Temperature management device, temperature management method and electronic equipment
By using deep learning models in electronic devices for temperature prediction and management, the problem of lack of flexibility in existing thermal management technologies is solved, and more efficient and reliable temperature management is achieved, and the service life of the device is extended.
Patent Information
- Application Number
- CN202510205715.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-24
- Publication Date
- 2025-05-30
AI Technical Summary
The thermal management technology of existing electronic devices lacks flexibility, which can easily lead to overcooling or overheating, affecting the performance and life of the device.
A temperature management device is adopted, including a data acquisition module, a temperature prediction module and a temperature management module. The deep learning model uses real-time data acquisition to predict temperature and adjust the heat dissipation equipment based on the prediction results to achieve accurate temperature management.
It realizes flexible, reliable and stable temperature management of electronic devices, avoids overcooling or overheating, extends the service life of the device, and continuously optimizes temperature prediction and management effects through self-learning mechanisms.
Smart Images
Figure CN120066151A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical field of temperature control, and particularly relates to a temperature management device, a temperature management method, and an electronic device. Background Art
[0002] Electronic devices such as FPC (Flexible Printed Circuit) are widely used in various electronic products. Taking FPC as an example, due to its characteristics such as being thin, flexible, and high-temperature resistant, it has been widely used in fields such as mobile phones, tablet computers, and smart wearable devices. However, with the continuous increase in the functions and power consumption of electronic products, these electronic devices will generate a large amount of heat during use, and the thermal management problem has become a key factor affecting their performance and lifespan.
[0003] Currently, the thermal management technology of electronic devices (such as FPC, etc.) mainly relies on fixed temperature threshold control: traditional thermal management devices set a fixed temperature threshold, and when the temperature reaches the threshold, the cooling device is started for cooling. The advantage of this method is its simplicity of implementation, but the disadvantage is its lack of flexibility, inability to be adjusted according to the actual usage situation, and prone to overcooling or overheating phenomena.
[0004] Correspondingly, a new temperature management solution is needed in this field to solve the above problems. Summary of the Invention
[0005] In order to overcome the above defects, this application is proposed to solve or at least partially solve the technical problem of how to achieve more flexible, reliable, and stable temperature management of electronic devices.
[0006] In a first aspect, a temperature management device is provided, and the device includes:
[0007] A data acquisition module configured to obtain real-time acquisition data of a device to be temperature-managed in an electronic device;
[0008] A temperature prediction module configured to obtain a temperature prediction result of the device to be temperature-managed based on a deep learning model according to the real-time acquisition data;
[0009] A temperature management module configured to perform temperature management on the device to be temperature-managed according to the temperature prediction result;
[0010] The deep learning model is trained based on a preset training data set, and the training data set includes historical acquisition data obtained by regularly collecting data on the device to be temperature-managed at historical moments; the device further includes a training data acquisition module; the training data acquisition module includes a historical data acquisition unit and a training data acquisition unit;
[0011] The historical data acquisition unit is configured to perform regular data acquisition on the device to be temperature - managed according to a preset acquisition frequency, and obtain historical acquisition data;
[0012] The training data acquisition unit is configured to obtain the training data set according to the historical acquisition data.
[0013] In a technical solution of the above - mentioned temperature management device, a heat dissipation device is provided on the device to be temperature - managed;
[0014] The temperature management module is further configured to:
[0015] Adjust the heat dissipation device according to the temperature prediction result to achieve temperature management of the device to be temperature - managed.
[0016] In a technical solution of the above - mentioned temperature management device, the training data acquisition unit includes a data cleaning sub - unit and a normalization processing sub - unit;
[0017] The data cleaning sub - unit is configured to perform data cleaning on the historical acquisition data to obtain the result of cleaning the historical acquisition data;
[0018] The normalization processing sub - unit is configured to perform data normalization processing on the result of cleaning the historical acquisition data to obtain the training data set.
[0019] In a technical solution of the above - mentioned temperature management device, the real - time acquisition data includes at least one of the temperature data, current data, and voltage data of the device to be temperature - managed;
[0020] The historical acquisition data includes at least one of the temperature data, current data, and voltage data of the device to be temperature - managed.
[0021] In a technical solution of the above - mentioned temperature management device, the temperature data includes at least one of the device area temperature and the ambient temperature of the device to be temperature - managed;
[0022] The device area temperature is obtained by a temperature acquisition device provided on the device to be temperature - managed.
[0023] In a technical solution of the above - mentioned temperature management device, the training data set includes a training set; the device further includes a model training module; the model training module is configured to:
[0024] Based on the training set and a preset sliding window, construct sequence data; use the sequence data as the input data of the deep learning model, and apply the early stopping method to train the deep learning model.
[0025] In one technical solution of the above temperature management device, the training data set further includes a validation set; the device further includes a performance verification module:
[0026] The performance verification module is configured to perform performance verification on the deep learning model according to the validation set.
[0027] In one technical solution of the above temperature management device, the training data set further includes an evaluation set; the device further includes an evaluation module:
[0028] The evaluation module is configured to perform model evaluation on the deep learning model according to the evaluation set to obtain an evaluation result; and adjust the model structure and / or model parameters of the deep learning model according to the evaluation result.
[0029] In one technical solution of the above temperature management device, the device to be temperature-managed is the flexible printed circuit of the electronic device;
[0030] The deep learning model is a long short-term memory network model.
[0031] In a second aspect, a temperature management method is provided, and the method includes:
[0032] Obtain real-time acquisition data of the device to be temperature-managed in the electronic device;
[0033] Based on the deep learning model, obtain a temperature prediction result of the device to be temperature-managed according to the real-time acquisition data;
[0034] Perform temperature management on the device to be temperature-managed according to the temperature prediction result;
[0035] The deep learning model is trained based on a preset training data set, and the training data set includes historical acquisition data obtained by periodically collecting data on the device to be temperature-managed at historical moments; the method further includes;
[0036] Periodically collect data on the device to be temperature-managed according to a preset collection frequency to obtain historical acquisition data;
[0037] Obtain the training data set according to the historical acquisition data.
[0038] In a third aspect, an electronic device is provided, and the electronic device includes a device to be temperature-managed and the temperature management device according to any one of the above technical solutions of the temperature management device.
[0039] One or more of the above technical solutions of the present application have at least one or more of the following beneficial effects:
[0040] In implementing the technical solution of the temperature management device provided by the present application, the temperature management device of the present application includes a data acquisition module, a temperature prediction module, and a temperature management module. The data acquisition module is configured to obtain real-time acquisition data of the device to be temperature-managed in the electronic device; the temperature prediction module is configured to perform temperature prediction on the device to be temperature-managed based on a deep learning model according to the real-time acquisition data to obtain a temperature prediction result; the temperature management module is configured to perform temperature management on the device to be temperature-managed according to the temperature prediction result. Through the above configuration method, since the deep learning model of the present application is obtained by training based on a training data set, and the training data set includes historical acquisition data obtained by regularly collecting data on the device to be temperature-managed, the deep learning model can accurately and effectively predict the temperature of the device to be temperature-managed, obtain an accurate temperature prediction result, and perform precise and effective temperature management on the device to be temperature-managed according to the temperature prediction result, thereby effectively protecting the device to be temperature-managed and avoiding damage to the device to be temperature-managed caused by overcooling or overheating, and effectively extending the service life of the device to be temperature-managed. At the same time, since the temperature management device of the embodiment of the present application uses a deep learning model for temperature prediction, it can also implement the self-learning mechanism of the deep learning model, thereby continuously optimizing the deep learning mode according to the historical acquisition data and the actual temperature management process, thereby continuously improving the accuracy of temperature prediction and the effectiveness of temperature management, and being able to better adapt to the changes in the thermal behavior of the device to be temperature-managed and the adjustment of the working environment and conditions, and being able to achieve long-term stable temperature management. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] Referring to the accompanying drawings, the disclosure of the present application will become more understandable. It is easy for those skilled in the art to understand that these drawings are only for illustrative purposes and are not intended to limit the protection scope of the present application. Among them:
[0042] Figure 1 is a schematic diagram of the main component structure of a temperature management device according to an embodiment of the present application;
[0043] Figure 2 is a schematic diagram of the main step flow of a temperature management method according to an embodiment of the present application;
[0044] Figure 3 is a schematic diagram of the main component structure of an electronic device according to an embodiment of an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0045] The following describes some embodiments of the present application with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principle of the present application and are not intended to limit the protection scope of the present application.
[0046] In the description of this application, "module" and "processor" may include hardware, software, or a combination of both. A module may include a hardware circuit, various suitable sensors, communication ports, memory, and may also include a software part, such as program code, or may be a combination of software and hardware. The term "A and / or B" represents all possible combinations of A and B, such as only A, only B, or A and B. The term "at least one A or B" or "at least one of A and B" has a meaning similar to "A and / or B", and may include only A, only B, or A and B. The singular terms "a" and "the" may also include the plural form.
[0047] Here, some terms related to this application are explained first.
[0048] FPC: Flexible Printed Circuit, flexible printed circuit.
[0049] ML: Machine Learning, machine learning.
[0050] CPU: Central Processing Unit, central processing unit.
[0051] LSTM: Long Short-Term Memory, long short-term memory network.
[0052] Refer to the appendix Figure 1 , Figure 1 is a schematic diagram of the main component structure of a temperature management device according to an embodiment of this application. As Figure 1 shown, the temperature management device of the embodiment of this application mainly includes a data acquisition module, a temperature prediction module, and a temperature management model.
[0053] In this embodiment, the data acquisition module can be configured to obtain real-time acquisition data of the device to be temperature-managed in the electronic device. Among them, the real-time acquisition data is real-time acquired acquisition data related to the temperature of the device to be temperature-managed. The temperature prediction module can be configured to obtain a temperature prediction result of the device to be temperature-managed based on a deep learning model according to the real-time acquisition data. The temperature management module can be configured to perform temperature management on the device to be temperature-managed according to the temperature prediction result. The temperature management device may further include a training data acquisition module, and the training data acquisition module may include a historical data acquisition unit and a training data acquisition unit. The historical data acquisition unit can be configured to perform regular data acquisition on the device to be temperature-managed according to a preset acquisition frequency to obtain historical acquisition data. The training data acquisition unit can be configured to obtain a training data set according to the historical acquisition data.
[0054] In one embodiment, the real-time data collection may include the temperature data, current data, and voltage data of the device to be temperature-managed. Specifically, the device temperature of the device to be temperature-managed can be obtained according to the temperature collection device set on the device to be temperature-managed, and the ambient temperature of the environment where the device to be temperature-managed is located can be collected as the temperature data. The voltages corresponding to the positive power supply (ELVDD) and negative power supply (ELVSS) of the device to be managed can be collected as the voltage data, and the currents corresponding to the positive power supply (ELVDD) and negative power supply (ELVSS) of the device to be managed can be collected as the current data.
[0055] In one embodiment, the electronic device may be, but is not limited to, a mobile phone, a tablet computer, a desktop computer, a laptop computer, a handheld computer, a notebook computer, a vehicle-mounted device, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), an augmented reality (AR) / virtual reality (VR) device, etc.
[0056] In one embodiment, the device to be temperature-managed may be an FPC in an electronic device, such as an FPC applied to an OLED (Organic Light-Emitting Diode) screen. The device to be temperature-managed may also be other electronic devices in the electronic device that require precise temperature control. The device to be temperature-managed may also be an electronic device or device composed of one or more electronic devices.
[0057] In one embodiment, the temperature collection device may be a temperature sensor. Taking the device to be temperature-managed as an FPC as an example, a high-precision temperature sensor can be installed at the position to be temperature-managed of the FPC (such as the device area), and the temperature sensor communicates with the main board of the electronic device through a standard interface (such as the I2C, SPI interface), so as to transmit the real-time collected data to the electronic device.
[0058] In one embodiment, the deep learning model is obtained by training based on a preset training data set, and the training data set includes historical collection data obtained by regularly collecting data on the device to be temperature-managed at historical moments. Among them, the historical collection data is the collection data related to the temperature of the device to be temperature-managed collected at historical moments.
[0059] In one embodiment, the historical collection data may include the temperature data, current data, and voltage data of the device to be temperature-managed.
[0060] In one embodiment, the deep learning model can be an LSTM model. Based on the LSTM model, temperature prediction can be performed on the device to be temperature-managed according to real-time collected data, and the future temperature change trend of the device to be temperature-managed can be obtained as the temperature prediction result of the device to be temperature-managed.
[0061] In one embodiment, the LSTM model can include two layers of LSTM network structures, with each layer including 100 units, a dropout rate of 0.2, the mean squared error (MSE) selected as the loss function, and the Adam optimizer for updating the model weights.
[0062] In one embodiment, regular data collection can be performed on the device to be temperature-managed to obtain historical collected data. For example, regular data collection can be performed on parameters such as the voltage data, current data, device area temperature, and ambient temperature of the device to be temperature-managed, so as to assist in temperature prediction based on these parameters.
[0063] In one embodiment, the preset collection frequency can be once per second. For example, if continuous collection is performed for 24 hours every day for one month, 720,000 sets of data can be obtained.
[0064] In one embodiment, the training data acquisition unit can include a data cleaning subunit and a normalization processing subunit.
[0065] In this embodiment, the data cleaning subunit can be configured to perform data cleaning on the historical collected data to obtain the result of cleaning the historical collected data. The normalization processing subunit can be configured to perform data normalization processing on the result of cleaning the historical collected data to obtain the training data set.
[0066] In one embodiment, statistical methods (such as mean and standard deviation) can be used to remove outliers and noise values to achieve the cleaning of the historical collected data.
[0067] In one embodiment, the minmax normalization (deviation normalization) method can be used to perform data normalization processing on the result of cleaning the historical collected data, and scale the data to the range of [0,1], thereby obtaining the training data set.
[0068] In one embodiment, the training data set can be divided into a training set, a validation set, and an evaluation set. In a specific example, the training data set can be divided according to the following ratio: training set (70%), validation set (15%), and test set (15%).
[0069] In one embodiment, the temperature management device can further include a model training module.
[0070] In this embodiment, the model training module can be configured to construct sequence data based on a preset sliding window according to a training set; use the sequence data as input data for a deep learning model, and apply early stopping to train the deep learning model. That is, sequence data can be constructed according to a preset sliding window, the sequence data can be input into the deep learning model, and early stopping can be applied to avoid overfitting and train the deep learning model.
[0071] In one embodiment, the window length of the preset sliding window can be 10.
[0072] In one embodiment, hyperparameters such as the learning rate (e.g., 0.001, 0.0001) and batch size (e.g., 32, 64) of the deep learning model can be adjusted using grid search.
[0073] In one embodiment, the temperature management device can include a performance verification module. The performance verification module can be configured to perform performance verification on the deep learning model using a validation set.
[0074] In one embodiment, the temperature management device can include an evaluation module. The evaluation module can be configured to evaluate the deep learning model according to an evaluation set to obtain an evaluation result, and adjust the model structure and model parameters of the deep learning model according to the evaluation result. Specifically, the deep learning model can be evaluated using the evaluation set, paying attention to the prediction accuracy (e.g., the root mean square error RMES of the prediction result) and generalization ability of the deep learning model, and adjusting the model structure and model parameters of the deep learning model based on the evaluation result to improve the model performance of the deep learning model.
[0075] In one embodiment, the trained deep learning model can be deployed in an embedded device on the main board of an electronic device to achieve temperature prediction of the device to be temperature-managed.
[0076] In one embodiment, the heat dissipation device can be a fan or a liquid cooling device.
[0077] In one embodiment, an embedded device or microcontroller (such as Raspberry Pi or Arduino) can be integrated on the main board of the electronic device, which is responsible for receiving the real-time acquisition data collected by the temperature sensor and performing data interaction with the central processing unit (CPU) of the electronic device through a standard communication interface (such as UART or I2C). The deep learning model in the embedded device or microcontroller can perform temperature prediction based on the real-time acquisition data, generate the temperature prediction result for the device to be temperature-managed, and obtain the future temperature trend of the device to be temperature-managed. Based on the temperature prediction result of the deep learning model, the CPU can adjust the heat dissipation device of the device to be temperature-managed (for example, control the fan or liquid cooling device through PWM) to achieve the temperature management of the device to be temperature-managed.
[0078] In one embodiment, a self-learning mechanism of the deep learning model can be designed to enable it to continuously perform self-learning optimization based on historical data and actual temperature management effects. The deep learning model can improve the prediction accuracy and device performance by continuously learning and adapting to new temperature management and prediction patterns. The update frequency of the deep learning model can be set according to the actual operation situation and data accumulation period (for example, weekly or monthly). New acquisition data can be collected from the real-time detection and temperature management process to update the training data set, so as to improve the prediction ability of the deep learning model.
[0079] In one embodiment, the electronic device can include a microcontroller and a CPU (Central Processing Unit), and the deep learning model can be deployed on the microcontroller. The microcontroller can perform temperature prediction on the device to be temperature-managed to obtain the temperature prediction result. Based on the temperature prediction result, the CPU can adjust the heat dissipation device to achieve the temperature management of the device to be temperature-managed.
[0080] Based on the above configuration method, the temperature management device according to the embodiments of the present application includes a data acquisition module, a temperature prediction module, and a temperature management module. The data acquisition module is configured to obtain real-time acquisition data of the device to be temperature-managed in the electronic device; the temperature prediction module is configured to perform temperature prediction on the device to be temperature-managed based on a deep learning model according to the real-time acquisition data to obtain a temperature prediction result; the temperature management module is configured to perform temperature management on the device to be temperature-managed according to the temperature prediction result. Through the above configuration method, since the deep learning model of the embodiments of the present application is obtained by training based on a training data set, and the training data set includes historical acquisition data obtained by periodically acquiring data of the device to be temperature-managed, the deep learning model can accurately and effectively predict the temperature of the device to be temperature-managed, obtain an accurate temperature prediction result, and realize precise and effective temperature management of the device to be temperature-managed according to the temperature prediction result, thereby effectively protecting the device to be temperature-managed and avoiding damage to the device to be temperature-managed caused by overcooling or overheating, and effectively extending the service life of the device to be temperature-managed. At the same time, since the temperature management device of the embodiments of the present application uses a deep learning model for temperature prediction, it can also implement the self-learning mechanism of the deep learning model, so as to continuously optimize the deep learning mode according to the historical acquisition data and the actual temperature management process, thereby continuously improving the accuracy of temperature prediction and the effectiveness of temperature management, and being able to better adapt to the changes in the thermal behavior of the device to be temperature-managed and the adjustment of the working environment and conditions, and realizing long-term stable temperature management.
[0081] In an application scenario according to the embodiments of the present application, taking the electronic device as a mobile phone and the device to be temperature-managed as an FPC device as an example, in combination with Figure 2 ,the temperature management device according to the embodiments of the present application will be described.
[0082] As Figure 2 shown, the FPC device in the mobile phone is used to connect the screen. A heat dissipation device and a temperature sensor are provided on the FPC device, and a CPU and a microcontroller are provided on the mobile phone motherboard. The temperature sensor can be used to collect the device area temperature of the FPC device. It can also collect the current data and voltage data of the FPC device. The microcontroller can include a data acquisition module for collecting the ambient temperature of the environment where the FPC device is located. The LSTM prediction model can be deployed in the microcontroller. The microcontroller can also include a temperature prediction module. The temperature prediction module can perform temperature prediction on the FPC device based on the LSTM prediction model according to the ambient temperature, current data, voltage data, and device area temperature to obtain a temperature prediction result, and send the temperature prediction result to the CPU. The CPU can include a temperature management module. The temperature management module can perform feedback control on the heat dissipation device of the FPC device according to the temperature prediction result, so as to realize temperature management of the FPC device.
[0083] Furthermore, the present application also provides a temperature management method.
[0084] Refer to the appendix Figure 2 , Figure 2 which is a schematic diagram of the main steps of the temperature management method according to an embodiment of the present application. As Figure 2 shown, the temperature management method in the embodiment of the present application mainly includes the following steps S101 to S103.
[0085] Step S101: Obtain the real-time acquisition data of the device to be temperature-managed in the electronic device.
[0086] Step S102: Based on the deep learning model, obtain the temperature prediction result of the device to be temperature-managed according to the real-time acquisition data.
[0087] Step S103: Perform temperature management on the device to be temperature-managed according to the temperature prediction result.
[0088] The deep learning model can be obtained by training based on a preset training data set, and the training data set includes historical acquisition data obtained by regularly collecting data of the device to be temperature-managed at historical moments; the temperature management method in the embodiment of the present application may further include the following steps S104 and S105:
[0089] Step S104: Regularly collect data of the device to be temperature-managed according to the preset acquisition frequency to obtain historical acquisition data.
[0090] Step S105: Obtain the training data set according to the historical acquisition data.
[0091] It should be noted that although the above embodiments describe the various steps in a specific order, those skilled in the art can understand that in order to achieve the effects of the present application, it is not necessary for different steps to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders, and the adjusted solutions are equivalent technical solutions to the technical solutions described in the present application, and thus will also fall within the protection scope of the present application.
[0092] Those skilled in the art can understand that all or part of the processes in the methods of the above-mentioned embodiments of the present application can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable storage medium can include: any entity or device, medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal, and software distribution medium, etc., that can carry the computer program code.
[0093] Another aspect of the present application also provides a computer-readable storage medium.
[0094] In an embodiment of a computer-readable storage medium according to the present application, the computer-readable storage medium can be configured to store a program for executing the temperature management method of the above-mentioned method embodiments. The program can be loaded and run by a processor to implement the above-mentioned temperature management method. For the sake of convenience of description, only the parts related to the embodiments of the present application are shown. For the specific technical details not disclosed, please refer to the method part of the embodiments of the present application. The computer-readable storage medium can be a storage device formed by various electronic devices, such as magnetic disks, hard disks, optical disks, flash memories, read-only memories, random access memories, etc. Optionally, the computer-readable storage medium in the embodiments of the present application is a non-transitory computer-readable storage medium.
[0095] Another aspect of the present application also provides an electronic device.
[0096] In an embodiment of an electronic device according to the present application, the electronic device can include a device to be temperature-managed and the temperature management device described in any one of the above-mentioned embodiments of the temperature management device.
[0097] The electronic device described in the present application can be, but is not limited to, mobile phones, tablet computers, desktop computers, laptop computers, handheld computers, notebook computers, vehicle-mounted devices, ultra-mobile personal computers (UMPCs), netbooks, personal digital assistants (PDAs), augmented reality (AR) / virtual reality (VR) devices, etc. The embodiments of the present application do not make any limitations in this regard.
[0098] So far, the technical solution of the present application has been described in conjunction with an embodiment shown in the accompanying drawings. However, those skilled in the art can easily understand that the protection scope of the present application is obviously not limited to these specific embodiments. Without departing from the principle of the present application, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present application.
Claims
1. A temperature management device, characterized in that: The device comprises: A data acquisition module, which is configured to obtain real-time data collected from a device to be temperature managed in an electronic device; A temperature prediction module, configured to obtain a temperature prediction result of the device to be temperature managed according to the real-time collected data based on a deep learning model; a temperature management module, configured to perform temperature management on the device to be temperature managed according to the temperature prediction result; The deep learning model is obtained by training based on a preset training data set, wherein the training data set includes historical data collected by periodically collecting data of the temperature-managed device at historical moments; the device also includes a training data acquisition module; the training data acquisition module includes a historical data acquisition unit and a training data acquisition unit; The historical data collection unit is configured to perform periodic data collection on the temperature-managed device according to a preset collection frequency to obtain historical collection data; The training data acquisition unit is configured to acquire the training data set according to the historical collected data.
2. The temperature management device according to claim 1, characterized in that: The temperature-managed device is provided with a heat dissipation device; The temperature management module is further configured to: According to the temperature prediction result, the heat dissipation device is adjusted to achieve temperature management of the component to be temperature managed.
3. The temperature management device according to claim 1, characterized in that: The training data acquisition unit includes a data cleaning subunit and a normalization processing subunit; The data cleaning subunit is configured to perform data cleaning on the historically collected data and obtain a cleaning result of the historically collected data; The normalization processing subunit is configured to perform data normalization processing on the historical collection data cleaning result to obtain the training data set.
4. The temperature management device according to claim 1, characterized in that The real-time collected data includes at least one of the temperature data, current data, and voltage data of the device to be temperature managed; The historically collected data includes at least one of temperature data, current data, and voltage data of the device to be temperature managed.
5. The temperature management device according to claim 4, characterized in that: The temperature data includes at least one of a device area temperature of the device to be temperature managed and an ambient temperature; The device zone temperature is acquired according to a temperature acquisition device provided on the device to be temperature managed.
6. The temperature management device according to claim 1, characterized in that: The training data set includes a training set; the device also includes a model training module; the model training module is configured to: According to the training set, based on a preset sliding window, sequence data is constructed; the sequence data is used as input data of the deep learning model, and the early stopping method is applied to train the deep learning model.
7. The temperature management device according to claim 6, characterized in that The training data set also includes a verification set; the device also includes a performance verification module: The performance verification module is configured to perform performance verification on the deep learning model based on the verification set.
8. The temperature management device according to claim 6, characterized in that: The training data set also includes an evaluation set; the device also includes an evaluation module: The evaluation module is configured to perform model evaluation on the deep learning model according to the evaluation set to obtain an evaluation result; and adjust the model structure and / or model parameters of the deep learning model according to the evaluation result.
9. The temperature management device according to any one of claims 1 to 8, characterized in that: The device to be temperature managed is a flexible printed circuit of the electronic device; The deep learning model is a long short-term memory network model.
10. A temperature management method, characterized in that: The method comprises: Obtain real-time data of temperature-managed components in electronic equipment; Based on the deep learning model, according to the real-time collected data, a temperature prediction result of the device to be temperature managed is obtained; Performing temperature management on the device to be temperature managed according to the temperature prediction result; The deep learning model is obtained by training based on a preset training data set, wherein the training data set includes historical collection data obtained by periodically collecting data of the device to be temperature managed at historical moments; the method further includes: According to a preset collection frequency, periodically collect data of the device to be temperature managed to obtain historical collection data; The training data set is obtained according to the historical collected data.
11. An electronic device, characterized in that: include: a device to be temperature managed; and, The temperature management device according to any one of claims 1 to 9.