of the LSTM model structure in an embodiment of the present invention is shown. This structural design can not only flexibly control the information flow, but also selectively store or forget historical information, thereby efficiently capturing long-term dependencies. The specific expression is as follows:
[0069] i t =σ(W i ·[[h t-1 ,x t ]+b i ) (1)
[0070] f t =σ(W f ·[h t-1 , x t ]+b f ) (2)
[0071]
[0072] o t =σ(W o ·[h t-1 , x t ]+b o ) (5)
[0073] h t =o t ☉c t-1 (6)
[0074] Among them, x t represents the input vector at time step t (i.e., the motor operation data at time t, including characteristic values such as operation time, frequency, and current); h t is the hidden state at time step t, h t-1 is the hidden state at the previous moment. t is the input data of the input gate, which determines how the new information affects the unit state, i.e., c in formula (4) t ;f t Forget gate data, which controls which parts of the unit state at the previous moment need to be forgotten; t The output gate data determines which part of the cell state information will be used to update the hidden state h t ; Hidden state ht Combined with the cell state controlled by the output gate, the output at the current moment is generated and used as the input at the next moment. i , W f , W c , W o is the weight matrix, b i , b f , b c , b o is the bias. σ is the sigmoid activation function, Generally, continuous input values are mapped to outputs between (0, 1); tanh is the hyperbolic tangent activation function, Map the input value to (-1, 1). For each time step t, LSTM updates its hidden state h t and cell status ct:h t ,c t =LSTM(x t ,h t-1 ,c t-1 ).
[0075] In the embodiment of the present invention, it is necessary to predict the temperature change of the motor in the future based on the historical motor operation data. If X represents the motor operation data of N historical time steps (including P features such as operation time, frequency, current, voltage, etc., and all have been normalized), then X=(x 1 ,x 2 ..., x N ), the dimension is N*P, x i =(x i1 ,x i2 ,...,x ip ) is the input vector of time step i, x i1 ,x i2 ,...,x ip They represent the motor running time, frequency, current and other values at time step i, respectively. i The dimension is 1*P; y represents the temperature to be predicted (i.e., the target value), y=(y 1 ,y 2 ,...y N ) dimension is N*1. When using LSTM for multi-step prediction (predicting the target value of the next T time steps), the sliding time window method is usually used to divide the data set into a series of input-output pairs. If the window size is w (you can try different window sizes and select the optimal w), for each time window, construct an input sequence X containing w time steps i:i+w =(x i , x i+1 ,...,x i+w-1), where i is the starting point of the window, and constructs the corresponding output sequence y for the next T time steps i+w:i+w+T =(y i+w ,y i+w+1 , ..., y i+w+T-1 ). If the data set contains N sample points, Nw-T+1 input-output sequence pairs can be constructed for training and evaluating the LSTM model.
[0076] Specifically, a multi-layer LSTM model is constructed, such as Figure 1c As shown, it includes an input layer, multiple LSTM layers and an output layer. The input layer and the hidden layer jointly extract the characteristic values of the motor operation data. The input of the next hidden layer is the output of the previous hidden layer. Finally, the predicted value of the motor temperature is obtained through the fully connected layer (i.e., the output layer). In the present invention, the input layer is a three-dimensional tensor with a shape of (batch_size, time_steps, features). Batch_size is a dynamic parameter, which indicates the number of samples processed in one training, time_steps is the time window size w, and features is the number of features P of the motor operation data. Therefore, the shape of the input layer is (batch_size, w, P), where batch_size represents a variable batch size. The hidden layer LSTM layer is responsible for capturing the long-term dependencies in the time series data. The number of neurons in each LSTM layer is a hyperparameter that needs to be determined by experiments. Assume that the first LSTM layer has L neurons, and its output will be passed to the next LSTM layer or the fully connected layer. After the LSTM layer, there are usually one or more fully connected layers (i.e., output layers) to convert the output of the LSTM layer into the final output of the predicted temperature. If the temperature is predicted for the next T time steps, then the output dimension of the last fully connected layer should be T. If the final output of the LSTM layer is output, then W fc is the weight matrix from the hidden layer to the output layer, b fc is the deviation, It is T*1-dimensional, that is, the motor temperature vector of the next T time steps.
[0077] Step S103: adjusting the window motor based on the first predicted temperature data.
[0078] After obtaining the first predicted temperature data through the target prediction model, the window motor can be adjusted in advance according to the first predicted temperature data to avoid performance degradation of the window motor due to abnormal temperature, thereby achieving the effect of early prevention.
[0079] In an embodiment of the present invention, target operating data of a window motor of a vehicle is obtained; the target operating data is input into a target prediction model, so that the target prediction model predicts the motor temperature of the vehicle based on the target operating data, and outputs first predicted temperature data of the window motor; the window motor is adjusted based on the first predicted temperature data, thereby achieving real-time prediction of the temperature change of the window motor within a period of time in the future. The prediction through the target prediction model can provide prediction accuracy. At the same time, based on the operating data of the window motor, even when the vehicle has no temperature sensor or the temperature sensor is inaccurate, the window motor can be detected to improve the safety of the motor.
[0080] Reference Figure 2 , shows a flowchart of another method for predicting the temperature of a window motor provided by an embodiment of the present invention, which may specifically include the following steps:
[0081] Step S201, obtaining target operation data of a window motor of a vehicle;
[0082] In actual applications, the window motor in a vehicle is a frequently operated component. When the temperature of the window motor is too high, it may cause the motor performance to decline, damage, or even cause safety hazards. In an embodiment of the present invention, the target operating data of the window motor is obtained to predict the window motor temperature.
[0083] The target operation data may include but are not limited to: any one or more of the window motor operation time data, the window motor operation frequency data, the window motor operation current data, and the window motor voltage data. In the embodiment of the present invention, the target operation data may be real-time operation data.
[0084] In one example, one or more sensors for collecting operating data of the window motor may be disposed in the vehicle, and the sensors are then used to collect target operating data of the window motor.
[0085] For example, a voltmeter and an ammeter may be pre-configured in the vehicle. The voltmeter may be used to measure the voltage data of the window motor, and the ammeter may be used to measure the current data of the window motor.
[0086] Step S202, inputting the target operation data into the target prediction model, so that the target prediction model predicts the motor temperature of the vehicle based on the target operation data, and outputs first predicted temperature data of the window motor;
[0087] After obtaining the target operation data, the target operation data can be input into the trained target prediction model to perform temperature prediction for a period of time in the future.
[0088] The target prediction model is a trained model, the input data of the model is the operating data of the window motor, and the output data is the predicted temperature of the window motor. The model type of the target prediction model can be a neural network model, such as an LSTM model. The target prediction model learns the correlation between the operating data of the window motor and the predicted temperature through training.
[0089] Step S203: when the first predicted temperature data is greater than or equal to the first preset temperature threshold, adjusting the window motor based on the first predicted temperature data.
[0090] In practical applications, a first preset temperature threshold may be set for a window motor of a vehicle, where the first preset temperature threshold is a critical temperature for determining whether the temperature of the window motor is safe.
[0091] After the first predicted temperature data is predicted by the target prediction model, it can be determined whether the first preset temperature data is greater than the first predicted temperature data. When the first preset temperature data is greater than the predicted temperature data, the window motor can be adjusted based on the first predicted temperature data to control the window motor temperature.
[0092] In one embodiment of the present invention, adjusting the window motor based on the first predicted temperature data includes: determining a target motor operating mode from a plurality of preset motor operating modes of the vehicle according to the first predicted temperature data; and adjusting the window motor according to the target motor operating mode.
[0093] The preset motor operation mode may include but is not limited to configuration information such as current output, cooling fan operation state or operating frequency, and the vehicle window motor may maintain a suitable operating temperature by adjusting the motor operation mode. For example, by changing the motor operation mode, the current output may be adjusted, the cooling fan may be started, or the operating frequency may be temporarily limited.
[0094] In one embodiment of the present invention, when the first predicted temperature data is greater than or equal to the first preset temperature threshold, an early warning signal is generated to remind the associated user.
[0095] In one embodiment of the present invention, when the first predicted temperature data is greater than or equal to the second preset temperature threshold, the window motor is controlled to stop running.
[0096] The second preset temperature threshold is greater than the first preset temperature threshold. The second preset temperature threshold is a temperature at which the vehicle's window motor is close to being unable to operate. When the first predicted temperature data is greater than the second preset temperature threshold, the future temperature of the vehicle's window motor is too high, and it may be impossible to adjust and control the window motor temperature when the window motor is turned on. In order to protect the window motor, the window motor can be controlled to stop operating.
[0097] In an embodiment of the present invention, target operating data of a window motor of a vehicle is obtained; the target operating data is input into a target prediction model, so that the target prediction model predicts the motor temperature of the vehicle based on the target operating data, and outputs first predicted temperature data of the window motor; when the first predicted temperature data is greater than or equal to a first preset temperature threshold, the window motor is adjusted based on the first predicted temperature data, thereby achieving real-time prediction of the temperature change of the window motor over a period of time in the future. The prediction through the target prediction model can provide prediction accuracy, and at the same time, the prediction based on the operating data of the window motor can achieve detection of the window motor even when the vehicle has no temperature sensor or the temperature sensor is inaccurate, thereby improving the safety of the motor.
[0098] Reference Figure 3 , shows a schematic diagram of a process for temperature prediction based on an LSMN model provided by an embodiment of the present invention, including a model training process, a real-time prediction process, and a thermal management decision process.
[0099] The model training process may include: collecting motor operation data, temperature data, preprocessing the data, such as normalization, and generating training sets and test sets. After the LSTM model is proposed, the training set can be used to train the LSTM model, and then the model error can be calculated to evaluate the LSTM model. When the model error meets the preset model error requirement, the training ends and the model is deployed in the vehicle ECU. If the model error does not meet the preset model error requirement, the LSTM model training continues.
[0100] The real-time prediction process may include: collecting real-time data of the motor, and using the trained and deployed LSTM model to predict the temperature of the vehicle's window motor. That is, receiving data in real time and quickly predicting the temperature change trend of the motor in the future. According to the prediction results, the motor working mode is automatically adjusted, such as adjusting the current output, starting the cooling fan, or temporarily limiting the operating frequency, to maintain a suitable working temperature.
[0101] The thermal management decision process includes: determining whether the predicted temperature reaches a threshold (i.e., the first preset temperature threshold). When the preset temperature reaches the threshold, the motor working state is adjusted, and the real-time data of the motor is continuously monitored.
[0102] Specifically, a temperature threshold can be set according to the safe operating temperature range of the motor; when the predicted temperature approaches or exceeds the preset threshold, the system sends a warning signal in advance.
[0103] In an embodiment of the present invention, protection measures can also be set for the window motor: dynamically adjust the motor operating mode according to the temperature prediction result, such as reducing the motor speed or power, starting the cooling fan or operating frequency to maintain a suitable operating temperature; when the temperature is about to exceed the safety range, the system can force the motor to suspend operation and perform cooling treatment.
[0104] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.
[0105] Reference Figure 4 , shows a schematic diagram of the structure of a temperature prediction device for a window motor provided by an embodiment of the present invention, which may specifically include the following modules:
[0106] The target operation data acquisition module 401 is used to acquire the target operation data of the vehicle window motor;
[0107] A first temperature prediction module 402, configured to input the target operation data into a target prediction model, so that the target prediction model predicts the motor temperature of the vehicle based on the target operation data, and outputs first predicted temperature data of the window motor;
[0108] The vehicle window motor adjustment module 403 is configured to adjust the vehicle window motor based on the first predicted temperature data.
[0109] In one embodiment of the present invention, the window motor adjustment module 403 may include:
[0110] The window motor adjustment submodule is used to adjust the window motor based on the first predicted temperature data when the first predicted temperature data is greater than or equal to a first preset temperature threshold.
[0111] In one embodiment of the present invention, the window motor adjustment submodule may include:
[0112] a target motor operation mode determination unit, configured to determine a target motor operation mode from a plurality of preset motor operation modes of the vehicle according to the first predicted temperature data;
[0113] A vehicle window motor adjustment unit is used to adjust the vehicle window motor according to the target motor operation mode.
[0114] In one embodiment of the present invention, the window motor adjustment module 403 may include:
[0115] The warning signal generation submodule is used to generate a warning signal for reminding an associated user when the first predicted temperature data is greater than or equal to a first preset temperature threshold.
[0116] In one embodiment of the present invention, the window motor adjustment module 403 includes:
[0117] The vehicle window motor stopping operation module is used to control the vehicle window motor to stop operating when the predicted temperature data is greater than or equal to a second preset temperature threshold.
[0118] In one embodiment of the present invention, the device comprises:
[0119] A data set acquisition module, used to acquire actual temperature data and actual operation data of various window motors, and generate a sample set and a test set based on the actual temperature data and the actual operation data;
[0120] A second temperature prediction module, used for inputting the actual operation data in the sample set into the initial prediction model to perform temperature prediction and output second predicted temperature data;
[0121] A model parameter adjustment module, configured to adjust the model parameters of the initial prediction model based on the actual temperature data in the sample set and the second predicted temperature data;
[0122] A model error generating module, used to use the test set to perform model evaluation on the prediction model after adjusting the model parameters, and generate a model error of the prediction model;
[0123] The target prediction model determination module is used to use the prediction model after adjusting the model parameters as the trained target prediction model when the model error is less than or equal to the preset model error.
[0124] In one embodiment of the present invention, the device comprises:
[0125] The normalization processing module is used to perform normalization processing on the target operation data.
[0126] In an embodiment of the present invention, target operating data of a window motor of a vehicle is obtained; the target operating data is input into a target prediction model, so that the target prediction model predicts the motor temperature of the vehicle based on the target operating data, and outputs first predicted temperature data of the window motor; the window motor is adjusted based on the first predicted temperature data, thereby achieving real-time prediction of the temperature change of the window motor within a period of time in the future. The prediction through the target prediction model can provide prediction accuracy. At the same time, the prediction based on the operating data of the window motor can achieve detection of the window motor even when the vehicle has no temperature sensor or the temperature sensor is inaccurate, thereby improving the safety of the motor.
[0127] An embodiment of the present invention further provides an electronic device, which may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, the temperature prediction method of the window motor as described above is implemented.
[0128] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the temperature prediction method of a vehicle window motor is implemented.
[0129] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0130] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.
[0131] Those skilled in the art will appreciate that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
[0132] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate a device for implementing the functions specified in one process or multiple processes in the flowchart and / or one box or multiple boxes in the block diagram.
[0133] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.
[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce computer-implemented processing, so that the instructions executed on the computer or other programmable terminal device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.
[0135] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.
[0136] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.
[0137] The above provides a detailed introduction to a temperature prediction method and device for a window motor, an electronic device, and a medium. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for a person skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.
Claims
1. A temperature prediction method for a vehicle window motor, characterized in that: The method comprises: Obtaining target operating data of a window motor of a vehicle; Inputting the target operation data into a target prediction model, so that the target prediction model predicts the motor temperature of the vehicle based on the target operation data, and outputs first predicted temperature data of the window motor; The window motor is adjusted based on the first predicted temperature data.
2. The method according to claim 1, characterized in that The adjusting the window motor based on the first predicted temperature data includes: When the first predicted temperature data is greater than or equal to a first preset temperature threshold, the window motor is adjusted based on the first predicted temperature data.
3. The method according to claim 2, characterized in that The adjusting the window motor based on the first predicted temperature data includes: determining a target motor operating mode from a plurality of preset motor operating modes of the vehicle based on the first predicted temperature data; The window motor is adjusted according to the target motor operation mode.
4. The method according to claim 1, characterized in that: Also includes: When the first predicted temperature data is greater than or equal to a first preset temperature threshold, an early warning signal is generated to remind an associated user.
5. The method according to claim 1, characterized in that: The adjusting the window motor based on the first predicted temperature data includes: When the first predicted temperature data is greater than or equal to a second preset temperature threshold, the window motor is controlled to stop running.
6. The method according to claim 1, characterized in that The training process of the target prediction model includes: Acquire actual temperature data and actual operation data of various window motors, and generate a sample set and a test set based on the actual temperature data and the actual operation data; Inputting the actual operation data in the sample set into the initial prediction model to perform temperature prediction, and outputting second predicted temperature data; Adjusting the model parameters of the initial prediction model based on the actual temperature data in the sample set and the second predicted temperature data; Using the test set to perform model evaluation on the prediction model after adjusting the model parameters, and generating a model error of the prediction model; When the model error is less than or equal to the preset model error, the prediction model after adjusting the model parameters is used as the trained target prediction model.
7. The method according to any one of claims 1 to 6, characterized in that Before inputting the target operation data into the target prediction model, the method further includes: The target operation data is normalized.
8. A temperature prediction device for a window motor, characterized in that: The device comprises: A target operation data acquisition module, used to acquire target operation data of a vehicle window motor; A first temperature prediction module, configured to input the target operation data into a target prediction model, so that the target prediction model predicts the motor temperature of the vehicle based on the target operation data, and outputs first predicted temperature data of the window motor; A vehicle window motor adjustment module is used to adjust the vehicle window motor based on the first predicted temperature data.
9. An electronic device, characterized in that: The invention comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the temperature prediction method of the vehicle window motor according to any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium, characterized in that: The computer readable storage medium stores a computer program, and when the computer program is executed by a processor, the temperature prediction method of a vehicle window motor according to any one of claims 1 to 7 is implemented.