Thermal management and adaptive dimming method and apparatus for LED driving circuit

Abstract

This application relates to a method, apparatus, computer device, and storage medium for thermal management and adaptive dimming based on an LED driver circuit. The method includes: acquiring ambient light intensity information, user activity information, and temperature distribution information of the LED driver circuit; obtaining dynamic environmental data of the LED driver circuit based on the ambient light intensity information and user activity information; obtaining thermal management data of the LED driver circuit based on the temperature distribution information; processing the thermal management data using a thermal management mechanism optimized based on a preset heat dissipation layer and microfluidic cooling structure to generate thermal management instructions; processing the dynamic environmental data using an adaptive dimming mechanism optimized based on a deep learning algorithm to generate adaptive dimming instructions; executing thermal management operations based on the thermal management instructions; and executing adaptive dimming operations based on the adaptive dimming instructions. This method can efficiently and adaptively implement thermal management and adaptive dimming functions based on the LED driver circuit.

Description

Technical Field

[0001] This application relates to the field of circuit control technology, and in particular to a thermal management and adaptive dimming method, apparatus, computer equipment, and storage medium based on LED driver circuits. Background Technology

[0002] With the widespread application of LED lighting technology, LED driver circuits play a key role in various lighting equipment. They not only need to ensure stable thermal management to ensure the normal operation of LEDs, but also need to realize dimming function to adapt to different lighting needs.

[0003] However, on the one hand, existing thermal management functions usually adopt passive heat dissipation methods, which are difficult to effectively deal with the excessive heat generated by LED driver circuits when operating under high load. They also lack real-time monitoring and dynamic adjustment capabilities, and cannot accurately manage according to environmental changes and actual heat generation, resulting in unsatisfactory heat dissipation and thus affecting the overall system performance.

[0004] On the other hand, existing dimming control functions mostly use fixed dimming curves or simple feedback mechanisms, lacking comprehensive consideration of ambient light intensity and user activities. In dynamic environments, it is difficult to achieve the best lighting effect, which may lead to increased energy consumption or poor user experience. Summary of the Invention

[0005] Therefore, it is necessary to provide a thermal management and adaptive dimming method, apparatus, computer device, and computer-readable storage medium based on LED driver circuits to address the above-mentioned technical problems, so as to efficiently and adaptively realize thermal management and adaptive dimming functions based on LED driver circuits.

[0006] In a first aspect, this application provides a thermal management and adaptive dimming method based on an LED driver circuit, including:

[0007] Acquire ambient light intensity information, user activity information, and temperature distribution information of the LED driver circuit; obtain dynamic environmental data of the LED driver circuit based on the ambient light intensity information and the user activity information; and obtain thermal management data of the LED driver circuit based on the temperature distribution information.

[0008] The thermal management data is processed by the thermal management mechanism of the LED driver circuit optimized based on the preset heat dissipation layer and microfluidic cooling structure to generate the thermal management command of the LED driver circuit.

[0009] The dynamic environmental data is processed by the adaptive dimming mechanism of the LED driver circuit optimized by deep learning algorithm to generate the adaptive dimming command of the LED driver circuit.

[0010] Based on the thermal management command, the thermal management operation corresponding to the LED driving circuit is executed; based on the adaptive dimming command, the adaptive dimming operation corresponding to the LED driving circuit is executed.

[0011] Secondly, this application also provides a thermal management and adaptive dimming device based on an LED driver circuit, comprising:

[0012] The acquisition module is used to acquire ambient light intensity information, user activity information, and temperature distribution information of the LED driver circuit. Based on the ambient light intensity information and the user activity information, it obtains the dynamic environmental data of the LED driver circuit and the thermal management data of the LED driver circuit based on the temperature distribution information.

[0013] The first generation module is used to process the thermal management data through the thermal management mechanism of the LED driver circuit optimized based on the preset heat dissipation layer and microfluidic cooling technology, and generate the thermal management instructions of the LED driver circuit.

[0014] The second generation module is used to process the dynamic environment data through the adaptive dimming mechanism of the LED driver circuit optimized by the deep learning algorithm, and generate the adaptive dimming command of the LED driver circuit.

[0015] The execution module is used to execute the thermal management operation corresponding to the LED driving circuit based on the thermal management instruction, and to execute the adaptive dimming operation corresponding to the LED driving circuit based on the adaptive dimming instruction.

[0016] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the above steps.

[0017] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the above steps.

[0018] The aforementioned method, apparatus, computer device, and computer-readable storage medium for thermal management and adaptive dimming based on LED driver circuits, on the one hand, acquire dynamic environmental data obtained from ambient light intensity information and user activity information, and process the dynamic environmental data in a thermal management mechanism optimized based on a preset heat dissipation layer and microfluidic cooling structure to obtain thermal management instructions and corresponding thermal management operations; on the other hand, acquire thermal management data obtained from temperature distribution information, and process the thermal management data in an adaptive dimming mechanism optimized based on a deep learning algorithm to obtain adaptive dimming instructions and corresponding adaptive dimming operations. Based on this, thermal management operations and adaptive dimming operations based on LED driver circuits are implemented efficiently and adaptively, thereby ensuring efficient heat dissipation performance and environmentally adaptable light output based on LED driver circuits. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating a thermal management and adaptive dimming method based on an LED driver circuit in one embodiment.

[0021] Figure 2 This is a structural block diagram of a thermal management and adaptive dimming device based on an LED driver circuit in one embodiment. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0023] In one embodiment, such as Figure 1 As shown, a thermal management and adaptive dimming method based on an LED driver circuit is provided. This embodiment illustrates the method by applying it to a server. It is understood that this method can also be applied to a terminal, or to a system including both a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps S101 to S104.

[0024] Step S101: Obtain ambient light intensity information, user activity information, and temperature distribution information of the LED driver circuit. Obtain dynamic environmental data of the LED driver circuit based on the ambient light intensity information and user activity information, and obtain thermal management data of the LED driver circuit based on the temperature distribution information.

[0025] Among them, the LED driver circuit refers to the circuit system used to control and regulate the working state of the LED.

[0026] Among them, ambient light intensity information represents the light intensity data of the environment in which the LED driver circuit is located. It can be obtained through a light sensor and reflects the current light environment status of the space.

[0027] User activity information refers to data reflecting a user's activity status based on user behavior, location, usage habits, or device interaction patterns, such as whether the user has entered a scene and the frequency of activity. This information can be obtained through sensors or related data collection devices.

[0028] Among them, the temperature distribution information of the LED driver circuit represents the temperature data of various parts of the LED driver circuit during operation. It can be obtained in real time through temperature sensors (such as thermocouples or infrared sensors) and is used to describe the heat dissipation and heat distribution characteristics of the circuit.

[0029] Among them, dynamic environmental data refers to reference data calculated based on ambient light intensity information and user activity information, which is used to guide the dimming behavior of LED driver circuits based on the current physical environment.

[0030] Among them, thermal management data represents reference data calculated based on the temperature distribution information of the LED driver circuit, which is used to guide the heat dissipation behavior of the LED driver circuit based on the current temperature conditions.

[0031] For example, multiple sensors are used, such as an ambient light sensor to collect ambient light intensity information, an activity detection sensor to collect user activity information, and a temperature sensor to collect temperature distribution information of the LED driver circuit. Specifically, the ambient light sensor detects the external light level and converts it into numerical ambient light intensity information; activity detection sensors such as infrared sensors and pressure sensors acquire user activity information, including behavioral data such as whether the user is approaching the light area, the intensity of their activity, and the frequency of their activity; and temperature sensors such as temperature probes placed at key parts of the circuit acquire the heat distribution characteristics of the LED driver circuit during operation.

[0032] For example, on the one hand, ambient light intensity information and user activity information are fused together to calculate dynamic environmental data. Dynamic environmental data can reflect characteristics such as illumination and user behavior, enabling the system to provide adaptive light source output under different illumination and user behavior scenarios. On the other hand, thermal management data reflecting the heat dissipation requirements of the circuit is generated based on temperature distribution information. This includes information such as the highest temperature area of ​​the circuit, the average temperature rise trend, and the heat dissipation power requirement, which can provide an optimization basis for subsequent heat dissipation management.

[0033] Step S102: The thermal management data is processed by the thermal management mechanism of the LED driver circuit optimized based on the preset heat dissipation layer and microfluidic cooling structure to generate thermal management instructions for the LED driver circuit.

[0034] The heat dissipation layer refers to a structure composed of functional heat dissipation components such as thermally conductive materials and phase change materials. It is precisely arranged in high-heat-density areas of the circuit to quickly absorb and conduct heat, thereby reducing the impact of heat on circuit performance.

[0035] Among them, the microfluidic cooling structure refers to the cooling channel built based on microfluidic cooling technology. By adjusting the flow rate and direction of the liquid in the cooling channel, the cooling effect of the high-temperature area of ​​the circuit can be precisely controlled and optimized to ensure temperature balance.

[0036] The thermal management mechanism refers to an optimization method that combines a pre-designed heat dissipation layer with microfluidic cooling technology to implement heat dissipation effects based on thermal management data.

[0037] Among them, thermal management instructions are operation instructions generated based on parameters provided by thermal management data, used to dynamically maintain the thermal balance of the circuit and prevent the risk of overheating.

[0038] For example, in the preset heat dissipation layer design, functional heat dissipation elements such as thermally conductive materials or phase change materials are precisely arranged in the high heat density area of ​​the LED driver circuit. When the thermal management data indicates that certain specific areas have reached excessive heat load, the heat dissipation layer immediately takes effect, directionally and rapidly absorbing and conducting heat. At the same time, combined with microfluidic cooling technology, the liquid flow rate and direction of the microfluidic cooling channel are controlled by the thermal management data, thereby precisely adjusting the cooling effect of the high temperature area.

[0039] For example, in this process, thermal management data is processed into a set of thermal management instructions, such as changing the operating frequency of the coolant pump or adjusting the configuration parameters of the heat dissipation layer, in order to maintain the thermal balance of the LED driver circuit.

[0040] Step S103: The dynamic environment data is processed by the adaptive dimming mechanism of the LED driver circuit optimized by the deep learning algorithm to generate the adaptive dimming command of the LED driver circuit.

[0041] Among them, deep learning algorithms refer to pre-trained deep learning models optimized based on convolutional neural networks (CNNs).

[0042] Among them, the adaptive dimming mechanism refers to an optimization method based on deep learning algorithms to adjust the brightness output according to dynamic environmental data, so as to ensure real-time and adaptive dimming effect based on the current ambient light intensity and user activity.

[0043] Among them, the adaptive dimming command refers to the operation command generated based on the parameters provided by the dynamic environment data, which is used to achieve adaptive dimming effect according to the current environment scene.

[0044] For example, dynamic environmental data is passed to an adaptive dimming mechanism, which uses a pre-trained deep learning model to analyze the optimal light output strategy suitable for the current user behavior and environmental conditions. The deep learning model uses a large amount of historical ambient light intensity information and user activity information as training samples. After optimization by a convolutional neural network, it can predict and generate output instructions corresponding to light intensity, color temperature, and other data that match the current environment.

[0045] For example, when the ambient light intensity is low in the dynamic environment data, the LED brightness is appropriately increased through an adaptive dimming mechanism to improve the brightness of the environment; when the user activity is frequent in the dynamic environment data, the LED brightness is appropriately increased through an adaptive dimming mechanism to enhance the scene response effect.

[0046] Step S104: Based on the thermal management instruction, execute the thermal management operation corresponding to the LED driver circuit; based on the adaptive dimming instruction, execute the adaptive dimming operation corresponding to the LED driver circuit.

[0047] Thermal management operation refers to an operation that optimizes the heat dissipation of the LED driver circuit to ensure that the LED driver circuit operates within a safe temperature range.

[0048] Adaptive dimming refers to an operation that dynamically adjusts LED performance parameters based on ambient light intensity and user activity to provide an adaptive lighting environment.

[0049] For example, in response to thermal management commands, the thermal balance of the LED driver circuit and related circuits is adjusted by controlling the working state of the heat dissipation layer and the microfluidic cooling structure, thereby realizing thermal management operation based on the LED driver circuit. For example, the circuit can be made to operate stably by adjusting the coolant flow rate or adjusting the heat conduction efficiency of the heat sink.

[0050] For example, for adaptive dimming commands, by controlling the performance parameters of LEDs such as brightness and color temperature, adaptive dimming operation based on LED driver circuit is realized, so that the light output meets the current user needs and environmental requirements.

[0051] In the aforementioned thermal management and adaptive dimming method based on LED driver circuits, on the one hand, dynamic environmental data obtained from ambient light intensity information and user activity information is acquired. This dynamic environmental data is then processed within a thermal management mechanism optimized based on a preset heat dissipation layer and microfluidic cooling structure to obtain thermal management commands and corresponding thermal management operations. On the other hand, thermal management data obtained from temperature distribution information is acquired. This thermal management data is then processed within an adaptive dimming mechanism optimized based on a deep learning algorithm to obtain adaptive dimming commands and corresponding adaptive dimming operations. Based on this, thermal management operations and adaptive dimming operations based on LED driver circuits are efficiently and adaptively implemented, thereby ensuring efficient heat dissipation performance and environmentally adaptable light output based on LED driver circuits.

[0052] In an exemplary embodiment, dynamic environmental data of the LED driver circuit is obtained based on ambient light intensity information and user activity information, including steps S201 to S203.

[0053] Step S201: Perform feature extraction processing on the illumination features of the ambient light intensity information to obtain the ambient light intensity feature information corresponding to the ambient light intensity information.

[0054] Among them, the illumination characteristics of ambient light intensity information are the characteristic representation of multi-dimensional attributes such as the intensity, spectral distribution, and fluctuation of ambient light; the ambient light illumination characteristic information represents the comprehensive information generated by collecting the illumination characteristics of ambient light intensity information, processing and analyzing them.

[0055] For example, feature extraction can be achieved based on signal processing and machine learning mechanisms. For instance, the frequency distribution features of light intensity can be extracted by Fast Fourier Transform (FFT), and the feature components in the spectral distribution can be extracted by Principal Component Analysis (PCA) for dimensionality reduction. The final output of this process is a comprehensive representation of ambient light feature information, including light intensity, dynamic change trend, and spectral features.

[0056] For example, in the process of feature extraction and parsing, in order to construct more comprehensive ambient light feature information, it is necessary to consider the temporal dynamic attributes of ambient light intensity information, that is, the fluctuation pattern of ambient light at different points in time, such as the gradual change of sunlight, sudden shading, etc. The trend features of light intensity change can be extracted through time series analysis. Furthermore, ambient light intensity information can also be converted into data corresponding to specific scene types through classification models, such as data corresponding to scene types such as "strong light", "weak light" or "night light" and labeled accordingly.

[0057] Step S202: Based on the parsing and processing of user behavior features of user activity information, user activity behavior feature information corresponding to user activity information is obtained.

[0058] Among them, user activity information, user behavior features, is a feature representation of multi-dimensional attributes such as user behavior, location, usage habits, or device interaction patterns; user activity behavior feature information represents comprehensive information generated by collecting user activity information, processing and analyzing the user behavior features.

[0059] For example, feature extraction can be achieved based on machine learning models. For instance, by analyzing trajectory changes (such as height changes) in user activity information through machine learning models, behavioral features such as "sitting down" or "standing up" can be identified. Visual data features can be extracted through convolutional neural networks, and time series behavioral data trends can be analyzed through long short-term memory networks. The user activity feature information ultimately extracted by this process is a comprehensive representation of the dynamics and patterns of user behavior.

[0060] For example, in order to quickly identify obvious user behaviors and handle complex behaviors, the feature extraction method can be optimized based on different application scenarios. For instance, in smart homes, real-time processing capabilities should be prioritized, while in health monitoring scenarios, the ability to identify behavioral details needs to be enhanced. Furthermore, there is a challenge in coordinating the joint expression of user activity behavior feature information in multimodal features based on different sensor data sources.

[0061] Step S203: Based on the ambient light characteristic information and user activity behavior characteristic information, construct the dynamic environment corresponding to the LED driving circuit to obtain the dynamic environment data corresponding to the dynamic environment.

[0062] Among them, the dynamic environment representation corresponding to the LED driving circuit is an environmental scene representation model constructed by fusing ambient lighting features and user behavior features, in order to learn and represent the joint feature distribution of ambient light and user behavior.

[0063] For example, by combining ambient lighting feature information with user activity behavior feature information, a dynamic environment corresponding to the current LED driving circuit is constructed, forming a unified environmental scene representation model. In this process, the ambient lighting feature information and user activity behavior feature information need to be standardized to ensure that their numerical range and data structure are comparable and coupled. For example, normalization processing can be used to transform feature data of different dimensions into data of the same range, or a specific encoding method can be used to fuse discrete and continuous state data in the same data space.

[0064] In this embodiment, ambient light feature information is obtained by extracting and processing the light features of ambient light intensity information, and user activity behavior feature information is obtained by parsing and processing the user behavior features of user activity information. Thus, at the feature information level, the dynamic environment corresponding to the LED driving circuit is constructed in a multi-dimensional and accurate manner, thereby efficiently obtaining the corresponding dynamic data.

[0065] In an exemplary embodiment, obtaining the thermal management data of the LED driving circuit based on the temperature distribution information includes steps S301 to S303.

[0066] Step S301: Based on the thermal region distribution analysis of the temperature distribution information, the temperature gradient corresponding to each thermal region and the heat conduction path information corresponding to each thermal region are obtained.

[0067] Among them, the hot zone refers to the logical or physical division of the circuit based on factors such as temperature change trend and thermal conduction characteristics, so as to divide it into several unit regions, and each hot zone has relatively consistent thermal characteristics.

[0068] The temperature gradient represents the direction and magnitude of temperature changes within or between thermal regions, and is used to reflect the potential heat conduction trend within the thermal region.

[0069] Among them, heat conduction path information describes the physical path and characteristics of heat transfer within a hot region or between adjacent hot regions, including conduction direction, path length, and path material properties (such as thermal conductivity and contact area).

[0070] For example, temperature distribution information can be input into a thermal field analysis tool. Combined with the circuit's structural layout, material properties, and boundary conditions (such as heat source power distribution, heat sink location, boundary temperature, etc.), a numerical segmentation algorithm (such as a clustering algorithm) can be used to divide the temperature distribution into regions, forming distinct thermal regions based on the analysis results. Furthermore, for the temperature changes within each thermal region or between adjacent regions, the temperature gradient of each thermal region can be calculated using a temperature gradient algorithm. Moreover, based on the temperature gradient of each thermal region, the heat transfer direction within each thermal region can be further calculated, thereby evaluating the heat conduction path information corresponding to each thermal region.

[0071] Step S302: Based on the temperature gradient and heat conduction path information corresponding to each hot region, perform dynamic thermal resistance analysis on the nodes and heat conduction paths of each hot region in the LED driving circuit to obtain the dynamic thermal resistance matrix of the nodes corresponding to each hot region and the heat flux density value between the nodes.

[0072] The node where the hot area is located in the LED driver circuit can represent a specific electronic component of the LED driver circuit or a connection node between electronic components, or it can represent a key point of heat distribution determined based on the temperature-sensitive part.

[0073] The dynamic thermal resistance matrix represents the thermal resistance characteristics generated in matrix form for different nodes based on dynamic thermal resistance analysis. The matrix elements represent the dynamic thermal resistance values ​​between a node and its neighboring nodes. Dynamic thermal resistance analysis combines the dynamic temperature and heat flow changes of electronic components in their working state to calculate the trend of thermal resistance changes with time or heat load, so as to dynamically reflect the thermal conduction characteristics of the circuit.

[0074] Among them, the heat flux density value represents the specific amount of heat passing through a unit area per unit time, which reflects the intensity of heat flow transfer between nodes.

[0075] For example, based on the temperature gradient and heat conduction path information corresponding to each thermal region, a dynamic thermal model (such as a Cauer network or Foster model) is used to simulate the dynamic thermal behavior between the nodes of each thermal region. The dynamic thermal resistance matrix between the nodes is generated through the above dynamic thermal model. The off-diagonal elements in the matrix represent the mutual thermal resistance characteristics between two nodes, and the main diagonal elements represent the self-thermal resistance characteristics between each node and the surrounding environment. Furthermore, the heat flux density between the nodes is calculated based on the node temperature difference, thermal conductivity, and heat transfer area between the nodes.

[0076] Step S303: Based on the dynamic thermal resistance matrix and the heat flux density values ​​between nodes, the thermal distribution characteristics of the LED driver circuit are comprehensively optimized and analyzed to obtain the thermal management data of the LED driver circuit.

[0077] For example, firstly, by combining the dynamic thermal resistance matrix, the path with low heat transfer efficiency in the LED driver circuit is identified, and the heat dissipation bottleneck is located by analyzing the heat flux density distribution of each hot region, thereby realizing the analysis of the thermal distribution characteristics of the LED driver circuit; secondly, by using thermal field simulation tools, and taking into account the actual circuit layout and material properties, the temperature distribution and heat flux change trends of different nodes are simulated and adjusted to optimize the thermal distribution characteristics of the LED driver circuit, thereby obtaining the thermal management data of the LED driver circuit.

[0078] In this embodiment, by determining the temperature gradient and heat conduction path information corresponding to each hot region, the dynamic thermal resistance matrix of the node corresponding to each hot region and the heat flux density value between the nodes are obtained, thereby obtaining the thermal management data of the LED driver circuit. Based on this, through precise analysis of temperature distribution and comprehensive evaluation of dynamic thermal resistance characteristics, the thermal management behavior of the LED driver circuit is efficiently and accurately guided.

[0079] In an exemplary embodiment, thermal management data is processed by a thermal management mechanism of the LED driver circuit optimized based on a preset heat dissipation layer and a microfluidic cooling structure to generate thermal management instructions for the LED driver circuit, including steps S401 to S403.

[0080] Step S401: Based on the analysis and processing of the thermal distribution characteristic parameters of the heat dissipation layer combining graphene and nanocomposite materials, a dynamic heat conduction model corresponding to the heat dissipation layer is obtained.

[0081] Among them, the heat dissipation layer, which is based on the combination of graphene and nanocomposite materials, has excellent thermal conductivity and uniform heat distribution.

[0082] Among them, the thermal distribution characteristic parameters represent data describing the thermal conductivity, heat capacity, and heat flux density distribution of the heat dissipation layer, as well as other material structure thermal conductivity performance.

[0083] Among them, the dynamic heat conduction model represents the description of the heat transfer law and temperature distribution characteristics of the heat dissipation layer under dynamic working conditions by combining heat distribution characteristic parameters through mathematical modeling.

[0084] For example, firstly, high-precision measurement techniques, such as laser thermal reflection and infrared thermal imaging, are applied to experimentally measure the thermal distribution characteristic parameters of the heat dissipation layer material, such as thermal conductivity, specific heat capacity, and thermal diffusivity, within the actual operating temperature range, to obtain a detailed dataset. Secondly, based on the obtained thermal distribution characteristic parameters, a dynamic heat conduction model corresponding to the heat dissipation layer is constructed by establishing a mathematical model based on the Fourier heat conduction equation. This model can accurately describe the temperature distribution and heat diffusion behavior of the heat dissipation layer under continuous and periodic heat source input.

[0085] Step S402: Based on the analysis and processing of the fluid characteristic parameters of the microfluidic cooling structure, a dynamic flow distribution model corresponding to the microfluidic cooling structure is obtained.

[0086] Among them, fluid characteristic parameters represent data describing the cooling fluid performance, such as fluid velocity, pressure, temperature, and geometric parameters of the flow path of the microfluidic cooling structure.

[0087] Among them, the dynamic flow distribution model represents the mathematical modeling of microfluidic cooling structures by combining microfluidic characteristic parameters, in order to simulate the flow law of fluid in microstructure channels and the process of heat transfer and diffusion.

[0088] For example, fluid dynamics methods are used to model and simulate the fluid motion characteristics and heat transfer laws in microfluidic cooling structures. Specifically, computational fluid dynamics (CFD) simulation software can be used to simulate the flow path and distribution characteristics of the coolant in the channels by inputting parameters such as the viscosity, density, specific heat capacity of the coolant, as well as the channel shape and fluid velocity of the microfluidic cooling structure. This allows the construction of a dynamic flow distribution model corresponding to the microfluidic cooling structure, which is used to describe the flow diffusion law of the coolant in the microchannel and the dynamic characteristics of heat exchange.

[0089] Step S403: Based on the coupling characteristic analysis of the dynamic heat conduction model and the dynamic flow distribution model, the thermal management mechanism of the LED driver circuit is determined. Based on the thermal management mechanism, the thermal management data is simulated and processed to generate the thermal management command of the LED driver circuit.

[0090] For example, when performing coupled characteristic analysis on the dynamic heat conduction model and the dynamic flow distribution model, firstly, it is necessary to unify the boundary conditions of the two. For instance, based on the heat flux density and temperature gradient variation law at the interface between the heat dissipation layer and the microfluidic cooling structure, it is necessary to ensure that the boundary conditions of the model are consistent. Secondly, through numerical calculation methods, the heat distribution characteristic parameters of the heat dissipation layer in the dynamic heat conduction model and the fluid characteristic parameters in the dynamic flow distribution model are jointly solved to determine the heat transfer path on the material surface and the transmission law in the microchannel, as well as the overall efficiency of heat transfer from the heat dissipation layer to the microfluidic, and the influence of the dynamic changes of the circuit operating parameters on the coupling characteristics of the two, thereby establishing the thermal management mechanism corresponding to the LED driver circuit.

[0091] Furthermore, based on the established thermal management mechanism, virtual simulation technology is used to perform qualitative and quantitative predictions of thermal management data under different working environments and dynamic thermal load conditions, and to generate optimization decision instructions that meet the requirements.

[0092] In this embodiment, a dynamic heat conduction model is obtained by analyzing and processing the thermal distribution characteristic parameters of the heat dissipation layer combining graphene and nanocomposite materials, and a dynamic flow distribution model is obtained by analyzing and processing the fluid characteristic parameters of the microfluidic cooling structure. Based on the coupled analysis of the two, the thermal management mechanism of the LED driving circuit is accurately determined, significantly improving the heat dissipation efficiency.

[0093] In an exemplary embodiment, dynamic environmental data is processed by an adaptive dimming mechanism of the LED driver circuit optimized by a deep learning algorithm to generate an adaptive dimming command for the LED driver circuit, including steps S501 to S503.

[0094] Step S501: Multimodal feature extraction is performed on the dynamic environment data using a multimodal feature extraction neural network constructed based on deep learning to obtain the environmental perception feature vector corresponding to the dynamic environment data.

[0095] Among them, the multimodal feature extraction neural network represents a deep learning model that is used to extract abstract features under the combined effect of different types of data, and obtain a high-dimensional feature representation that can express complex environmental changes.

[0096] Among them, the environmental perception feature vector represents a high-dimensional feature vector generated by processing dynamic environmental data through a multimodal feature extraction neural network, which is used to describe the characteristics of the current environment.

[0097] For example, in order to address the need for fusion of different modal environmental data (such as light intensity data, user activity data, and time series features), it is necessary to design a deep learning network model that can support multiple input types. For instance, a hybrid structure combining convolutional neural networks and recurrent neural networks can be used. The convolutional neural network is used to capture the spatial characteristics of light intensity distribution, while the recurrent neural network is used to capture the dynamic trends over time. After being processed by the deep learning network model, the dynamic environmental data is projected into a unified feature space to generate multimodal environmental perception feature vectors.

[0098] Step S502: Combining the environmental perception feature vector and the power characteristics of the LED driving circuit, the power distribution parameters of the LED driving circuit are determined based on the DC-DC converter constructed with gallium nitride structure.

[0099] Among them, the electrical characteristics of the LED driver circuit represent the key parameters of the electrical output of the LED driver circuit, such as voltage, current and power.

[0100] Among them, the DC-DC converter constructed with gallium nitride structure represents a high-efficiency power regulation device that utilizes the high frequency and high efficiency characteristics of gallium nitride (GaN) material to accurately distribute electrical energy and meet complex dimming requirements.

[0101] Among them, the power distribution parameters represent key indicators used to adjust the output of the LED driver circuit, such as the current-voltage distribution ratio and power settings.

[0102] For example, due to the superior high-frequency and high-efficiency characteristics of gallium nitride materials compared to traditional semiconductors, its DC-DC converter allows for rapid and precise power configuration of LED driver circuits. Specifically, by analyzing the dynamic change information reflected in the environmental perception feature vector (such as the current required light intensity and color temperature), and analyzing the current voltage, current characteristics, and power limitations of the LED driver circuit, and then combining the DC-DC converter constructed with the gallium nitride structure, the power allocation parameters of the LED driver circuit that can meet the target lighting requirements are obtained by using optimization algorithms (such as genetic algorithms or particle swarm optimization algorithms).

[0103] Step S503: Based on the dynamic relationship between the power distribution parameters and the preset pulse width modulation algorithm, determine the adaptive dimming mechanism of the LED driver circuit, generate a pulse width modulation signal based on the adaptive dimming mechanism, and use the pulse width modulation signal as the adaptive dimming command of the LED driver circuit.

[0104] Among them, the pulse width modulation algorithm represents an algorithm for controlling the width of a pulse signal, which affects the brightness output of the LED light source by adjusting the signal duty cycle; the pulse width modulation signal represents a digital signal that controls the output power by adjusting the signal duty cycle (i.e., the ratio of the high-level duration to the total period time).

[0105] For example, the data mapping relationship between power allocation parameters and pulse width modulation signals generated based on a preset pulse width modulation algorithm is determined in advance. That is, it is determined which types of power allocation parameters (such as power supply voltage, current, load conditions, etc.) can be mapped to the duty cycle and frequency parameters of the pulse width modulation signal, thereby constructing a dynamic relationship between power allocation parameters and the preset pulse width modulation algorithm. Based on this, an adaptive dimming mechanism for LED driving circuit is obtained, which can obtain a pulse width modulation control mode suitable for the current power allocation parameters according to the current power allocation parameters, thereby determining the duty cycle and frequency parameters corresponding to the pulse width modulation signal to be generated.

[0106] In this embodiment, on the one hand, the multimodal feature extraction neural network and gallium nitride DC-DC converter, combined with dynamic environment perception and power optimization allocation, realize intelligent and adaptive light efficiency control of the LED driving circuit; on the other hand, the preset pulse width modulation algorithm makes LED dimming smoother and more precise.

[0107] In an exemplary embodiment, based on the thermal management instruction, the thermal management operation corresponding to the LED driving circuit is executed, including step S601; based on the adaptive dimming instruction, the adaptive dimming operation corresponding to the LED driving circuit is executed, including step S602.

[0108] Step S601: Based on the preset partitioned heat flow control strategy, the LED driving circuit is divided into several hot zones, the heat management instructions are parsed, and the heat management operations corresponding to each hot zone are obtained and executed.

[0109] Among them, the zoned heat flow control strategy means that a heat regulation scheme is pre-set for each heat zone according to the heat characteristics generated in different areas of the LED driver circuit, and the possibility of local overheating is reduced by means of fluid mechanics or heat conduction.

[0110] For example, in conjunction with a preset zoned heat flow control strategy, the LED driver circuit is divided into several thermal zones based on information such as the distribution of heat sources, heat conduction paths, and thermal conductivity characteristics of materials in the LED driver circuit; the thermal management command is parsed to obtain the parsing results such as the number, current temperature value, target temperature value, and temperature deviation corresponding to each thermal zone; and the thermal management operation corresponding to each thermal zone is generated based on the parsing results corresponding to each thermal zone.

[0111] Step S602: Based on the preset multi-level brightness scheduling strategy, the brightness performance of the LED driving circuit is divided into several brightness levels. The adaptive dimming command is parsed to obtain and execute the adaptive dimming operation corresponding to the target brightness level.

[0112] Among them, the multi-level brightness scheduling strategy means that the brightness requirements of LEDs during operation are divided into multiple brightness levels, and dynamic adjustments are made to meet the needs of energy saving and usage scenarios.

[0113] For example, by combining a preset multi-level brightness scheduling strategy, the brightness performance of the LED driver circuit is divided into several brightness levels based on information such as the current input range of the circuit and the luminous efficacy output characteristics of the LED itself. For example, several brightness levels are set from the lowest brightness to the highest brightness, and each brightness level corresponds to a specific input current value or pulse width modulation duty cycle to finely control the light intensity. The adaptive dimming command is parsed to obtain the parsing results such as the input current value or pulse width modulation duty cycle corresponding to the current light demand. Based on the parsing results, the target brightness level corresponding to the current light demand is determined, thereby generating the adaptive dimming operation corresponding to the target brightness level.

[0114] In this embodiment, on the one hand, based on the preset partitioned heat flow control strategy, the thermal management operation corresponding to each thermal zone is executed precisely; on the other hand, based on the preset multi-level brightness scheduling strategy, the adaptive dimming operation corresponding to each target brightness level is executed precisely.

[0115] In an exemplary embodiment, the method further includes steps S701 to S703.

[0116] Step S701: Based on a preset wireless communication protocol, receive control request information from a smart terminal device and perform demodulation processing to obtain demodulated data corresponding to the control request information.

[0117] Among them, wireless communication protocols represent a set of pre-defined communication rules and standards that define the data transmission method between smart terminal devices and IoT platforms, such as Bluetooth, Wi-Fi, or ZigBee protocols.

[0118] Among them, the control request information represents the specific control needs or operation instructions sent by the smart terminal device to the Internet of Things platform, such as personalized service needs for controlling the brightness, color, and dynamic effects of LED lights.

[0119] For example, based on a preset wireless communication protocol, a smart terminal device sends a control request information to an IoT platform via a wireless signal. This wireless signal can be a digitized frequency modulation signal or a data packet transmission signal. Based on a demodulation algorithm, the original wireless signal is converted into digitized demodulated data through demodulation processing of the control request information. In this process, the demodulation algorithm performs waveform demodulation, frequency identification, and data stream extraction according to preset communication protocol rules, thereby significantly reducing the bit error rate and ensuring the accuracy of signal parsing.

[0120] Step S702: Based on a preset data parsing algorithm, the demodulated data is parsed and its format is converted to obtain personalized control parameters compatible with the IoT platform.

[0121] Among them, the data parsing algorithm refers to a logical program used to analyze the data format and convert it into a target format to ensure that the data meets the requirements of the Internet of Things platform.

[0122] Among them, personalized control parameters refer to specific parameters extracted from the control request information of smart terminal devices. They can directly indicate the change mode of LEDs and control the brightness, color, dynamic effects, etc. of LED lights.

[0123] For example, during the parsing process, the data parsing algorithm reads important fields from the demodulated data according to specific rules, such as LED brightness values, color codes, and dynamic effect instructions, and eliminates unnecessary data. Furthermore, the parsed data is reformatted according to the IoT platform standard, for example, by recombining discrete data segments into a unified data packet format. Moreover, the formatted data is defined as personalized control parameters compatible with the IoT platform and stored in a standardized structure, such as JSON format.

[0124] Step S703: Generate LED control instructions corresponding to the smart terminal device based on the personalized control parameters, and transmit the LED control instructions to the LED driver circuit so that the LED driver circuit can perform remote personalized control operations based on the LED control instructions.

[0125] Among them, LED control commands represent commands generated based on personalized adjustment parameters, which can be used to guide LED driver circuits to complete specific control tasks.

[0126] For example, during the generation of LED control instructions, it is necessary to analyze the control content involved in the personalized control parameters and match the corresponding control template. For instance, if a personalized control parameter requires "setting the LED brightness to 80%", then it is necessary to calculate, based on the performance of the LED driver circuit, the actual output value required for physical control, such as the value of current or power, to convert "setting the LED brightness to 80%" into the value of physical control. Furthermore, the generated LED control instructions are transmitted to the LED driver circuit as independent instruction packages. After receiving and recognizing the LED control instructions, the LED driver circuit drives the corresponding control module to execute the remote control task.

[0127] In this embodiment, on the one hand, based on a unified wireless communication protocol and data parsing algorithm, the high adaptability of data transmission and parsing between the smart terminal and the Internet of Things platform is ensured; on the other hand, through the generated LED control commands, remote personalized control operations based on the LED driver circuit are realized, thereby improving the environmental adaptability of the LED driver circuit.

[0128] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0129] Based on the same inventive concept, this application also provides a thermal management and adaptive dimming device based on an LED driver circuit for implementing the aforementioned thermal management and adaptive dimming method based on an LED driver circuit. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the thermal management and adaptive dimming device based on an LED driver circuit provided below can be found in the limitations of the thermal management and adaptive dimming method based on an LED driver circuit described above, and will not be repeated here.

[0130] In one exemplary embodiment, such as Figure 2 As shown, a thermal management and adaptive dimming device based on an LED driver circuit is provided, comprising: an acquisition module 201, a first generation module 202, a second generation module 203, and an execution module 204, wherein:

[0131] The acquisition module 201 is used to acquire ambient light intensity information, user activity information and temperature distribution information of LED driver circuit, obtain dynamic environmental data of LED driver circuit based on ambient light intensity information and user activity information, and obtain thermal management data of LED driver circuit based on temperature distribution information.

[0132] The first generation module 202 is used to process thermal management data through the thermal management mechanism of the LED driver circuit optimized based on the preset heat dissipation layer and microfluidic cooling technology, and generate thermal management instructions for the LED driver circuit.

[0133] The second generation module 203 is used to process dynamic environmental data through the adaptive dimming mechanism of the LED driver circuit optimized by deep learning algorithm, and generate adaptive dimming instructions for the LED driver circuit.

[0134] The execution module 204 is used to execute the thermal management operation corresponding to the LED driver circuit based on the thermal management instruction, and to execute the adaptive dimming operation corresponding to the LED driver circuit based on the adaptive dimming instruction.

[0135] In an exemplary embodiment, the acquisition module 201 is further configured to: perform feature extraction processing on the illumination features of the ambient light intensity information to obtain ambient light intensity feature information corresponding to the ambient light intensity information; perform parsing processing on the user behavior features of the user activity information to obtain user activity behavior feature information corresponding to the user activity information; and construct the dynamic environment corresponding to the LED driving circuit based on the ambient light intensity feature information and the user activity behavior feature information to obtain dynamic environment data corresponding to the dynamic environment.

[0136] In an exemplary embodiment, the acquisition module 201 is further configured to: perform thermal region distribution analysis processing on the temperature distribution information to obtain the temperature gradient corresponding to each thermal region and the heat conduction path information corresponding to each thermal region; perform dynamic thermal resistance analysis processing on the nodes and heat conduction paths of each thermal region in the LED driver circuit based on the temperature gradient and heat conduction path information corresponding to each thermal region to obtain the dynamic thermal resistance matrix of the nodes corresponding to each thermal region and the heat flux density value between the nodes; and perform comprehensive optimization analysis processing on the thermal distribution characteristics of the LED driver circuit based on the dynamic thermal resistance matrix and the heat flux density value between the nodes to obtain the thermal management data of the LED driver circuit.

[0137] In an exemplary embodiment, the first generation module 202 is further configured to: analyze and process the thermal distribution characteristic parameters of the heat dissipation layer combining graphene and nanocomposite materials to obtain a dynamic heat conduction model corresponding to the heat dissipation layer; analyze and process the fluid characteristic parameters of the microfluidic cooling structure to obtain a dynamic flow distribution model corresponding to the microfluidic cooling structure; determine the thermal management mechanism of the LED driver circuit based on the coupling characteristic analysis of the dynamic heat conduction model and the dynamic flow distribution model; and perform simulation processing on the thermal management data based on the thermal management mechanism to generate thermal management instructions for the LED driver circuit.

[0138] In an exemplary embodiment, the second generation module 203 is further configured to: extract multimodal features from dynamic environment data using a multimodal feature extraction neural network constructed based on deep learning, and obtain an environment perception feature vector corresponding to the dynamic environment data; combine the environment perception feature vector and the power characteristics of the LED driving circuit, and determine the power allocation parameters of the LED driving circuit based on a DC-DC converter constructed based on a gallium nitride structure; determine the adaptive dimming mechanism of the LED driving circuit according to the dynamic relationship between the power allocation parameters and the preset pulse width modulation algorithm; generate a pulse width modulation signal based on the adaptive dimming mechanism; and use the pulse width modulation signal as the adaptive dimming command of the LED driving circuit.

[0139] In an exemplary embodiment, the execution module 204 is further configured to: divide the LED driving circuit into several hot zones based on a preset partitioned heat flow control strategy, parse the heat management instructions, obtain and execute the heat management operations corresponding to each hot zone; and divide the brightness performance of the LED driving circuit into several brightness levels based on a preset multi-level brightness scheduling strategy, parse the adaptive dimming instructions, obtain and execute the adaptive dimming operations corresponding to each target brightness level.

[0140] In one exemplary embodiment, the device further includes a remote control module, which is configured to: receive and demodulate control request information from a smart terminal device based on a preset wireless communication protocol to obtain demodulated data corresponding to the control request information; parse and convert the demodulated data according to a preset data parsing algorithm to obtain personalized control parameters compatible with the Internet of Things platform; generate LED control instructions corresponding to the smart terminal device based on the personalized control parameters, and transmit the LED control instructions to the LED driver circuit so that the LED driver circuit can perform remote personalized control operations based on the LED control instructions.

[0141] The modules in the aforementioned thermal management and adaptive dimming device based on LED driver circuits can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0142] In an exemplary embodiment, a computer device is provided, which may be a server. The computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is connected to the system bus via the I / O interfaces. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device stores data related to thermal management and adaptive dimming based on LED driver circuits. The I / O interfaces of the computer device are used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a thermal management and adaptive dimming method based on LED driver circuits.

[0143] In an exemplary embodiment, a computer device is provided, which may be a terminal. The computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a thermal management and adaptive dimming method based on an LED driving circuit. The display unit of the computer device is used to form a visually visible image and may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0144] Those skilled in the art will understand that the structure of the computer device described above is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. A specific computer device may include more or fewer components than those shown in the figure, or may combine certain components, or may have different component arrangements.

[0145] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of any of the above embodiments.

[0146] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above embodiments.

[0147] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0148] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0149] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A thermal management and adaptive dimming method based on an LED driver circuit, characterized in that, The method includes: Acquire ambient light intensity information, user activity information, and temperature distribution information of the LED driver circuit; obtain dynamic environmental data of the LED driver circuit based on the ambient light intensity information and the user activity information; and obtain thermal management data of the LED driver circuit based on the temperature distribution information. The thermal management data is processed by a thermal management mechanism for the LED driver circuit optimized based on a preset heat dissipation layer and a microfluidic cooling structure to generate thermal management instructions for the LED driver circuit. In the thermal management mechanism, the characteristic parameters related to the heat dissipation layer and the characteristic parameters related to the microfluidic cooling structure are jointly solved to determine the heat transfer path on the material surface and the transmission law in the microchannel, as well as the overall efficiency of heat transfer from the heat dissipation layer to the microfluidic cooling structure, and the influence of dynamic changes in circuit operating parameters on the coupling characteristics of the two. The dynamic environmental data is processed by an adaptive dimming mechanism for the LED driver circuit optimized by a deep learning algorithm to generate an adaptive dimming command for the LED driver circuit. In the adaptive dimming mechanism, a deep learning network model that supports multiple input types is pre-designed. The deep learning network model is a hybrid structure combining convolutional neural networks and recurrent neural networks. The convolutional neural network is used to capture the spatial light intensity distribution characteristics, and the recurrent neural network is used to capture the dynamic change trend over time. Based on the thermal management instruction, the thermal management operation corresponding to the LED driving circuit is executed; based on the adaptive dimming instruction, the adaptive dimming operation corresponding to the LED driving circuit is executed. The thermal management mechanism for the LED driver circuit, optimized based on a preset heat dissipation layer and microfluidic cooling structure, processes the thermal management data to generate thermal management instructions for the LED driver circuit, including: Based on the analysis and processing of the thermal distribution characteristic parameters of the heat dissipation layer combining graphene and nanocomposite materials, a dynamic heat conduction model corresponding to the heat dissipation layer is obtained; based on the analysis and processing of the fluid characteristic parameters of the microfluidic cooling structure, a dynamic flow distribution model corresponding to the microfluidic cooling structure is obtained; based on the coupling characteristic analysis of the dynamic heat conduction model and the dynamic flow distribution model, the thermal management mechanism of the LED driving circuit is determined; based on the thermal management mechanism, the thermal management data is simulated and processed to generate the thermal management command of the LED driving circuit. The process of processing the dynamic environment data using the adaptive dimming mechanism of the LED driver circuit optimized based on a deep learning algorithm to generate adaptive dimming instructions for the LED driver circuit includes: A multimodal feature extraction neural network based on deep learning is used to extract multimodal features from the dynamic environment data to obtain the environmental perception feature vector corresponding to the dynamic environment data. Combining the environmental perception feature vector and the power characteristics of the LED driving circuit, the power allocation parameters of the LED driving circuit are determined based on a DC-DC converter constructed with a gallium nitride structure. According to the dynamic relationship between the power allocation parameters and the preset pulse width modulation algorithm, the adaptive dimming mechanism of the LED driving circuit is determined. A pulse width modulation signal is generated based on the adaptive dimming mechanism, and the pulse width modulation signal is used as the adaptive dimming command of the LED driving circuit.

2. The method according to claim 1, characterized in that, The step of obtaining the dynamic environmental data of the LED driving circuit based on the ambient light intensity information and the user activity information includes: Based on the illumination features of the ambient light intensity information, feature extraction processing is performed to obtain the ambient light intensity feature information corresponding to the ambient light intensity information; By parsing and processing the user behavior features of the user activity information, user activity behavior feature information corresponding to the user activity information is obtained. Based on the ambient lighting characteristics and the user activity behavior characteristics, a dynamic environment corresponding to the LED driving circuit is constructed to obtain dynamic environment data corresponding to the dynamic environment.

3. The method according to claim 1, characterized in that, The step of obtaining the thermal management data of the LED driver circuit based on the temperature distribution information includes: Based on the thermal region distribution analysis of the temperature distribution information, the temperature gradient and heat conduction path information corresponding to each thermal region are obtained. Based on the temperature gradient and heat conduction path information corresponding to each hot region, dynamic thermal resistance analysis is performed on the nodes and heat conduction paths of each hot region in the LED driving circuit to obtain the dynamic thermal resistance matrix of the nodes corresponding to each hot region and the heat flux density value between the nodes. Based on the dynamic thermal resistance matrix and the heat flux density values ​​between nodes, the thermal distribution characteristics of the LED driver circuit are comprehensively optimized and analyzed to obtain the thermal management data of the LED driver circuit.

4. The method according to claim 1, characterized in that, The step of executing the thermal management operation corresponding to the LED driving circuit based on the thermal management command includes: Based on a preset zoned heat flow control strategy, the LED driving circuit is divided into several hot zones, the heat management instructions are parsed, and the heat management operations corresponding to each hot zone are obtained and executed. The step of executing the adaptive dimming operation corresponding to the LED driving circuit based on the adaptive dimming command includes: Based on a preset multi-level brightness scheduling strategy, the brightness performance of the LED driving circuit is divided into several brightness levels. The adaptive dimming command is parsed to obtain and execute the adaptive dimming operation corresponding to the target brightness level.

5. The method according to claim 1, characterized in that, The method further includes: Based on a preset wireless communication protocol, control request information from a smart terminal device is received and demodulated to obtain demodulated data corresponding to the control request information. Based on a preset data parsing algorithm, the demodulated data is parsed and its format is converted to obtain personalized control parameters compatible with the Internet of Things platform; The LED control command corresponding to the smart terminal device is generated according to the personalized adjustment parameters, and the LED control command is transmitted to the LED driver circuit so that the LED driver circuit can perform remote personalized control operation based on the LED control command.

6. A thermal management and adaptive dimming device based on an LED driver circuit, characterized in that, The device includes: The acquisition module is used to acquire ambient light intensity information, user activity information, and temperature distribution information of the LED driver circuit. Based on the ambient light intensity information and the user activity information, it obtains the dynamic environmental data of the LED driver circuit and the thermal management data of the LED driver circuit based on the temperature distribution information. The first generation module is used to process the thermal management data through a thermal management mechanism of the LED driving circuit optimized based on a preset heat dissipation layer and a microfluidic cooling structure, and generate thermal management instructions for the LED driving circuit. The first generation module is further used to: in the thermal management mechanism, jointly solve the characteristic parameters related to the heat dissipation layer and the characteristic parameters related to the microfluidic cooling structure to determine the heat transfer path on the material surface and the transmission law within the microchannel, the overall efficiency of heat transfer from the heat dissipation layer to the microfluidic cooling structure, and the impact of dynamic changes in circuit operating parameters on the coupling characteristics of the two. The second generation module is used to process the dynamic environment data through an adaptive dimming mechanism of the LED driver circuit optimized by a deep learning algorithm, and generate an adaptive dimming command for the LED driver circuit; wherein, the second generation module is further used to: in the adaptive dimming mechanism, pre-design a deep learning network model that supports multiple input types, wherein the deep learning network model is a hybrid structure combining convolutional neural networks and recurrent neural networks, wherein the convolutional neural network is used to capture the spatial light intensity distribution characteristics, and the recurrent neural network is used to capture the dynamic change trend over time; The execution module is used to execute the thermal management operation corresponding to the LED driving circuit based on the thermal management instruction, and to execute the adaptive dimming operation corresponding to the LED driving circuit based on the adaptive dimming instruction. The first generation module is further configured to: analyze and process the thermal distribution characteristic parameters of the heat dissipation layer combining graphene and nanocomposite materials to obtain a dynamic heat conduction model corresponding to the heat dissipation layer; analyze and process the fluid characteristic parameters of the microfluidic cooling structure to obtain a dynamic flow distribution model corresponding to the microfluidic cooling structure; determine the thermal management mechanism of the LED driving circuit based on the coupling characteristic analysis of the dynamic heat conduction model and the dynamic flow distribution model; and perform simulation processing on the thermal management data based on the thermal management mechanism to generate thermal management instructions for the LED driving circuit. The second generation module is further configured to: extract multimodal features from the dynamic environment data using a multimodal feature extraction neural network constructed based on deep learning, to obtain an environment perception feature vector corresponding to the dynamic environment data; combine the environment perception feature vector with the power characteristics of the LED driving circuit, and determine the power allocation parameters of the LED driving circuit based on a DC-DC converter constructed using a gallium nitride structure; determine the adaptive dimming mechanism of the LED driving circuit according to the dynamic relationship between the power allocation parameters and a preset pulse width modulation algorithm; generate a pulse width modulation signal based on the adaptive dimming mechanism; and use the pulse width modulation signal as the adaptive dimming command of the LED driving circuit.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images