A visual dynamic control method for tablet computer based on heat dissipation balance

Abstract

The present invention discloses a visual dynamic control method for a tablet computer based on heat dissipation balance, which relates to the field of heat dissipation visual control technology, including: establishing a three-dimensional heat conduction model of the core components of chips, screens and batteries; constructing a double-layer network architecture; deploying phase change materials at hot nodes, and realizing on-demand heat storage and heat release through electro-induced phase change technology; using a front camera to realize augmented reality technology projection of the thermal field on the surface of the device; constructing a ternary decision tree of energy consumption, performance and heat dissipation, and providing dynamic optimization suggestions in the augmented reality technology interface; integrating a micro piezoelectric pump in the device frame, and driving nanofluids for directional heat transfer through a blood vessel pulsation algorithm; and establishing a thermal management knowledge map containing environmental parameters and usage habits. By quantifying the contribution of each application scenario to each area, the precise allocation of heat dissipation resources is realized, the heat dissipation efficiency is improved, and the augmented reality technology projection of the thermal field on the surface of the device is realized using a front camera.

Description

Technical Field

[0001] The invention relates to the technical field of heat dissipation visualization control, and in particular to a tablet computer visualization dynamic control method based on heat dissipation balance. Background Art

[0002] With the rapid development of information technology, tablet computers have become an indispensable smart device in people's daily lives and are widely used in entertainment, office, learning and other fields. However, with the continuous improvement of device performance, power consumption and heat dissipation issues have become increasingly prominent, becoming a key factor restricting the performance of tablet computers and user experience. Especially in long-term high-load operation and complex and changeable usage environments, how to effectively manage the thermal distribution of tablet computers and ensure their stable operation under high performance has become a technical problem to be solved.

[0003] The core components of tablet computers, such as chips, screens, and batteries, will generate a lot of heat when used intensively. If they cannot be dissipated in a timely and effective manner, they will lead to device performance degradation, system crashes, and even hardware damage. Traditional heat dissipation solutions, such as passive heat dissipation such as heat sinks and fans, and active heat dissipation such as liquid cooling systems, have alleviated the heat dissipation problem to a certain extent, but they often have limitations such as low heat dissipation efficiency, high energy consumption, and large size, which are difficult to meet the needs of modern tablet computers for thinness and high performance. Therefore, it is particularly important to develop a heat dissipation management method that can not only dissipate heat efficiently but also take into account the size and energy consumption of the device. Summary of the invention

[0004] In order to solve the above technical problems, a visual dynamic control method for a tablet computer based on heat dissipation balance is provided. This technical solution solves the problems raised in the above background technology.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A visual dynamic control method for a tablet computer based on heat dissipation balance, comprising:

[0007] Establish a three-dimensional heat conduction model for the core components of chips, screens, and batteries, generate a dynamic heat source fingerprint map based on historical usage data, and quantify the contribution of each application scenario to each area;

[0008] Build a two-layer network architecture. The perception layer network analyzes temperature gradients, application loads, and ambient temperature and humidity in real time, and the decision layer network outputs dynamic scheduling strategies.

[0009] Deploy phase change materials at heat nodes, realize on-demand heat storage and release through electro-induced phase change technology, and optimize the triggering timing and intensity by combining reinforcement learning decision-making;

[0010] The front camera is used to realize the augmented reality projection of the thermal field on the surface of the equipment, display the temperature distribution through color gradient, and support gesture interaction to view the real-time temperature and heat source contribution of each point;

[0011] Construct a three-element decision tree of energy consumption, performance and heat dissipation, combine multi-objective optimization theory and hierarchical analysis method, realize intelligent decision support, and provide dynamic optimization suggestions on the augmented reality technology interface;

[0012] A micro piezoelectric pump is integrated in the device frame to drive the nanofluid for directional heat transfer through a blood vessel pulsation algorithm. The pulse frequency is dynamically adjusted by the heat flux density field gradient to achieve active heat dissipation.

[0013] A thermal management knowledge graph that includes environmental parameters and usage habits is established to continuously optimize control strategies. Users can share anonymous data to participate in global model training, and the system generates personalized cooling performance reports every month.

[0014] Preferably, the three-dimensional heat conduction model of the core components of the chip, screen and battery is established, and a dynamic heat source fingerprint is generated in combination with historical usage data to quantify the contribution of each application scenario to each area. Specifically, it includes:

[0015] Collect geometric dimensions, material properties, and heat source distribution information of core components of chips, screens, and batteries, including thermal conductivity and specific heat capacity;

[0016] Clean and format the collected data to ensure data quality and consistency;

[0017] Use 3D modeling software to build 3D geometric models of the core components of chips, screens, and batteries, and assign corresponding thermal parameters to each part in the model based on material properties;

[0018] Use finite element analysis to simulate the heat conduction process and mesh the three-dimensional geometric model;

[0019] Set boundary conditions and initial conditions for ambient temperature and heat source intensity, and run the simulation to obtain the temperature distribution and heat flow path of each component of the tablet computer;

[0020] Collect historical usage data under different application scenarios, the usage data including usage time, power consumption and temperature;

[0021] Correlate historical usage data with simulation results from a three-dimensional heat conduction model to analyze heat source distribution and temperature changes in different application scenarios;

[0022] Extracting key heat source features, wherein the key heat source features include heat source location, intensity, and duration;

[0023] Based on the extracted heat source features, a dynamic heat source fingerprint map is generated using visualization tools to intuitively display the heat source distribution and changes in different application scenarios;

[0024] Based on actual needs, the quantitative indicators are set as the average values ​​of the temperature rise and the heat flux density change;

[0025] Quantitative indicators are used to calculate the contribution of each application scenario to each region.

[0026] Preferably, the two-layer network architecture is constructed, the perception layer network analyzes the temperature gradient, application load and ambient temperature and humidity in real time, and the decision layer network outputs a dynamic scheduling strategy, specifically including:

[0027] The perception layer network is responsible for data collection and preliminary processing. It collects temperature gradient, ambient temperature and humidity, and application load data in real time through various sensors and actuators.

[0028] Distributed fiber optic temperature sensors are embedded inside the tablet computer to achieve real-time reconstruction of sub-millimeter temperature fields;

[0029] By deploying humidity sensors, the ambient humidity of the tablet computer can be monitored in real time;

[0030] Deploy load monitoring sensors based on application requirements to obtain application load conditions in real time;

[0031] Establish a stable data transmission channel to transmit the collected data to the data processing center;

[0032] Calculate the temperature gradient, ambient temperature and humidity, and changes in application load in real time, and store the analysis results in the database for use by the decision-making network;

[0033] The decision-making network uses machine learning algorithms and models based on the data provided by the perception layer network to output dynamic scheduling strategies;

[0034] The decision-making layer network obtains real-time data and analysis results from the perception layer network;

[0035] Use historical data to train and validate machine learning models, and generate dynamic scheduling strategies based on real-time data and model prediction results;

[0036] Allocate different levels of resources to each task based on its priority and urgency;

[0037] When a task with a higher priority than the preset priority arrives, the resources of tasks with a lower priority than the preset priority will be preempted for the execution of the high priority task;

[0038] Based on the feedback from each node, task allocation and resource allocation are performed to dynamically adjust the application performance and resource allocation.

[0039] Preferably, the deployment of phase change materials at the heat nodes, the realization of on-demand heat storage and heat release through the electro-induced phase change technology, and the optimization of the triggering timing and intensity in combination with the reinforcement learning decision specifically include:

[0040] Determine whether the temperature range of the hot node exceeds the preset temperature threshold. If so, select the molten salt phase change material for heat storage and heat release; if not, select the organic phase change material for heat storage and heat release;

[0041] An electric heating element is integrated in the hot node, and the phase change material is heated by electric current to realize its phase change process;

[0042] Design control systems to monitor the temperature of hot nodes, the phase state of phase change materials, and the working status of electric heating elements;

[0043] When the thermal node needs to store heat, the control system starts the electric heating element, which heats the phase change material through electric current, causing it to change from solid to liquid and absorb heat;

[0044] When the hot node needs to release heat, the control system stops the heating of the electric heating element, and the phase change material gradually changes from liquid to solid under the influence of the ambient temperature, releasing heat;

[0045] The goal of reinforcement learning is to optimize the heat storage and release process of phase change materials and improve the energy efficiency of thermal nodes;

[0046] The environment is defined as the heat node and its surrounding heat exchange system, the agent is the control system, the state is the temperature of the heat node and the phase state of the phase change material, the action is to start or stop the heating of the electric heating element, and the reward is the degree of energy efficiency improvement of the heat node;

[0047] Collect data on the temperature of the hot node, the phase change of the phase change material and the working status of the electric heating element;

[0048] Use the collected data to train a reinforcement learning model, and based on the trained reinforcement learning model, give the real-time status and demand of the heat node, and make intelligent decisions on the timing and intensity of starting or stopping the heating of the electric heating element;

[0049] Through continuous iteration and optimization, the reinforcement learning model adapts to changes in thermal nodes and improves the efficiency of heat storage and release.

[0050] Preferably, the use of a front camera to implement augmented reality projection of the thermal field on the surface of the device, displaying the temperature distribution through color gradients, and supporting gesture interaction to view the real-time temperature and heat source contribution of each point specifically includes:

[0051] The front camera is used to capture real-time images of the device surface, while the thermal imaging sensor measures the temperature distribution on the device surface and generates thermal imaging data;

[0052] Fusion of images captured by the front camera with thermal imaging data to generate augmented reality images;

[0053] Based on thermal imaging data, color gradient technology is used to display the temperature distribution on the device surface, with red representing high temperature and blue representing low temperature;

[0054] Using a gesture recognition module to recognize a user's gesture input, and based on the recognized gesture, sending a corresponding operation instruction to the augmented reality application, the gesture includes clicking, sliding, and zooming;

[0055] The augmented reality application displays the real-time temperature and heat source contribution of the point selected by the user according to the instructions.

[0056] Preferably, the energy consumption-performance-heat dissipation ternary decision tree is constructed, and the multi-objective optimization theory and the analytic hierarchy process are combined to realize intelligent decision support, and the dynamic optimization suggestions are provided in the augmented reality technology interface, specifically including:

[0057] Collect energy consumption, performance and thermal data for each device, configuration and usage scenario;

[0058] Extract device power, processing speed, and heat dissipation efficiency from the data and output them as energy consumption, performance, and heat dissipation related features respectively;

[0059] The objective function is set as a weighted quantitative indicator of energy consumption, performance, and heat dissipation, and the constraints are set as the physical limitations of the device and the requirements of the usage scenario;

[0060] Energy consumption, performance, and heat dissipation are used as decision-making goals, device power, processing speed, and heat dissipation efficiency are used as the criterion layer, and specific devices and configurations are used as the solution layer;

[0061] The importance of each element in the same level with respect to each criterion in the previous level is compared pairwise and output as a judgment matrix;

[0062] Add up each row of the judgment matrix and divide it by the total number of factors to calculate the weight of each factor;

[0063] Based on the comparison results of weights and solution layers, the dynamic optimization suggestions are comprehensively ranked.

[0064] Preferably, the device frame is integrated with a micro piezoelectric pump, and the nanofluid is driven to perform directional heat transfer through a vascular pulsation algorithm, and the pulse frequency is dynamically adjusted by the heat flux density field gradient to achieve active heat dissipation, specifically including:

[0065] Use sensors to monitor the heat flux density field gradient inside the device in real time;

[0066] Dynamically adjust the pulse frequency of the micro piezoelectric pump based on the monitored heat flux density field gradient;

[0067] Determine whether the real-time heat flux density is higher than a preset density threshold, if so, increase the pulse frequency to increase the heat transfer speed of the nanofluid, if not, reduce the pulse frequency to reduce energy consumption and noise;

[0068] The pulsation waveform simulates the pulsation of human blood vessels and is driven by a sine wave;

[0069] A micro piezoelectric pump is integrated in the device frame, and active heat dissipation of the device is achieved through the synergistic effect of the micro piezoelectric pump and nanofluid.

[0070] Compared with the prior art, the present invention has the following beneficial effects:

[0071] By establishing a three-dimensional heat conduction model and combining it with a dynamic heat source fingerprint map, it is possible to quantify the contribution of each application scenario to each area, achieve accurate allocation of heat dissipation resources, and improve heat dissipation efficiency. By building a two-layer network architecture, it can analyze temperature gradients, application loads, and ambient temperature and humidity in real time, output dynamic scheduling strategies, and achieve a balance between heat dissipation and energy consumption. It supports gesture interaction to view the real-time temperature and heat source contribution of each point, which improves the user experience. The vascular pulsation algorithm is used to drive nanofluids for directional heat transfer. The pulse frequency is dynamically adjusted by the heat flux density field gradient to achieve active heat dissipation, which can more effectively export heat from the inside of the device and improve the heat dissipation effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 It is a flow chart of the visualized dynamic control method of a tablet computer based on heat dissipation balance of the present invention;

[0073] Figure 2 A flow chart of the method for establishing a three-dimensional heat conduction model of the core components of a chip, a screen and a battery according to the present invention;

[0074] Figure 3 A flow chart of the method for constructing a double-layer network architecture of the present invention;

[0075] Figure 4 This is a flow chart of the method for realizing on-demand heat storage and heat release through the electro-induced phase change technology of the present invention;

[0076] Figure 5 This is a flow chart of the augmented reality technology projection method for realizing the thermal field on the surface of the device using the front camera of the present invention;

[0077] Figure 6 A flow chart of the method for constructing a ternary decision tree of energy consumption, performance and heat dissipation according to the present invention;

[0078] Figure 7This is a flow chart of the method for directional heat transfer of nanofluids driven by a vascular pulsation simulation algorithm of the present invention. DETAILED DESCRIPTION

[0079] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0080] Reference Figure 1 As shown, a visual dynamic control method for a tablet computer based on heat dissipation balance includes:

[0081] Establish a three-dimensional heat conduction model for the core components of chips, screens, and batteries, generate a dynamic heat source fingerprint map based on historical usage data, and quantify the contribution of each application scenario to each area;

[0082] Build a two-layer network architecture. The perception layer network analyzes temperature gradients, application loads, and ambient temperature and humidity in real time, and the decision layer network outputs dynamic scheduling strategies.

[0083] Deploy phase change materials at heat nodes, realize on-demand heat storage and release through electro-induced phase change technology, and optimize the triggering timing and intensity by combining reinforcement learning decision-making;

[0084] The front camera is used to realize the augmented reality projection of the thermal field on the surface of the equipment, display the temperature distribution through color gradient, and support gesture interaction to view the real-time temperature and heat source contribution of each point;

[0085] Construct a three-element decision tree of energy consumption, performance and heat dissipation, combine multi-objective optimization theory and hierarchical analysis method, realize intelligent decision support, and provide dynamic optimization suggestions on the augmented reality technology interface;

[0086] A micro piezoelectric pump is integrated in the device frame to drive the nanofluid for directional heat transfer through a blood vessel pulsation algorithm. The pulse frequency is dynamically adjusted by the heat flux density field gradient to achieve active heat dissipation.

[0087] A thermal management knowledge graph that includes environmental parameters and usage habits is established to continuously optimize control strategies. Users can share anonymous data to participate in global model training, and the system generates personalized cooling performance reports every month.

[0088] Reference Figure 2 As shown in the figure, a three-dimensional heat conduction model of the core components of the chip, screen and battery is established, and a dynamic heat source fingerprint map is generated in combination with historical usage data to quantify the contribution of each application scenario to each area. Specifically, it includes:

[0089] Collect geometric dimensions, material properties, and heat source distribution information of core components of chips, screens, and batteries, including thermal conductivity and specific heat capacity;

[0090] Clean and format the collected data to ensure data quality and consistency;

[0091] Use 3D modeling software to build 3D geometric models of the core components of chips, screens, and batteries, and assign corresponding thermal parameters to each part in the model based on material properties;

[0092] Use finite element analysis to simulate the heat conduction process and mesh the three-dimensional geometric model;

[0093] Set boundary conditions and initial conditions for ambient temperature and heat source intensity, and run the simulation to obtain the temperature distribution and heat flow path of each component of the tablet computer;

[0094] Collect historical usage data under different application scenarios, the usage data including usage time, power consumption and temperature;

[0095] Correlate historical usage data with simulation results from a three-dimensional heat conduction model to analyze heat source distribution and temperature changes in different application scenarios;

[0096] Extracting key heat source features, wherein the key heat source features include heat source location, intensity, and duration;

[0097] Based on the extracted heat source features, a dynamic heat source fingerprint map is generated using visualization tools to intuitively display the heat source distribution and changes in different application scenarios;

[0098] Based on actual needs, the quantitative indicators are set as the average values ​​of the temperature rise and the heat flux density change;

[0099] Quantitative indicators are used to calculate the contribution of each application scenario to each region.

[0100] Quantitative indicators are used to calculate the contribution of each application scenario to each area of ​​the tablet computer. The specific calculation process involves taking a weighted average of the temperature rise and the heat flux density change, and allocating them according to the weight of the application scenario.

[0101] Reference Figure 3 As shown in the figure, a two-layer network architecture is constructed. The perception layer network analyzes the temperature gradient, application load, and ambient temperature and humidity in real time, and the decision layer network outputs a dynamic scheduling strategy, which specifically includes:

[0102] The perception layer network is responsible for data collection and preliminary processing. It collects temperature gradient, ambient temperature and humidity, and application load data in real time through various sensors and actuators.

[0103] Distributed fiber optic temperature sensors are embedded inside the tablet computer to achieve real-time reconstruction of sub-millimeter temperature fields;

[0104] By deploying humidity sensors, the ambient humidity of the tablet computer can be monitored in real time;

[0105] Deploy load monitoring sensors based on application requirements to obtain application load conditions in real time;

[0106] Establish a stable data transmission channel to transmit the collected data to the data processing center;

[0107] Calculate the temperature gradient, ambient temperature and humidity, and changes in application load in real time, and store the analysis results in the database for use by the decision-making network;

[0108] The decision-making network uses machine learning algorithms and models based on the data provided by the perception layer network to output dynamic scheduling strategies;

[0109] The decision-making layer network obtains real-time data and analysis results from the perception layer network;

[0110] Use historical data to train and validate machine learning models, and generate dynamic scheduling strategies based on real-time data and model prediction results;

[0111] Allocate different levels of resources to each task based on its priority and urgency;

[0112] When a task with a higher priority than the preset priority arrives, the resources of tasks with a lower priority than the preset priority will be preempted for the execution of the high priority task;

[0113] Based on the feedback from each node, task allocation and resource allocation are performed to dynamically adjust the application performance and resource allocation.

[0114] Distributed fiber optic temperature sensors should be embedded inside the tablet computer. These sensors should be evenly distributed in key heat dissipation areas to ensure that sub-millimeter temperature gradient changes can be captured. Humidity sensors should be deployed in the tablet computer's casing or at appropriate locations inside to monitor the ambient humidity in real time. Load monitoring sensors should be deployed near key components such as the CPU, GPU, and memory according to application requirements to obtain application load data in real time.

[0115] Reference Figure 4 As shown in the figure, phase change materials are deployed at the heat nodes, and heat storage and release on demand are realized through electro-induced phase change technology. The triggering timing and intensity are optimized by combining reinforcement learning decision-making, including:

[0116] Determine whether the temperature range of the hot node exceeds the preset temperature threshold. If so, select the molten salt phase change material for heat storage and heat release; if not, select the organic phase change material for heat storage and heat release;

[0117] An electric heating element is integrated in the hot node, and the phase change material is heated by electric current to realize its phase change process;

[0118] Design control systems to monitor the temperature of hot nodes, the phase state of phase change materials, and the working status of electric heating elements;

[0119] When the thermal node needs to store heat, the control system starts the electric heating element, which heats the phase change material through electric current, causing it to change from solid to liquid and absorb heat;

[0120] When the hot node needs to release heat, the control system stops the heating of the electric heating element, and the phase change material gradually changes from liquid to solid under the influence of the ambient temperature, releasing heat;

[0121] The goal of reinforcement learning is to optimize the heat storage and release process of phase change materials and improve the energy efficiency of thermal nodes;

[0122] The environment is defined as the heat node and its surrounding heat exchange system, the agent is the control system, the state is the temperature of the heat node and the phase state of the phase change material, the action is to start or stop the heating of the electric heating element, and the reward is the degree of energy efficiency improvement of the heat node;

[0123] Collect data on the temperature of the hot node, the phase change of the phase change material and the working status of the electric heating element;

[0124] Use the collected data to train a reinforcement learning model, and based on the trained reinforcement learning model, give the real-time status and demand of the heat node, and make intelligent decisions on the timing and intensity of starting or stopping the heating of the electric heating element;

[0125] Through continuous iteration and optimization, the reinforcement learning model adapts to changes in thermal nodes and improves the efficiency of heat storage and release.

[0126] The selected phase change material is encapsulated in a high temperature resistant and corrosion resistant container to ensure that the material will not leak or pollute the environment during the phase change process. These encapsulated phase change material units are integrated inside or near the hot node to facilitate connection with the electric heating element and the heat exchange system.

[0127] Reference Figure 5 As shown in the figure, the front camera is used to realize the augmented reality technology projection of the thermal field on the surface of the equipment, the temperature distribution is displayed through color gradient, and gesture interaction is supported to view the real-time temperature and heat source contribution of each point. Specifically, it includes:

[0128] The front camera is used to capture real-time images of the device surface, while the thermal imaging sensor measures the temperature distribution on the device surface and generates thermal imaging data;

[0129] Fusion of images captured by the front camera with thermal imaging data to generate augmented reality images;

[0130] Based on thermal imaging data, color gradient technology is used to display the temperature distribution on the device surface, with red representing high temperature and blue representing low temperature;

[0131] Using a gesture recognition module to recognize a user's gesture input, and based on the recognized gesture, sending a corresponding operation instruction to the augmented reality application, the gesture includes clicking, sliding, and zooming;

[0132] The augmented reality application displays the real-time temperature and heat source contribution of the point selected by the user according to the instructions.

[0133] Integrate the front camera, thermal imaging sensor, gesture recognition module and augmented reality application into a complete system, and debug the system to ensure that the parts can work together and that functions such as image fusion, color gradient, gesture recognition and interaction are normal.

[0134] Reference Figure 6 As shown in the figure, a ternary decision tree of energy consumption, performance and heat dissipation is constructed, and multi-objective optimization theory and hierarchical analysis method are combined to realize intelligent decision support, and dynamic optimization suggestions are provided in the augmented reality technology interface, including:

[0135] Collect energy consumption, performance and thermal data for each device, configuration and usage scenario;

[0136] Extract device power, processing speed, and heat dissipation efficiency from the data and output them as energy consumption, performance, and heat dissipation related features respectively;

[0137] The objective function is set as a weighted quantitative indicator of energy consumption, performance, and heat dissipation, and the constraints are set as the physical limitations of the device and the requirements of the usage scenario;

[0138] Energy consumption, performance, and heat dissipation are used as decision-making goals, device power, processing speed, and heat dissipation efficiency are used as the criterion layer, and specific devices and configurations are used as the solution layer;

[0139] The importance of each element in the same level with respect to each criterion in the previous level is compared pairwise and output as a judgment matrix;

[0140] Add up each row of the judgment matrix and divide it by the total number of factors to calculate the weight of each factor;

[0141] Based on the comparison results of weights and solution layers, the dynamic optimization suggestions are comprehensively ranked.

[0142] The physical limitations of the equipment include maximum power consumption, maximum operating temperature, etc. The requirements of the usage scenarios include performance requirements, heat dissipation requirements, etc. Energy consumption, performance and heat dissipation are used as decision goals and are located at the top layer of the decision tree. Equipment power, processing speed and heat dissipation efficiency are used as the criterion layer and are located in the middle layer of the decision tree. Specific equipment and configuration are used as the solution layer and are located at the bottom layer of the decision tree.

[0143] Reference Figure 7 As shown, a micro piezoelectric pump is integrated in the device frame, and the nanofluid is driven to perform directional heat transfer through a vascular pulsation algorithm. The pulse frequency is dynamically adjusted by the heat flux density field gradient to achieve active heat dissipation. Specifically, it includes:

[0144] Use sensors to monitor the heat flux density field gradient inside the device in real time;

[0145] Dynamically adjust the pulse frequency of the micro piezoelectric pump based on the monitored heat flux density field gradient;

[0146] Determine whether the real-time heat flux density is higher than a preset density threshold, if so, increase the pulse frequency to increase the heat transfer speed of the nanofluid, if not, reduce the pulse frequency to reduce energy consumption and noise;

[0147] The pulsation waveform simulates the pulsation of human blood vessels and is driven by a sine wave;

[0148] A micro piezoelectric pump is integrated in the device frame, and active heat dissipation of the device is achieved through the synergistic effect of the micro piezoelectric pump and nanofluid.

[0149] Select a micro piezoelectric pump of appropriate size to ensure that its flow, pressure and pulsation performance meet the equipment's heat dissipation requirements; design a special pump installation position on the equipment frame to ensure that the pump is connected to the heat dissipation channel inside the equipment; when integrating the micro piezoelectric pump, pay attention to the layout of its power connection and signal control lines to ensure that it does not interfere with other functions of the equipment.

[0150] Furthermore, the present solution also proposes a computer-readable storage medium on which a computer-readable program is stored. When the computer-readable program is called, the above-mentioned visual dynamic control method of a tablet computer based on heat dissipation balance is executed.

[0151] It is understandable that the storage medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; an optical medium, such as a DVD; or a semiconductor medium, such as a solid state drive (SSD).

[0152] In summary, the advantages of the present invention are: by establishing a three-dimensional heat conduction model and combining it with a dynamic heat source fingerprint map, it is possible to quantify the contribution of each application scenario to each area, realize accurate allocation of heat dissipation resources, and improve heat dissipation efficiency; by constructing a two-layer network architecture, it is possible to analyze temperature gradients, application loads, and ambient temperature and humidity in real time, output dynamic scheduling strategies, and achieve a balance between heat dissipation and energy consumption; it supports gesture interaction to view the real-time temperature and heat source contribution of each point, thereby improving the user experience; it drives nanofluids for directional heat transfer through a vascular pulsation algorithm, and the pulse frequency is dynamically adjusted by the heat flux density field gradient to achieve active heat dissipation, which can more effectively export heat from the inside of the device and improve the heat dissipation effect.

[0153] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A visual dynamic control method for a tablet computer based on heat dissipation balance, characterized in that: include: Establish a three-dimensional heat conduction model for the core components of chips, screens, and batteries, generate a dynamic heat source fingerprint map based on historical usage data, and quantify the contribution of each application scenario to each area; Build a two-layer network architecture. The perception layer network analyzes temperature gradients, application loads, and ambient temperature and humidity in real time, and the decision layer network outputs dynamic scheduling strategies. Deploy phase change materials at heat nodes, realize on-demand heat storage and release through electro-induced phase change technology, and optimize the triggering timing and intensity by combining reinforcement learning decision-making; The front camera is used to realize the augmented reality projection of the thermal field on the surface of the equipment, display the temperature distribution through color gradient, and support gesture interaction to view the real-time temperature and heat source contribution of each point; Construct a three-element decision tree of energy consumption, performance and heat dissipation, combine multi-objective optimization theory and hierarchical analysis method, realize intelligent decision support, and provide dynamic optimization suggestions on the augmented reality technology interface; A micro piezoelectric pump is integrated in the device frame to drive the nanofluid for directional heat transfer through a blood vessel pulsation algorithm. The pulse frequency is dynamically adjusted by the heat flux density field gradient to achieve active heat dissipation. Establish a thermal management knowledge graph that includes environmental parameters and usage habits, continuously optimize control strategies, and users can share anonymous data to participate in global model training. The system generates personalized cooling performance reports every month. The device frame is integrated with a micro piezoelectric pump, and the nanofluid is driven to perform directional heat transfer through a vascular pulsation algorithm. The pulse frequency is dynamically adjusted by the heat flux density field gradient to achieve active heat dissipation. Specifically, the following are included: Use sensors to monitor the heat flux density field gradient inside the device in real time; Dynamically adjust the pulse frequency of the micro piezoelectric pump based on the monitored heat flux density field gradient; Determine whether the real-time heat flux density is higher than a preset density threshold, if so, increase the pulse frequency to increase the heat transfer speed of the nanofluid, if not, reduce the pulse frequency to reduce energy consumption and noise; The pulsation waveform simulates the pulsation of human blood vessels and is driven by a sine wave; A micro piezoelectric pump is integrated in the device frame, and active heat dissipation of the device is achieved through the synergistic effect of the micro piezoelectric pump and nanofluid.

2. According to the method of claim 1, the visual dynamic control method of a tablet computer based on heat dissipation balance is characterized in that: The three-dimensional heat conduction model of the core components of the chip, screen and battery is established, and a dynamic heat source fingerprint is generated in combination with historical usage data to quantify the contribution of each application scenario to each area. Specifically, it includes: Collect geometric dimensions, material properties, and heat source distribution information of core components of chips, screens, and batteries, including thermal conductivity and specific heat capacity; Clean and format the collected data to ensure data quality and consistency; Use 3D modeling software to build 3D geometric models of the core components of chips, screens, and batteries, and assign corresponding thermal parameters to each part in the model based on material properties; Use finite element analysis to simulate the heat conduction process and mesh the three-dimensional geometric model; Set boundary conditions and initial conditions for ambient temperature and heat source intensity, and run the simulation to obtain the temperature distribution and heat flow path of each component of the tablet computer; Collect historical usage data under different application scenarios, the usage data including usage time, power consumption and temperature; Correlate historical usage data with simulation results from a three-dimensional heat conduction model to analyze heat source distribution and temperature changes in different application scenarios; Extracting key heat source features, wherein the key heat source features include heat source location, intensity, and duration; Based on the extracted heat source features, a dynamic heat source fingerprint map is generated using visualization tools to intuitively display the heat source distribution and changes in different application scenarios; Based on actual needs, the quantitative indicators are set as the average values ​​of the temperature rise and the heat flux density change; Quantitative indicators are used to calculate the contribution of each application scenario to each region.

3. The method for visualizing dynamic control of a tablet computer based on heat dissipation balance according to claim 2 is characterized in that: The two-layer network architecture is constructed, the perception layer network analyzes the temperature gradient, application load and ambient temperature and humidity in real time, and the decision layer network outputs a dynamic scheduling strategy, which specifically includes: The perception layer network is responsible for data collection and preliminary processing. It collects temperature gradient, ambient temperature and humidity, and application load data in real time through various sensors and actuators. Distributed fiber optic temperature sensors are embedded inside the tablet computer to achieve real-time reconstruction of sub-millimeter temperature fields; By deploying humidity sensors, the ambient humidity of the tablet computer can be monitored in real time; Deploy load monitoring sensors based on application requirements to obtain application load conditions in real time; Establish a stable data transmission channel to transmit the collected data to the data processing center; Calculate the temperature gradient, ambient temperature and humidity, and changes in application load in real time, and store the analysis results in the database for use by the decision-making network; The decision-making network uses machine learning algorithms and models based on the data provided by the perception layer network to output dynamic scheduling strategies; The decision-making layer network obtains real-time data and analysis results from the perception layer network; Use historical data to train and validate machine learning models, and generate dynamic scheduling strategies based on real-time data and model prediction results; Allocate different levels of resources to each task based on its priority and urgency; When a task with a higher priority than the preset priority arrives, the resources of tasks with a lower priority than the preset priority will be preempted for the execution of the high priority task; Based on the feedback from each node, task allocation and resource allocation are performed to dynamically adjust the application performance and resource allocation.

4. The method for visualizing dynamic control of a tablet computer based on heat dissipation balance according to claim 3 is characterized in that: The deployment of phase change materials at the heat nodes, the realization of on-demand heat storage and release through electro-induced phase change technology, and the optimization of triggering timing and intensity in combination with reinforcement learning decision-making specifically include: Determine whether the temperature range of the hot node exceeds the preset temperature threshold. If so, select the molten salt phase change material for heat storage and heat release; if not, select the organic phase change material for heat storage and heat release; An electric heating element is integrated in the hot node, and the phase change material is heated by electric current to realize its phase change process; Design control systems to monitor the temperature of hot nodes, the phase state of phase change materials, and the working status of electric heating elements; When the thermal node needs to store heat, the control system starts the electric heating element, which heats the phase change material through electric current, causing it to change from solid to liquid and absorb heat; When the hot node needs to release heat, the control system stops the heating of the electric heating element, and the phase change material gradually changes from liquid to solid under the influence of the ambient temperature, releasing heat; The goal of reinforcement learning is to optimize the heat storage and release process of phase change materials and improve the energy efficiency of thermal nodes; The environment is defined as the heat node and its surrounding heat exchange system, the agent is the control system, the state is the temperature of the heat node and the phase state of the phase change material, the action is to start or stop the heating of the electric heating element, and the reward is the degree of energy efficiency improvement of the heat node; Collect data on the temperature of the hot node, the phase change of the phase change material and the working status of the electric heating element; Use the collected data to train a reinforcement learning model, and based on the trained reinforcement learning model, give the real-time status and demand of the heat node, and make intelligent decisions on the timing and intensity of starting or stopping the heating of the electric heating element; Through continuous iteration and optimization, the reinforcement learning model adapts to changes in thermal nodes and improves the efficiency of heat storage and release.

5. The method for visual dynamic control of a tablet computer based on heat dissipation balance according to claim 4 is characterized in that: The use of the front camera to realize the augmented reality technology projection of the thermal field on the surface of the device, displaying the temperature distribution through color gradient, and supporting gesture interaction to view the real-time temperature and heat source contribution of each point specifically includes: The front camera is used to capture real-time images of the device surface, while the thermal imaging sensor measures the temperature distribution on the device surface and generates thermal imaging data; Fusion of images captured by the front camera with thermal imaging data to generate augmented reality images; Based on thermal imaging data, color gradient technology is used to display the temperature distribution on the device surface, with red representing high temperature and blue representing low temperature; Using a gesture recognition module to recognize a user's gesture input, and based on the recognized gesture, sending a corresponding operation instruction to the augmented reality application, the gesture includes clicking, sliding, and zooming; The augmented reality application displays the real-time temperature and heat source contribution of the point selected by the user according to the instructions.

6. The method for visual dynamic control of a tablet computer based on heat dissipation balance according to claim 5 is characterized in that: The energy consumption-performance-heat dissipation ternary decision tree is constructed, combined with multi-objective optimization theory and hierarchical analysis method, to realize intelligent decision support, and provide dynamic optimization suggestions in the augmented reality technology interface, specifically including: Collect energy consumption, performance and thermal data for each device, configuration and usage scenario; Extract device power, processing speed, and heat dissipation efficiency from the data and output them as energy consumption, performance, and heat dissipation related features respectively; The objective function is set as a weighted quantitative indicator of energy consumption, performance, and heat dissipation, and the constraints are set as the physical limitations of the device and the requirements of the usage scenario; Energy consumption, performance, and heat dissipation are used as decision-making goals, device power, processing speed, and heat dissipation efficiency are used as the criterion layer, and specific devices and configurations are used as the solution layer; The importance of each element in the same level with respect to each criterion in the previous level is compared pairwise and output as a judgment matrix; Add up each row of the judgment matrix and divide it by the total number of factors to calculate the weight of each factor; Based on the comparison results of weights and solution layers, the dynamic optimization suggestions are comprehensively ranked.

Images