Temperature management system of gallium nitride power adapter

Abstract

The invention relates to the technical field of power adapter temperature management, and discloses a gallium nitride power adapter temperature management system comprising a dynamic thermal model module used for accurately predicting the temperature change trend of each key component; the multi-level temperature monitoring network module is used for forming a complete temperature distribution diagram; the multi-device collaborative sensing module is used for generating a sensing result of the whole heat dissipation environment; the self-adaptive air duct structure module is used for optimizing an air flow path; the heat dissipation path module based on swarm intelligence is used for calculating and generating an optimal multi-device collaborative heat dissipation path by applying a swarm intelligence algorithm; the self-adaptive heat dissipation control strategy module is used for realizing multi-target balance optimization of temperature, noise and energy consumption; the problem that heat dissipation is difficult when multiple adapters are used in a centralized mode is solved, heat dissipation efficiency is improved, energy consumption is reduced, and noise is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of power adapter temperature management, and more specifically, to a temperature management system for a gallium nitride power adapter. Background Art

[0002] Due to its high power density characteristics, a gallium nitride power adapter generates a large amount of heat during operation. Especially in scenarios such as conference rooms and shared workspaces where multiple devices are charged portably, when multiple adapters are placed together, local high-temperature areas are likely to form.

[0003] In the prior art, each adapter dissipates heat independently, lacking cooperation between devices; the air duct structure is fixed and cannot cope with dynamically changing hot spot positions; the fan control strategy is simple, making it difficult to balance noise, energy consumption, and heat dissipation effect. This results in inefficient utilization of heat dissipation resources, affecting the performance and service life of the power adapter. When multiple gallium nitride power adapters are placed together, the heat generated by each adapter affects each other, forming a complex thermal environment. Traditional single-device independent heat dissipation control is difficult to handle such a cluster environment and cannot achieve globally optimal temperature management. Eventually, the temperature in the hot spot area is too high, while heat dissipation resources are wasted in other areas. Summary of the Invention

[0004] The present invention provides a temperature management system for a gallium nitride power adapter to solve the technical problem of low heat dissipation efficiency when multiple adapters are placed together in related technologies.

[0005] The present invention provides a temperature management system for a gallium nitride power adapter, including: A dynamic thermal model module for real-time constructing a three-dimensional thermal distribution model inside the gallium nitride power adapter, and accurately predicting the temperature change trend of each key component based on the heat conduction equation and the finite element analysis method; A multi-level temperature monitoring network module for real-time collecting temperature data of each key point inside the power adapter through a distributed micro temperature sensor array to form a complete temperature distribution map; A multi-device collaborative perception module for collecting and sharing temperature distribution data, fan status data, and air flow information between multiple gallium nitride power adapters to generate a perception result of the overall heat dissipation environment; An adaptive air duct structure module for dynamically adjusting the internal air duct structure through shape memory materials and microelectromechanical actuators according to real-time thermal gradient distribution data to optimize the air flow path; A heat dissipation path module based on swarm intelligence, which calculates and generates an optimal multi-device collaborative heat dissipation path based on the device topology network and the thermal state information of each device by applying swarm intelligence algorithms; The adaptive heat dissipation control strategy module, based on environmental perception data and heat dissipation paths, uses a deep reinforcement learning algorithm to intelligently regulate the operating parameters of the fan, achieving multi-objective balance optimization of temperature, noise, and energy consumption.

[0006] In a preferred embodiment, the multi-device collaborative perception module includes: Collect the temperature distribution data of each key point of itself through the built-in temperature sensor network, and the sampling frequency of each temperature sensor is dynamically adjusted according to the temperature change gradient; Dynamically adjust the information exchange frequency between devices according to the temperature change rate; use the proximity device discovery algorithm based on signal strength to identify adjacent adapter devices in the physical space through near-field communication technology; Apply the weighted data fusion algorithm to generate a comprehensive state representation of the local environment.

[0007] In a preferred embodiment, the information exchange frequency between devices is calculated according to the following formula: ; Where, represents the information exchange frequency between devices; represents the lowest communication frequency of the system in the stable state; represents the adjustment coefficient, which is used to control the influence degree of temperature change on the communication frequency; represents the absolute magnitude of temperature change per unit time; When the temperature changes violently, the communication frequency will increase accordingly to ensure that the system can respond to the changes in the thermal environment in a timely manner.

[0008] In a preferred embodiment, the adaptive air duct structure module includes: Construct a micro air duct network made of shape memory polymer materials. In the initial state, the air ducts are in a uniformly distributed grid structure; Based on the temperature distribution data, calculate the thermal gradient vector field in the space; Based on the thermal response equation, calculate the deformation state of the air duct structure; Convert the calculated air duct structure deformation instruction into an electric control signal, and precisely control the local deformation of the shape memory polymer material through the micro actuator network.

[0009] In a preferred embodiment, the swarm particle collaborative optimization algorithm adopted in the swarm intelligence-based heat dissipation path module includes the following steps: According to the temperature distribution and heat dissipation requirements of multiple adapters, construct an objective function for overall heat dissipation optimization; Initialize a heat dissipation path vector for each adapter, and the heat dissipation path vector represents the direction and intensity of the device's heat dissipation air flow; Adopt an improved particle swarm optimization algorithm to iteratively update the heat dissipation path vector of each device; During the iteration process, continuously update the optimal position record of each device and the global optimal position record.

[0010] In a preferred embodiment, the improved particle swarm optimization algorithm updates the heat dissipation path vector through the following formula: ; Where, represents the heat dissipation path vector of device at time ; represents the updated heat dissipation path vector of device at time ; represents the historical optimal path of device itself; represents the global optimal path; , , , respectively represent the weight coefficients of inertia, cognitive learning, social learning, and neighbor cooperation; , , respectively represent the acceleration coefficients of cognitive learning, social learning, and neighbor cooperation; represents the set of neighbor devices of device ; represents the total difference between the heat dissipation paths of neighbor devices and the heat dissipation path of the current device, which is used to achieve heat dissipation cooperation between adjacent devices.

[0011] In a preferred embodiment, the adaptive heat dissipation control strategy module includes the following steps: Define the state space and action space of fan control; Design a reward function that comprehensively considers temperature control accuracy, noise level, energy consumption, and group cooperation effect; Adopt an improved double deep Q-network structure, including an online network and a target network; Based on the learned Q-network, regularly execute fan control decisions.

[0012] In a preferred embodiment, the reward function is calculated through the following formula: ; Where, represents the comprehensive evaluation score of the fan control decision; represents the temperature control reward; represents the noise control reward; represents the energy consumption control reward; Indicates group collaborative reward; , , , respectively represent the importance degrees of temperature, noise, energy consumption, and group collaboration in the total reward.

[0013] In a preferred embodiment, the adaptive heat dissipation control strategy module further includes the following steps: Continuously record the performance data during operation; Based on the collected historical data, use the clustering algorithm to divide the operating environment into multiple typical scenarios; Combine the simulated annealing algorithm to improve the search process of the genetic algorithm.

[0014] In a preferred embodiment, a computer-readable storage medium is used to store computer-readable instructions, which can run a temperature management system of a gallium nitride power adapter when read by a computer.

[0015] The beneficial effects of the present invention are as follows: Through the collaborative perception and information sharing among devices, the accurate perception of the overall heat dissipation environment is realized; Through the adaptive air duct structure, targeted heat dissipation is realized; Through the optimization of the swarm intelligence heat dissipation path, the efficient guidance of heat is realized; Through the reinforcement learning fan control, the multi-objective balance of temperature, noise, and energy consumption is realized; Through rule evolution, the continuous self-optimization of the system is realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a module diagram of a temperature management system of a gallium nitride power adapter according to the present invention. DETAILED DESCRIPTION

[0017] Now, the subject matter described herein will be discussed with reference to example embodiments. It should be understood that discussing these embodiments is only to enable those skilled in the art to better understand and thus implement the subject matter described herein, and the functions and arrangements of the elements discussed can be changed without departing from the protection scope of the content of this specification. Each example can omit, substitute, or add various processes or components as needed. Additionally, the features described in some examples can also be combined in other examples.

[0018] At least one embodiment of the present invention discloses a temperature management system of a gallium nitride power adapter, as Figure 1 shown, including: A dynamic thermal model module is used to construct a three-dimensional thermal distribution model inside a gallium nitride power adapter in real time. Based on the heat conduction equation and the finite element analysis method, it can accurately predict the temperature change trends of key components. It includes the following: Establish a dynamic thermal model that includes a multi-level thermal resistance and capacitance network. This model accurately depicts the thermal characteristics of each component inside the gallium nitride power adapter and their interactions. The dynamic thermal model can be expressed as: ; where represents the heat capacity of each component of the system; represents the temperature at each point in the system; is the rate of change of temperature with time; is the power loss vector; represents the thermal conductivity between each point inside the system and between the system and the environment; is the ambient temperature.

[0019] This dynamic thermal model can be further enhanced to a time-varying adaptive model by updating the thermal resistance and capacitance parameters in real time through an online parameter estimation method. The system can use the Recursive Least Squares (RLS) or the Kalman filter to estimate the model parameters in real time, expressed as: ; where , represent the parameter estimation values at time and time respectively; is the gain matrix, controlling the step size and direction of parameter update; is the actual measured value; is the regression vector, containing input variables related to parameter estimation; is the model prediction output based on the previous parameter estimation; is the prediction error, used to correct parameter estimation.

[0020] During the model construction process, the system can adopt multiple heat conduction models according to the different characteristics of the heat conduction paths. For example, for the inside of electronic components, a three-dimensional heat diffusion equation can be used for fine modeling; for the heat exchange between the radiator and the environment, a convective heat transfer model can be used; for the thermal radiation between components, the Stefan-Boltzmann law can be used for description. This multi-physics field coupling modeling method can more accurately reflect the thermal behavior of the actual system.

[0021] In practical applications, this dynamic thermal model demonstrates strong environmental adaptability. For example, in a high-power gallium nitride charging pile used in an electric vehicle fast charging station, the system needs to adapt to a wide environmental temperature range from -20°C to 45°C.

[0022] Traditional static models often exhibit large deviations under extreme temperature conditions, while the adaptive dynamic thermal model of this system can adjust parameters in real time, accurately capture changes in material thermal properties and the temperature transient process during the startup phase in low-temperature environments, and precisely predict the thermal saturation phenomenon of electronic components in high-temperature environments.

[0023] This model reduces the prediction error across the entire temperature range, improves the prediction accuracy, and effectively avoids the risks of overprotection or thermal runaway caused by inaccurate temperature prediction.

[0024] A multi-level temperature monitoring network module is used to collect temperature data of key points inside the power adapter in real time through a distributed micro temperature sensor array, forming a complete temperature distribution map; Specifically, it includes the following: The system designs a multi-level temperature monitoring network, including surface temperature sensors, internal temperature sensors, and thermal imagers, etc., to comprehensively monitor the thermal distribution of the gallium nitride power adapter. The multi-level temperature monitoring network can provide accurate thermal distribution data, providing a scientific basis for formulating thermal management strategies.

[0025] The temperature monitoring network can adopt a hierarchical architecture, consisting of three levels: the core component layer, the power heat dissipation layer, and the outer shell surface layer. Different types and precisions of temperature sensors are deployed at each level to meet different monitoring requirements.

[0026] The core component layer uses micro thermocouples or integrated MEMS temperature sensors, which have high precision (±0.1°C) and fast response characteristics (response time < 20ms), and can accurately capture the transient temperature changes of key components such as GaN power devices and drive chips; The power heat dissipation layer uses an infrared array sensor, which can achieve temperature distribution scanning of heat dissipation components such as radiators and heat pipes, with a resolution of up to 0.5mm; The outer shell surface layer uses a combination of thermal resistors and thermistors to reduce the system cost while ensuring measurement stability.

[0027] The system can also implement sensor redundancy design and dynamic calibration mechanisms. Multiple sensors are set at key temperature points for redundant monitoring, and abnormal readings are identified and excluded by comparing the data of different sensors.

[0028] At the same time, the system periodically executes a self-calibration program, using known temperature points as references to dynamically adjust the calibration coefficients of each sensor to ensure long-term monitoring accuracy.

[0029] In practical applications, the multi-level temperature monitoring network performs excellently. For example, in a gallium nitride server power supply system deployed in a high-density server room, traditional single-point temperature monitoring solutions often fail to detect local hotspots in a timely manner. However, the multi-level monitoring network of this system can accurately locate the hotspot position and visually present the temperature distribution through the real-time heat map display function.

[0030] In a test, the system successfully identified a local overheating phenomenon caused by a blocked radiator. The warning mechanism was triggered within only 7 seconds after the temperature anomaly occurred, sounding an alarm 43 seconds earlier than the traditional monitoring solution, effectively avoiding the potential risk of equipment damage.

[0031] The multi-device collaborative sensing module is used to collect and share temperature distribution data, fan status data, and airflow information among multiple gallium nitride power adapters, and generate a perception result of the overall heat dissipation environment; Specifically, it includes the following: This system uses wireless communication technologies such as Bluetooth Low Energy (BLE), ZigBee, or WiFi to achieve communication and information sharing among multiple gallium nitride power adapters. The adapters share temperature data, power load information, and heat dissipation resource status, thus forming a collaborative sensing network.

[0032] The system can adopt a hierarchical communication architecture, including a device-level communication layer and a regional coordination layer.

[0033] The device-level communication layer is responsible for direct data exchange between nearby devices and can use the BLE Mesh network to achieve low-latency (<10ms) point-to-point and broadcast communication; The regional coordination layer is connected to the central management unit through WiFi or Ethernet to achieve information aggregation and decision-making distribution over a wider range.

[0034] The system applies a lightweight compression algorithm and an incremental transmission mechanism during communication, reducing the transmission bandwidth requirement for temperature monitoring data while keeping the data accuracy loss within an acceptable range (<0.2°C).

[0035] The system can also implement an adaptive communication strategy, dynamically adjusting the communication frequency and data priority according to network congestion conditions and data importance. For example, when a sharp rise in temperature is detected, the relevant devices will automatically increase the data transmission frequency and priority to ensure that key information can be conveyed in a timely manner; while during the temperature stable stage, the communication frequency is reduced to save energy.

[0036] In practical applications, the collaborative perception and information sharing mechanism performs excellently. In an enterprise meeting room scenario, when 12 laptops are simultaneously using gallium nitride chargers, the system identifies the hotspot distribution pattern through information sharing among devices and coordinates the heat dissipation resources of each charger.

[0037] Compared with the traditional independent operation scheme, the collaborative system reduces the maximum temperature in the hotspot area and simultaneously reduces the overall energy consumption. User feedback shows that the intelligent collaborative feature of the system significantly improves the charging experience in high-density usage environments and reduces the risk of device overheating shutdown.

[0038] The adaptive air duct structure module is used to dynamically adjust the internal air duct structure according to real-time thermal gradient distribution data through shape memory materials and microelectromechanical actuators, and optimize the air flow path; Specifically, it includes the following: The system adopts a deformable air duct structure, which can dynamically adjust the air duct shape and air volume distribution according to the real-time monitored temperature distribution to achieve precise heat dissipation. The adaptive air duct structure includes multiple independently controllable micro fans, adjustable air guide plates, and an electromagnetic-driven air duct switching mechanism, etc.

[0039] The adaptive air duct structure can adopt flexible air guide blades driven by shape memory alloy (SMA), which can undergo controllable deformation under current excitation to change the air flow direction and distribution.

[0040] The system uses a PWM control method to precisely adjust the SMA drive current to achieve continuous adjustment of the air guide blade angle within the range of 0 - 45°.

[0041] At the same time, the air duct structure also includes a main air duct switching valve driven by a micro servo, which can quickly switch between 3 preset air duct modes (switching time < 500ms) to adapt to different heat dissipation demand scenarios.

[0042] The system can also implement the dynamic optimization function of the air duct structure. Through computational fluid dynamics (CFD) simulation and digital twin technology, the system can real-time predict the air flow distribution and heat dissipation effect under different air duct configurations and select the optimal air duct structure.

[0043] The optimization algorithm adopts an improved particle swarm optimization method to complete the air duct configuration optimization calculation within an average of 3.2 seconds to meet the real-time adjustment requirements.

[0044] In practical applications, the adaptive air duct structure performs outstandingly. In the gallium nitride power supply system of a portable high-performance computing workstation, the traditional fixed air duct design either has insufficient heat dissipation or energy waste under different load conditions.

[0045] The adaptive air duct of this system can adjust the heat dissipation strategy in real time according to the change of the computing load of the workstation: In the light load condition, the system automatically switches to the low-noise mode, reducing the fan noise from 38 dB to 26 dB; In the heavy load condition, the system quickly switches to the high-efficiency heat dissipation mode, controlling the temperature of key components within a safe range, while saving energy consumption compared with the traditional fixed air duct design. This intelligent adaptive feature significantly improves user satisfaction and system reliability.

[0046] Step 5: Generate a heat dissipation path based on swarm intelligence; Based on an embodiment of this application, in this step, the swarm particle collaborative optimization algorithm is applied to calculate and generate an optimal multi-device collaborative heat dissipation path based on the device topology network and the thermal state information of each device, realizing efficient heat conduction. It should be understood that the specific implementation process of this step is as follows: The heat dissipation path module based on swarm intelligence calculates and generates an optimal multi-device collaborative heat dissipation path based on the device topology network and the thermal state information of each device by applying the swarm intelligence algorithm; Specifically, it includes the following content: The system constructs an objective function for overall heat dissipation optimization according to the temperature distribution and heat dissipation requirements of multiple adapters: ; Among them, represents the objective function for overall heat dissipation optimization, represents the set of heat dissipation path vectors of all devices, and each vector describes the heat dissipation direction and intensity of the corresponding device; is the average temperature of device ; is the target temperature; is the weight coefficient of device , which is determined according to its heat load and heat dissipation importance. The larger the value, the more important the temperature control of this device; is the collaborative consistency weight, which controls the consistency requirement of the heat dissipation paths of adjacent devices. The larger the value, the higher the requirement for the coordination of the heat dissipation paths of adjacent devices; is the total number of devices in the system; represents the set of neighbor devices of device ; represents the square difference between the actual temperature and the target temperature of device , which is used to quantify the degree of temperature deviation; represents the square difference between the heat dissipation path vector of device and that of its neighbor device , which is used to quantify the inconsistency degree of the heat dissipation paths; The first term of the objective function represents the weighted sum of squares of the deviations between the temperatures of all devices and the target temperature, which prompts each device to reach the target temperature; The second term of the objective function represents the sum of squares of the differences in heat dissipation paths between all adjacent devices, which prompts the heat dissipation paths of adjacent devices to be coordinated and consistent, avoiding air flow conflicts.

[0047] Initialization of particle swarm position and velocity: The system initializes a heat dissipation path vector for each adapter , which represents the direction and intensity of the heat dissipation air flow of the device. The initialization process takes into account the physical location and current thermal state of the device: ; Among them, represents the initial heat dissipation path vector of device ; represents the negative gradient direction of the local temperature field of device , that is, the natural heat flow direction, pointing to the direction where the temperature drops fastest; is a small random perturbation vector, which is used to increase the diversity of the initial solution and prevent the algorithm from falling into a local optimal solution.

[0048] At the same time, the system initializes the optimal position record of each device (the initial value is equal to ), representing the best heat dissipation path found by this device in history; and the global optimal position record (the initial value is the one that makes the objective function the smallest among all ), representing the best heat dissipation path configuration found among all devices.

[0049] In some embodiments, various strategies can be adopted for the initialization of the heat dissipation path vector. For example, according to the historical heat dissipation effect data of the device, a memory-based initialization method can be used, that is, when the similarity between the current environment and a certain historical environment is higher than a threshold, the optimal heat dissipation path in that historical environment is directly used as the initial solution to accelerate the convergence process. Another optional method is to adopt an initialization strategy based on the device layout, analyze the geometric arrangement of the devices in advance, calculate the ideal heat dissipation direction, use it as the dominant direction of the initial vector, and then add a small random perturbation.

[0050] The random perturbation term can be generated using different distributions.

[0051] In the early exploration stage, a uniform distribution can be used, where is the perturbation amplitude parameter, representing the maximum value of the perturbation, which is set to 10%-20% of the temperature gradient magnitude, and is used to control the range of random perturbation; In the later fine-tuning stage, a normal distribution can be adopted , where is the standard deviation parameter, representing the degree of dispersion of random perturbations, and is set to 5% - 10% of the temperature gradient magnitude, used to control the concentration of perturbations.

[0052] Uniform distribution means that the probabilities of random values within to are equal, while the normal distribution means that the random values are distributed in a bell shape around the mean value of 0, where is the variance, determining the width of the distribution.

[0053] This adaptive perturbation generation strategy helps to maintain a large exploration range in the early stage of the algorithm, enabling the system to widely search for possible heat dissipation path solutions. In the later stage, it focuses on the fine optimization of the solution, fine-tuning the found better heat dissipation paths, and improving the accuracy of the final solution.

[0054] In scenarios with high-density electronic devices such as multimedia classrooms, this particle swarm position initialization system exhibits excellent adaptability. For example, in a classroom containing 30 computers and 8 gallium nitride power adapters, the system can quickly identify the temperature distribution characteristics in different areas (such as near the projector, near the window or door), and accordingly initialize the heat dissipation paths of the adapters.

[0055] For the high-heat area in the center of the classroom, the heat dissipation path initialized by the system will point towards the cooler window or door direction; while for the adapters at the edge, the system will initialize heat dissipation paths towards the outside of the classroom, preventing heat from accumulating inside the classroom. Actual measurements show that this intelligent initialization strategy can shorten the convergence time compared to simple gradient reverse initialization and achieve an improvement in heat dissipation efficiency in the final solution.

[0056] Iterative optimization of heat dissipation paths:

[0057] The system uses an improved particle swarm optimization algorithm to iteratively update the heat dissipation path vectors of each device: ; where represents the heat dissipation path vector of device after the th iteration; , respectively represent the heat dissipation path vectors of device and device at the th iteration; represents device The historical optimal heat dissipation path vector; Represents the device The set of neighbor devices; Is the inertia weight, controlling the tendency of the path to maintain the original direction; And Respectively represent the individual cognitive weight and acceleration coefficient, controlling the degree of approaching the device's own historical optimal path; And Respectively represent the social learning weight and acceleration coefficient, controlling the degree of approaching the global optimal path; And Respectively represent the neighbor cooperation weight and acceleration coefficient, controlling the degree of path coordination with adjacent devices. Through this multi-level optimization mechanism, the system can achieve collaborative optimization of the group while maintaining local heat dissipation efficiency.

[0058] In a specific embodiment of the present application, the parameter settings of the group particle collaborative optimization algorithm are as follows: Inertia weight The initial value is 0.8 and linearly decreases to 0.4 with the number of iterations; Individual cognitive weight Is set to 0.6, and the social learning weight Is set to 0.4; Neighbor cooperation weight Is dynamically adjusted according to the device density, set to 0.2 in the sparse device scenario and increased to 0.5 in the dense device scenario; Acceleration coefficient , And Are respectively set to 1.5, 1.2, and 0.8.

[0059] The improved particle swarm algorithm also includes an adaptive congestion control mechanism. When it detects that devices are overly concentrated in a local area, it automatically increases the repulsive force between devices in that area to avoid airflow interference caused by overly concentrated heat dissipation paths. The calculation formula is: ; Wherein, Represents the repulsive force vector of device On device To avoid overly concentrated heat dissipation paths, Is the physical distance between device And device , Is the unit vector from device Pointing to device , Is the repulsive force coefficient, with an initial value of 0.15 and linearly increasing to 0.4 when the local device density exceeds the preset threshold; It represents the characteristic that the repulsive force decays inversely with the square of the distance. The closer the distance, the greater the repulsive force. Represents the device Points to the device The unit vector of determines the direction of the repulsive force. This repulsive force term is added to the particle update formula to form a more balanced heat dissipation path distribution.

[0060] In practical applications, the system quantifies the heat dissipation paths into 8 basic directions and 3 wind force intensity levels, forming a total of 24 discrete action options, enabling the control instructions to be effectively understood and implemented by the fan execution system. During the iterative process of the algorithm, the physical layout constraints of the devices are considered to avoid generating infeasible heat dissipation paths.

[0061] Path Convergence and Implementation: The system continuously updates the optimal position record of each device during the iterative process And the global optimal position record : ; Among them, Represents the historical optimal heat dissipation path vector of the device ; Represents the device At the th iteration, the heat dissipation path vector; Represents updating the heat dissipation path of the device To The objective function value after; Represents using the historical optimal heat dissipation path of the device The objective function value at that time. This formula means that if the new heat dissipation path vector can reduce the objective function value (i.e., better heat dissipation effect), then update the historical optimal record, otherwise keep it unchanged.

[0062] ; Among them, Represents the global optimal heat dissipation path configuration, that is, the heat dissipation path configuration that makes the objective function Obtain the minimum value among all devices; Represents finding the parameter that minimizes the objective function ; . This formula means that the global optimal position record is the one that selects the minimum objective function value among the historical optimal positions of all devices.

[0063] When the iteration converges (the improvement amplitude of the objective function in consecutive iterations is less than the preset threshold) or reaches the maximum number of iterations, the system distributes the final heat dissipation path vector to each device to guide fan control and duct adjustment. Here, the "preset threshold" refers to a small positive number preset by the system to determine whether the algorithm has converged to a stable solution; The "maximum number of iterations" refers to the maximum number of calculation cycles allowed by the algorithm, usually set to 100 to 200 times, to prevent the algorithm from looping infinitely.

[0064] Therefore, through this collaborative optimization based on swarm intelligence, the system can achieve efficient collaborative guidance of heat flow in a group consisting of 3 to 8 devices, significantly improving the overall heat dissipation efficiency.

[0065] In practical applications, this collaborative heat dissipation technology performs excellently. For example, in an edge computing node of a data center, 6 servers equipped with gallium nitride power adapters are deployed. In the traditional scheme, each device manages heat dissipation independently, which easily leads to heat accumulation in some areas.

[0066] The swarm intelligence heat dissipation path optimization function of this system can form a "heat wave promotion effect", synergistically pushing heat from high-temperature areas to areas with better heat dissipation conditions.

[0067] In a high-load test, the collaborative system reduced the highest temperature point in the cabinet, while narrowing the temperature difference, significantly reducing the damage to devices caused by thermal cycling. More importantly, the system reduced the average fan energy consumption of the edge computing node while maintaining the same computing performance, improving the overall energy efficiency level.

[0068] The adaptive heat dissipation control strategy module, based on environmental perception data and heat dissipation paths, uses a deep reinforcement learning algorithm to intelligently regulate the operating parameters of the fans, achieving multi-objective balance optimization of temperature, noise, and energy consumption.

[0069] Specifically, it includes the following contents: Environmental state representation: Define the environmental state space, including the following key features: Multi-point temperature sequence: , where The temperature values of , , respectively represent the temperature values of the , , th key monitoring points; represents the number of key monitoring points; Power load status: , indicating The load information of , , respectively represent the load information of the , , th power levels; represents the number of power levels; Environmental conditions: , where , , respectively represent the environmental temperature, humidity, and air flow conditions; Equipment operation time: , representing the current continuous operation time; Historical control effect: , representing the actions and rewards of the past time steps, where , , respectively represent the heat dissipation control actions executed by the system at the , , th time steps; , , respectively represent the reward values obtained by the system after executing the heat dissipation control actions at the , , th time steps; represents the historical record length; The state features have undergone feature engineering, including time series feature extraction (such as temperature change rate, maximum temperature, temperature difference, etc.) and spatial distribution feature extraction (such as hot spot clustering, temperature gradient, etc.). The processed features are normalized so that the range of feature values in each dimension is unified within the interval, which is beneficial to the training of the neural network.

[0070] The system can also apply an autoencoder to the state space for dimensionality reduction, compressing the original high-dimensional state into a low-dimensional latent space and reducing the learning difficulty.

[0071] The autoencoder adopts a stacked fully connected layer structure. The encoder part compresses from the original 128-dimensional features to 32-dimensional latent representations, and the decoder part reconstructs back to the original dimension.

[0072] After pre-training, the autoencoder improves the reconstruction accuracy in the state reconstruction task, reduces the feature space, and effectively reduces the complexity of reinforcement learning.

[0073] Heat dissipation control action space: The system defines the heat dissipation control action space, including: Fan speed control: , representing the rotational speed settings of , , respectively representing the rotational speed values of the , , th fans; represents the number of fans; Air duct switching decision: , representing the switch states of , , respectively representing the state values of the , , th air duct components, with the values being 0 (closed) or 1 (open); represents the number of air duct components; Power limit strategy: , representing the limit levels of , , respectively representing the limit levels of the , , th power modules, with the value range being 0 - 3, corresponding to no limit, mild limit, moderate limit, and severe limit respectively; represents the number of power modules; To simplify the control complexity, the system discretizes the above continuous action space into a finite number of action combinations, forming a total of 128 heat dissipation control strategy options. These options are pre-designed through expert knowledge to cover various heat dissipation scenario requirements.

[0074] The system can also implement a hierarchical design of the action space.

[0075] The top-level control strategy selector is responsible for switching among three modes: "energy-saving mode", "balanced mode", and "high-performance mode"; The middle-level controller is responsible for determining the cooperative control mode of the fan group; The bottom-level actuator is responsible for precisely adjusting the rotational speed of each fan and the position of the air duct components.

[0076] This hierarchical design enables the system to reduce the complexity of the decision-making space while maintaining sufficient flexibility.

[0077] Reward function design: The multi-objective reward function designed by the system considers three aspects: heat dissipation effect, energy consumption, and noise: ; Among them, is the total reward function, representing the comprehensive reward value obtained by executing the action under the state ; represents the current environmental state of the system, including information such as temperature distribution and power load; represents the heat dissipation control actions taken by the system, such as fan speed adjustment and air duct switching; is the temperature control reward, representing the evaluation of the temperature control effect of the system; is the energy consumption control reward, representing the evaluation of the energy consumption control effect of the system; is the noise control reward, representing the evaluation of the noise control effect of the system; , and respectively represent the importance weights of temperature control, energy consumption control, and noise control in the overall reward, which are dynamically adjusted according to different usage scenarios and user preferences, and satisfy , , ensuring the normalization of the weights in the three aspects.

[0078] The temperature control reward adopts the following formula: ; Among them, represents the temperature control reward value obtained by executing the action under the state ; is the current highest temperature, representing the value of the highest temperature point monitored in the system; is the temperature threshold, representing the highest safe temperature allowed by the system; represents the square penalty for the highest temperature exceeding the threshold, which is 0 when the temperature does not exceed the threshold; is the standard deviation of the temperature distribution, characterizing the temperature uniformity, and the smaller the value, the more uniform the temperature distribution; , respectively represent the weight coefficients of the highest temperature overrun penalty and the temperature non-uniformity penalty; indicates that these factors reduce the overall reward value as penalty terms. The better the temperature control, the smaller the penalty and the higher the reward value.

[0079] The calculation formula for the energy consumption control reward is: ; Among them, represents the energy consumption control reward value obtained by executing the action under the state ; represents the fan at the rotational speed Power consumption under; is the energy consumption weight coefficient, which controls the intensity of energy consumption penalty. The larger the value, the higher the degree of attention of the system to energy consumption; represents the total number of fans in the system; represents the fan number, ranging from 1 to ; represents summing up the power consumption of all fans; represents that energy consumption is used as a penalty term to reduce the overall reward value. The lower the energy consumption, the smaller the penalty and the higher the reward value.

[0080] The calculation formula for the noise control reward is: ; Among them, represents the noise control reward value obtained by executing action in state ; represents the noise decibel value generated by fan at rotational speed ; represents the rotational speed value of the th fan; represents the total number of fans in the system; is the noise weight coefficient, which controls the intensity of noise penalty. The larger the value, the higher the degree of attention of the system to noise control; represents the operation of taking the maximum noise value among all fans, because human ear perception is usually affected by the maximum noise source; represents that noise is used as a penalty term to reduce the overall reward value. The smaller the noise, the smaller the penalty and the higher the reward value.

[0081] In practical applications, the reward function also includes additional smoothing terms and sparse control terms to avoid frequent jumps in the control strategy: ; Among them, represents the smoothing control reward value obtained by executing action in state ; represents the rotational speed of fan at the current time step ; represents the rotational speed of fan at the previous time step ; represents the absolute value of the change in fan rotational speed, which is used to quantify the degree of rotational speed fluctuation; is the smoothing penalty coefficient, which controls the intensity of rotational speed change penalty. The larger the value, the higher the requirement of the system for rotational speed stability; Represents the total number of fans in the system; Represents the fan number, ranging from 1 to ; Represents summing up the rotational speed changes of all fans; Represents that the rotational speed change reduces the overall reward value as a penalty term. The smaller the rotational speed change, the smaller the penalty and the higher the reward value, thus encouraging the system to maintain a stable control strategy.

[0082] Through this multi-objective reward design, the system can balance energy efficiency and user experience while meeting the heat dissipation requirements.

[0083] Implementation of the deep reinforcement learning algorithm: The system uses an improved deep reinforcement learning Q-network (DeepQ-Network, DQN) algorithm to implement heat dissipation control strategy learning. The network architecture consists of 3 layers of MLP, including an input layer with 256 nodes, hidden layers with 128 nodes and 64 nodes, and an output layer with the number of actions. The network is optimized using the Adam optimizer, with the learning rate set to 0.001 and the discount factor set to 0.95.

[0084] To improve learning efficiency and policy stability, the system adopts the following improvement techniques: Dual network structure: including an evaluation network and a target network, and the target network is updated every 100 training steps; Prioritized experience replay: Sampling and prioritizing experiences based on the magnitude of TD error to improve learning efficiency; Noise injection exploration: Adding Ornstein-Uhlenbeck noise during action selection to promote exploration of the policy space.

[0085] In addition, the system also implements transfer learning functionality, migrating the policy pre-trained in the simulation environment to the actual device to accelerate the learning process in actual applications.

[0086] During the transfer process, a hierarchical fine-tuning strategy is adopted. First, the underlying feature extraction part of the network is fixed, and only the decision layer parameters are fine-tuned; subsequently, more layers are gradually unlocked for fine-tuning according to performance feedback. This method can retain general heat dissipation knowledge while quickly adapting to the characteristics of specific devices.

[0087] In the scenario of an electric vehicle charging station, this adaptive heat dissipation control strategy performs excellently. The high-power gallium nitride charging piles in the charging station need to maintain stable operation in outdoor environments and under varying charging loads.

[0088] Traditional rule-based heat dissipation control schemes cannot adapt to complex environmental changes. The reinforcement learning control strategy of this system can automatically adjust the optimal heat dissipation strategy according to different seasons and charging powers:

[0089] In the high-temperature environment of summer, the system will pre-start heat dissipation and cooling; In the low-temperature environment of winter, the system adopts a more energy-saving intermittent heat dissipation mode.

[0090] Actual measurements show that compared with traditional control schemes, the reinforcement learning control system reduces the average temperature fluctuation of the charging pile, saves heat dissipation energy consumption during the annual operation cycle, and significantly improves the reliability and service life of the charging equipment.

[0091] Technical effects of this embodiment: A temperature management system for a gallium nitride power adapter provided by this embodiment, through the use of technical means such as a dynamic thermal model, a multi-level temperature monitoring network, multi-device collaborative perception and information sharing, an adaptive air duct structure, a heat dissipation path based on swarm intelligence, and an adaptive heat dissipation control strategy, has achieved remarkable technical effects in the temperature management of the gallium nitride power adapter: Improved heat dissipation efficiency: Compared with traditional static heat dissipation systems, the dynamic thermal model and adaptive air duct structure of this system can accurately identify hot spots and dissipate heat targeted, improving heat dissipation efficiency.

[0092] Significantly reduced energy consumption: The adaptive control strategy based on deep reinforcement learning flexibly adjusts the heat dissipation intensity according to actual needs, minimizing energy consumption while meeting the heat dissipation requirements.

[0093] Substantially reduced noise: The intelligent air duct structure and machine learning-based control algorithm can minimize noise while meeting the heat dissipation requirements.

[0094] Enhanced system adaptability: The dynamic thermal model combined with a multi-sensor monitoring network enables the system to adapt to different environmental conditions and usage scenarios. In the range of ambient temperature from -10°C to 45°C, the system can maintain the best heat dissipation effect, and its adaptability is improved compared with traditional systems.

[0095] Improved device reliability: Through precise temperature control and thermal distribution equalization, the system can significantly reduce thermal stress and reduce the damage of thermal cycling to components. Long-term tests show that this system extends the expected life of gallium nitride power devices and significantly reduces the failure rate caused by overheating.

[0096] Expanded application scenarios: Multi-device collaborative perception and optimization of the heat dissipation path based on swarm intelligence enable the system to adapt to high-density device deployment scenarios. In environments such as data centers and server rooms, the collaborative heat dissipation effect between adjacent devices is improved compared with independent heat dissipation, providing the possibility for the application of gallium nitride power adapters in more professional scenarios.

[0097] Improved system integration: The intelligent control of the adaptive temperature management system enables the gallium nitride power adapter to dissipate heat safely in a smaller volume, supporting a higher power density. This allows for an increase in power density within the same volume, providing technical support for the development of portable high-power adapters.

[0098] Optimized user experience: The system automatically adjusts the heat dissipation strategy based on the device usage pattern, maintaining optimal performance and user experience in different load scenarios. For example, it automatically switches to the low-noise mode in quiet environments such as presentations in a meeting room, and prioritizes heat dissipation in high-density computing environments, intelligently balancing various indicators.

[0099] Through the above technical effects, the temperature management system provided in this embodiment comprehensively improves the performance, reliability, and user experience of the gallium nitride power adapter, providing key technical support for the development and application of high-efficiency, small-size, and high-reliability power adapters.

[0100] The above describes the embodiments of the present invention. However, these embodiments are not limited to the above specific implementation manners. The above specific implementation manners are merely illustrative and not restrictive. Under the inspiration of this embodiment, those of ordinary skill in the art can also make more equivalent embodiments in various forms, all of which fall within the protection scope of this embodiment.

Claims

1. A temperature management system for a gallium nitride power adapter, characterized in that: include: Dynamic thermal model module, which is used to construct a three-dimensional thermal distribution model inside the GaN power adapter in real time. Based on the heat conduction equation and finite element analysis method, it can accurately predict the temperature change trend of each key component. Multi-level temperature monitoring network module, used to collect temperature data of key points inside the power adapter in real time through a distributed micro temperature sensor array to form a complete temperature distribution map; Multi-device collaborative perception module, used to collect and share temperature distribution data, fan status data and airflow information between multiple GaN power adapters, and generate perception results of the overall heat dissipation environment; Adaptive air duct structure module, which is used to dynamically adjust the internal air duct structure and optimize the airflow path based on real-time thermal gradient distribution data through shape memory materials and micro-electromechanical actuators; The heat dissipation path module based on swarm intelligence uses swarm intelligence algorithms to calculate and generate the optimal multi-device collaborative heat dissipation path based on the device topology network and the thermal status information of each device; The adaptive heat dissipation control strategy module uses a deep reinforcement learning algorithm to intelligently adjust fan operating parameters based on environmental perception data and heat dissipation paths, achieving multi-objective balanced optimization of temperature, noise and energy consumption.

2. The temperature management system of a gallium nitride power adapter according to claim 1, characterized in that: The multi-device collaborative sensing module includes: The temperature distribution data of each key point is collected through the built-in temperature sensor network. The sampling frequency of each temperature sensor is dynamically adjusted according to the temperature change gradient. Dynamically adjust the frequency of information exchange between devices according to the temperature change rate; use a neighboring device discovery algorithm based on signal strength to identify adjacent adapter devices in the physical space through near-field communication technology; A weighted data fusion algorithm is applied to generate a comprehensive state representation of the local environment.

3. The temperature management system of a gallium nitride power adapter according to claim 2, characterized in that: The frequency of information exchange between devices is calculated according to the following formula: ； in, Indicates the frequency of information exchange between devices; Indicates the lowest communication frequency of the system in a stable state; Represents the adjustment coefficient, which is used to control the impact of temperature changes on the communication frequency; Indicates the absolute magnitude of temperature change per unit time; When the temperature changes dramatically, the communication frequency will increase accordingly to ensure that the system can respond to changes in the thermal environment in a timely manner.

4. The temperature management system of a gallium nitride power adapter according to claim 1, characterized in that: The adaptive air duct structure module comprises: Construct a micro air duct network made of shape memory polymer material, and the ducts are in a uniformly distributed grid structure in the initial state; Based on the temperature distribution data, calculate the thermal gradient vector field in space; Calculate the deformation state of the duct structure based on the thermal response equation; The calculated deformation instructions of the duct structure are converted into electrical control signals, and the local deformation of the shape memory polymer material is precisely controlled through a microactuator network.

5. The temperature management system of a gallium nitride power adapter according to claim 1, characterized in that: The swarm particle collaborative optimization algorithm adopted in the heat dissipation path module based on swarm intelligence includes the following steps: According to the temperature distribution and heat dissipation requirements of multiple adapters, the objective function of overall heat dissipation optimization is constructed; Initialize a heat dissipation path vector for each adapter, which represents the direction and intensity of the heat dissipation airflow of the device; An improved particle swarm optimization algorithm is used to iteratively update the heat dissipation path vector of each device; During the iteration process, the optimal location record of each device and the global optimal location record are continuously updated.

6. The temperature management system of a gallium nitride power adapter according to claim 5, characterized in that: The improved particle swarm optimization algorithm updates the heat dissipation path vector by the following formula: ； in, Indicates the device In time The heat dissipation path vector; Indicates the device In time The updated heat dissipation path vector of ; Indicates the device The best historical path for itself; represents the global optimal path; , , , represent the weight coefficients of inertia, cognitive learning, social learning and neighbor cooperation respectively; , , denote the acceleration coefficients of cognitive learning, social learning, and neighbor collaboration, respectively; Indicates the device The neighbor device set; Indicates the sum of the differences between the cooling paths of neighboring devices and the cooling path of the current device, which is used to achieve cooling coordination between neighboring devices.

7. The temperature management system of a gallium nitride power adapter according to claim 1, characterized in that: The adaptive heat dissipation control strategy module includes the following steps: Define the state space and action space of fan control; Design a reward function that comprehensively considers temperature control accuracy, noise level, energy consumption, and group synergy effect; Adopt an improved dual deep Q network structure, which includes an online network and a target network; Based on the learned Q-network, fan control decisions are performed periodically.

8. The temperature management system of a gallium nitride power adapter according to claim 7, characterized in that: The reward function is calculated by the following formula: ； in, represents the comprehensive evaluation score of the fan control decision; Indicates temperature control reward; indicates a noise control reward; Indicates energy consumption control reward; represents group coordination reward; , , , Respectively represent the importance of temperature, noise, energy consumption and group coordination in the total reward.

9. The temperature management system of a gallium nitride power adapter according to claim 1, characterized in that: The adaptive heat dissipation control strategy module also includes the following steps: Continuously record performance data during operation; Based on the collected historical data, the operating environment is divided into multiple typical scenarios using clustering algorithms; Combined with simulated annealing algorithm, the search process of genetic algorithm is improved.

10. A computer-readable storage medium, characterized in that: It is used to store computer-readable instructions, and when the computer-readable instructions are read by a computer, it can run a temperature management system of a gallium nitride power adapter as described in any one of claims 1-9.

Images