Self-adaptive temperature regulation and control method and device for power adapter

Abstract

The invention relates to the technical field of power supply temperature regulation and control, in particular to a self-adaptive temperature regulation and control method and device of a power adapter. The method comprises the following steps: acquiring a real-time thermal imaging image of the power adapter; performing independent core heat source identification on the real-time thermal imaging image, and performing image region division processing to generate a plurality of core heat source region images; pixel point temperature value calculation is carried out on the multiple core heat source area images, temperature flow trend analysis is carried out, and a three-dimensional temperature flow distribution field is constructed; acquiring current and voltage parameters of a plurality of parts of the power adapter based on the sensor nodes; carrying out operation load calculation in a period on the current and voltage parameters of the plurality of parts so as to obtain load situations of the plurality of parts; and performing multi-time-point temperature trend prediction on the three-dimensional temperature flow distribution field based on the load situations of the plurality of parts, and constructing a plurality of heat source point temperature trend prediction curves. According to the invention, adaptive and safe temperature control of the power adapter is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of power supply temperature control, and in particular to a method and device for adaptively controlling temperature of a power supply adapter. Background Art

[0002] With the rapid development of electronic devices, power adapters have become an indispensable and important component. As a key component that provides power supply for various electronic products, power adapters bear the key power supply function. But at the same time, power adapters also face some important safety issues, especially the risk of overheating. The internal temperature of a power adapter that runs at high load for a long time may continue to rise. If effective temperature control measures are not taken in time, it may cause serious overheating failures, thereby endangering the safe operation of the entire electronic system.

[0003] Traditional power adapter temperature monitoring and overheat protection methods often rely on simple temperature sensors and fixed temperature thresholds. When the measured temperature exceeds a preset threshold, the protection mechanism is triggered and the power output is cut off. This passive overheat protection method not only fails to predict and actively regulate the temperature change trend, but also makes it difficult to take into account the normal power supply needs of the power adapter, which can easily cause unnecessary interruptions. Therefore, in order to meet the requirements of modern electronic devices for the safety and reliability of power adapters, a more intelligent temperature control method is urgently needed, which can actively predict and sense the temperature change trend inside the power adapter, and take targeted control measures at critical moments, so as to achieve adaptive overheat protection. Summary of the invention

[0004] In order to solve the above technical problems, the present invention proposes a method and device for adaptive temperature control of a power adapter to solve at least one of the above technical problems.

[0005] To achieve the above object, the present invention provides a method for adaptively controlling temperature of a power adapter, comprising the following steps: Step S1: acquiring a real-time thermal imaging image of a power adapter; performing independent core heat source identification on the real-time thermal imaging image, and performing image area division processing to generate a plurality of core heat source area images; Step S2: Calculate the pixel temperature values ​​of multiple core heat source area images, perform temperature flow trend analysis, and construct a three-dimensional temperature flow distribution field; Step S3: obtaining current and voltage parameters of multiple parts of the power adapter based on the sensor node; performing periodic operation load calculation on the current and voltage parameters of the multiple parts, and performing load situation evolution, thereby obtaining the load situation of the multiple parts; Step S4: Based on the load situation of multiple parts, the three-dimensional temperature flow distribution field is subjected to multi-time point temperature trend prediction, and multiple heat source point temperature trend prediction curves are constructed; Step S5: performing overheating temperature detection on the temperature trend prediction curves of multiple heat source points based on the preset power adapter heat source temperature threshold, and performing iterative temperature control simulation to generate multiple temperature control simulation data; Step S6: obtaining multiple temperature trend prediction curves after control based on multiple temperature control simulation data; performing adaptive advance load parameter fine-tuning based on multiple temperature trend prediction curves after control, and constructing an adaptive temperature control model to perform adaptive temperature control operations.

[0006] The present invention acquires real-time thermal imaging images and identifies core heat sources, timely monitors the heat distribution of the power adapter, identifies potential hot spots, generates multiple core heat source area images, accurately locates the heat source position, and provides a basis for subsequent temperature control. Through pixel point temperature value calculation and temperature flow trend analysis, a three-dimensional temperature flow distribution field is constructed to fully understand the heat transfer situation and help predict the temperature change of the heat source. The establishment of the three-dimensional temperature flow distribution field detects temperature anomalies in advance and provides data support for temperature control. The current and voltage parameters of multiple parts are acquired and load calculations are performed. The operating status of each part of the power adapter is monitored in real time, load anomalies are identified, and the load situation of multiple parts is obtained to understand the load situation, providing a basis for temperature control. Data, predict the temperature trend based on the load situation, predict the temperature change of the heat source point in advance, help formulate the corresponding temperature control strategy, build multiple heat source point temperature trend prediction curves to dynamically adjust the temperature control parameters, improve the accuracy of overheating detection, perform overheating temperature detection based on the heat source temperature threshold to respond to temperature anomalies in time, protect the power adapter from overload damage, optimize the temperature control algorithm through the data generated by iterative temperature control simulation, improve the system's adaptability and stability, perform overheating protection operations based on the adaptive temperature control model, adjust the temperature control parameters according to the real-time situation, ensure the safe operation of the power adapter, establish an adaptive temperature control model to quickly respond to temperature anomalies, effectively prevent overheating damage, and improve the reliability and life of the equipment.

[0007] Preferably, step S1 comprises the following steps: Step S11: performing thermal imaging detection on the power adapter in a continuous working state, and extracting a real-time thermal imaging image of the power adapter; Step S12: performing local contrast enhancement processing on the real-time thermal imaging image to generate a local enhanced thermal imaging image; Step S13: performing independent core heat source identification on the local enhanced thermal imaging image to extract multiple core heat source areas; Step S14: performing image region division processing based on multiple core heat source regions to generate multiple core heat source region images.

[0008] The present invention performs thermal imaging detection on the power adapter in a continuous working state, monitors the heat distribution of the device in actual operation in real time, helps identify potential hot spots, extracts real-time thermal imaging images to timely understand the temperature status of the device, and provides data support for subsequent temperature control and prediction. By performing local contrast enhancement processing on the real-time thermal imaging image, local details and features in the image are highlighted and enhanced, the recognition accuracy of the heat source area is improved, and a local enhanced thermal imaging image is generated to more clearly display the heat source area, providing a more reliable data basis for subsequent core heat source identification. By performing core heat source identification on the local enhanced thermal imaging image, multiple core heat source areas existing in the device are accurately identified, which is conducive to targeted temperature control and monitoring. Multiple core heat source areas are extracted to more finely divide the heat source areas, providing more detailed information for subsequent image processing and temperature analysis. Image area division processing is performed based on multiple core heat source areas to generate multiple core heat source area images, further refine the position and range of the heat source, and generate multiple core heat source area images to more accurately locate the heat source area.

[0009] Preferably, step S2 comprises the following steps: Step S21: Calculating the temperature values ​​of pixels of multiple core heat source area images to generate multiple heat source area temperature values; Step S22: performing regional average temperature analysis on multiple heat source region temperature values ​​to obtain heat source region average temperature data; Step S23: performing temperature distribution analysis in the region according to the average temperature data of the heat source region to generate temperature distribution characteristics of each heat source region; Step S24: performing heat source region connectivity inference on multiple core heat source region images to obtain region connectivity data; Step S25: Based on the regional connectivity data, the temperature distribution characteristics of each heat source area are analyzed for temperature flow trend, and a three-dimensional temperature flow distribution field is constructed. The present invention calculates the temperature values ​​of pixels of multiple core heat source area images to obtain the temperature data of each pixel, accurately reflects the temperature distribution of the heat source area, and generates multiple heat source area temperature values, which provide basic data for subsequent analysis and help further understand the temperature state inside the equipment. By performing an average temperature analysis on multiple heat source area temperature values, the overall heat situation of the heat source area is obtained, which provides a basis for overall overheating risk assessment, and the overall overheating situation is discovered by obtaining the average temperature data of the heat source area, which provides guidance for further analysis. By performing temperature distribution analysis on the average temperature data of the heat source area, the temperature distribution situation inside each heat source area is carefully understood, and the temperature state inside the heat source area is determined. The heat accumulation area is located, and the temperature distribution characteristics of each heat source area are generated to provide a basis for the subsequent temperature flow trend analysis, and help design an adaptive overheating control strategy. By inferring the connectivity of the core heat source area image, the connection and association between the heat source areas are identified, and the heat transfer path is understood. The regional connectivity data is obtained to help identify the path and method of heat transfer, and provide support for temperature flow trend analysis. Temperature flow trend analysis based on regional connectivity data reveals the flow of heat between various areas, providing an intuitive reference for overheating control. Constructing a three-dimensional temperature flow distribution field helps understand the dynamic changes of heat transfer and provides a basis for designing intelligent overheating control strategies.

[0010] Preferably, step S25 specifically comprises the following steps: The temperature distribution characteristics of each heat source area are used to identify the temperature differences in multiple areas, and the temperature difference characteristic data of different areas are obtained; Extracting continuous frame core heat source area images based on multiple core heat source area images; Perform time-series fitting on the core heat source area of ​​consecutive frames to construct a heat source area image frame sequence; Based on the image frame sequence of the heat source area, the temperature difference characteristic data of different areas are used to evolve the temperature difference change trend, so as to obtain the temperature difference change trend between the areas; Based on the regional connectivity data, the temperature difference flow is mined for the core heat source area images of consecutive frames, so as to obtain the temperature difference flow direction between heat sources; According to the flow direction of temperature difference between heat sources, the temperature flow trend analysis is performed on the temperature difference change trend between regions to obtain the temperature difference flow trend change characteristics; The three-dimensional temperature distribution is fitted for the temperature difference flow trend change characteristics to construct a three-dimensional temperature flow distribution field.

[0011] The present invention determines the unevenness of heat distribution by identifying the temperature difference in different heat source areas, discovers the hot spots in advance, and obtains the temperature difference characteristic data of different areas to provide a basis for the subsequent temperature difference change trend analysis. By extracting the core heat source area image of continuous frames and fitting the time series changes, the dynamic change information of the heat source area is captured to provide time series data for subsequent analysis, and the heat source area image frame sequence is constructed to track the temperature change of the heat source area, providing support for the temperature flow trend analysis. By performing temperature difference change trend evolution analysis on the temperature difference characteristic data of different areas, the change law of temperature difference over time is understood to help identify the direction of heat transfer, the temperature difference flow direction is mined according to the regional connectivity data, and the temperature difference flow path between heat sources is understood to provide a basis for the temperature flow trend analysis. By performing three-dimensional temperature distribution fitting on the temperature difference flow trend change characteristics, the flow of temperature between different areas is visually displayed to provide an intuitive reference for temperature control, and a three-dimensional temperature flow distribution field is constructed to deeply understand the dynamic characteristics of temperature change, providing support for the design of intelligent overheating control strategies.

[0012] Preferably, step S3 specifically comprises the following steps: Step S31: acquiring current and voltage parameters of multiple parts of the power adapter based on the sensor node; Step S32: performing cycle operation load calculation on the current and voltage parameters of the multiple parts, thereby obtaining cycle operation load parameters of the multiple parts; Step S33: performing load peak identification on the periodic operation load parameters of multiple parts, and extracting the periodic load peak of each part; Step S34: performing transient load change rate analysis on the periodic operation load parameters of multiple parts to generate transient load change characteristics within the period of each part; Step S35: performing load situation evolution on the periodic load peak of each part according to the transient load variation characteristics of each part within the period, thereby obtaining the load situations of multiple parts.

[0013] The present invention obtains the current and voltage parameters of various parts of the power adapter through sensor nodes, monitors the working status of the power supply in real time, provides real-time data support for subsequent analysis, obtains these parameters to understand the power consumption of different parts of the power adapter, provides a basis for power management and optimization, calculates the current and voltage parameters of each part in the cycle, accurately evaluates the load of the power adapter in different time periods, obtains the cycle operation load parameters of multiple parts to help analyze the heat distribution under different load conditions, provides basic data for overheating risk assessment, identifies the load peaks of multiple parts to determine the extreme value of load fluctuations, helps predict the stability of the power adapter under high load conditions, and extracts The cyclic load peak of each part helps to identify potential overheating risk areas and provide a basis for the formulation of control strategies. By analyzing the transient load change rate of multiple parts, the rapid changes in the load of the power adapter can be understood and the overheating risk can be predicted. The transient load change characteristics within the cycle of each part are generated to help identify parts with large load changes and provide support for temperature flow trend analysis. According to the transient load change characteristics of each part, the load situation evolution analysis of the load peak is performed to reveal the load change trend within the cycle and provide a basis for overheating control. The load situation of multiple parts is obtained to predict the working status of the power adapter under different load conditions and provide guidance for the optimization of the adaptive overheating control strategy.

[0014] Preferably, the specific steps of step S4 are: Step S41: based on the load situation of multiple parts, deep mining of temperature-load correlation is performed on the three-dimensional temperature flow distribution field to extract the temperature-load variation law; Step S42: performing multi-time point temperature trend prediction on the three-dimensional temperature flow distribution field based on the temperature-load variation law to obtain temperature trend prediction values ​​at multiple time points; Step S43: locating the heat source area based on the temperature trend prediction values ​​at multiple time points, and marking the temperature trend prediction values ​​of the heat source points; Step S44: performing step-by-step time series temperature fitting on the predicted values ​​of the temperature trend of the heat source points to construct multiple temperature trend prediction curves of the heat source points.

[0015] The present invention conducts in-depth mining of the temperature-load association of the load situation of multiple parts, reveals the complex relationship between temperature and load, helps to understand the propagation law of heat in the power adapter, extracts the temperature-load change law to identify the potential pattern between temperature rise and load change, provides in-depth insights for thermal management strategies, and performs multi-time point temperature trend prediction on the three-dimensional temperature flow distribution field based on the temperature-load change law to achieve the prediction of future temperature changes, help to take thermal management measures in advance, obtain the temperature trend prediction values ​​at multiple time points to determine the hot spot area and predict the trend of temperature change, provide support for the optimization of the control strategy, locate the heat source area according to the temperature trend prediction values ​​at multiple time points, accurately locate the heat source points inside the power adapter, help refined thermal management, mark the temperature trend prediction values ​​of the heat source points to identify potential overheating areas, provide target areas for the implementation of subsequent thermal management measures, perform step-by-step time series temperature fitting on the temperature trend prediction values ​​of the heat source points, construct temperature trend prediction curves of multiple heat source points, provide a basis for the formulation of thermal management strategies, construct multiple temperature trend prediction curves of heat source points to understand the heat change trend of different parts, and provide a reference for real-time temperature monitoring and control.

[0016] Preferably, the specific steps of step S5 are: Step S51: performing overheat temperature detection on a plurality of heat source point temperature trend prediction curves based on a preset power adapter heat source temperature threshold, and marking overheat temperature prediction points; Step S52: extracting the timestamp of the overheat temperature prediction point to generate the timestamp of the overheat prediction point; Step S53: Calculating the front and rear adjustable time windows for the overheat prediction point timestamp to obtain multiple temperature adjustable time windows; Step S54: performing iterative temperature control simulation on multiple temperature controllable time windows to generate multiple temperature control simulation data.

[0017] The present invention detects overheating temperatures on temperature trend prediction curves of multiple heat source points based on a preset power adapter heat source temperature threshold, timely discovers potential overheating risk points, marks overheating temperature prediction points to help determine areas where overheating problems occur, and provides target points for subsequent temperature control. It extracts timestamps from overheating temperature prediction points to generate overheating prediction point timestamps, records the time when the overheating event occurs, and provides a time reference for subsequent analysis and control. It calculates front and back adjustable time windows on the overheating prediction point timestamp to obtain multiple temperature adjustable time windows, determines the time range for temperature control, calculates multiple temperature adjustable time windows to help determine the timeliness of temperature control, and provides guidance for the formulation of temperature control strategies. It iterates temperature control simulations on multiple temperature adjustable time windows to generate multiple temperature control simulation data, evaluates the effects of different control strategies, and generates multiple temperature control simulation data to help simulate temperature change trends under different control schemes, and provides support for selecting the optimal control strategy.

[0018] Preferably, the specific steps of step S6 are: Step S61: re-predicting the temperature trend of a plurality of temperature control simulation data, thereby obtaining a plurality of temperature trend prediction curves after control; Step S62: Adaptively advance load parameter fine-tuning the power adapter based on the multiple regulated temperature trend prediction curves to generate an adaptive advance fine-tuning strategy; Step S63: Perform deep learning decision-making on the adaptive advance fine-tuning strategy and build an adaptive temperature control model to perform adaptive temperature control operations.

[0019] The present invention re-predicts the temperature trend of multiple temperature control simulation data, generates multiple temperature trend prediction curves after control according to different control strategies, evaluates the impact of different control strategies on temperature changes, and obtains multiple temperature trend prediction curves after control to help understand the temperature change trend under different control strategies, providing a basis for selecting the best control strategy, and adaptively advances the load parameters of the power adapter based on the multiple temperature trend prediction curves after control, and fine-tunes the load parameters according to actual conditions to generate an adaptive advance fine-tuning strategy. The adaptive advance fine-tuning strategy adjusts the load parameters according to the predicted temperature trend, further optimizes the control strategy, improves the overheating protection effect, performs deep learning decisions on the adaptive advance fine-tuning strategy, constructs an adaptive temperature control model to perform adaptive temperature control operations, and constructs an adaptive temperature control model to make intelligent decisions based on real-time data, so as to achieve more refined temperature control and improve the adaptability and stability of the system.

[0020] Preferably, the specific steps of step S62 are: Calculate the temperature change response amplitude of multiple temperature trend prediction curves after adjustment to obtain the temperature change amplitude value of each curve; Based on the temperature variation amplitude value of each curve, the curve with the largest temperature variation amplitude value is extracted as the optimal control window curve; Perform optimal control time point analysis on the optimal control window curve to generate the optimal temperature control time point; The power adapter is adaptively and advancely load parameter fine-tuned according to the optimal temperature control time point to generate an adaptive advance fine-tuning strategy.

[0021] The present invention quantifies the degree of influence of different control strategies on temperature by calculating the temperature change amplitude value of each curve, obtains the temperature change amplitude value of each curve to evaluate the effects of different control strategies, provides a reference for selecting the best control scheme, extracts the curve with the largest temperature change amplitude value to determine the control strategy with the most significant impact on temperature change, and uses the optimal control window curve as the optimal control window curve. The optimal control window curve is to select the one with the best effect among multiple strategies to ensure the maximization of the control effect, analyze the optimal control window curve, determine the optimal control time point, execute the temperature control strategy at the most effective time point, generate the optimal temperature control time point, implement control measures at the critical moment, improve the effect of overheating protection, adaptively advance load parameter fine-tuning is performed on the power adapter according to the optimal temperature control time point, adjust the load parameters according to the real-time situation, improve the accuracy and efficiency of the control, generate an adaptive advance fine-tuning strategy to adjust the load parameters according to the optimal time point, achieve more accurate temperature control, and effectively reduce the risk of overheating.

[0022] In this specification, an adaptive temperature control system of a power adapter is provided, which is used to execute the adaptive temperature control method of the power adapter as described above, including: A region division module is used to obtain a real-time thermal imaging image of the power adapter; perform independent core heat source identification on the real-time thermal imaging image, and perform image region division processing to generate multiple core heat source region images; The temperature flow trend module is used to calculate the pixel temperature values ​​of multiple core heat source area images, perform temperature flow trend analysis, and construct a three-dimensional temperature flow distribution field; A load situation evolution module is used to obtain current and voltage parameters of multiple parts of the power adapter based on sensor nodes; perform cycle operation load calculation on the current and voltage parameters of the multiple parts, and perform load situation evolution, so as to obtain the load situation of the multiple parts; The temperature trend prediction module is used to predict the temperature trend of three-dimensional temperature flow distribution field at multiple time points based on the load situation of multiple parts, and to construct temperature trend prediction curves for multiple heat source points; A temperature control simulation module is used to detect overheating temperature of multiple heat source point temperature trend prediction curves based on a preset power adapter heat source temperature threshold, and perform iterative temperature control simulation to generate multiple temperature control simulation data; The adaptive temperature control module is used to obtain multiple temperature trend prediction curves after control based on multiple temperature control simulation data; based on the multiple temperature trend prediction curves after control, adaptive advance load parameter fine-tuning is performed to build an adaptive temperature control model to perform adaptive temperature control operations.

[0023] The present invention can monitor the heat distribution of the power adapter in real time by acquiring real-time thermal imaging images, and promptly discover hot spots. Independent core heat source identification and image area division can effectively separate multiple heat sources in the power adapter, providing an accurate data basis for subsequent temperature analysis. Through pixel point temperature value calculation and temperature flow trend analysis, a three-dimensional temperature flow distribution field inside the power adapter is constructed to help understand the heat propagation law inside the device. The establishment of the three-dimensional temperature flow distribution field identifies hot spot areas, providing a reliable basis for subsequent temperature control. By acquiring current and voltage parameters of multiple parts and performing load situation evolution analysis, the load conditions of various parts of the power adapter can be accurately understood, and the load situation of multiple parts can be obtained to evaluate the operating status of the device, providing a basis for subsequent temperature analysis. The control provides real-time load information support, predicts the temperature trend of load status at multiple time points, predicts the trend of future temperature changes, takes control measures in advance, and constructs a temperature trend prediction curve for heat source points to warn of potential overheating risks and ensure safe operation of equipment. Through iterative temperature control simulation, it can generate multiple temperature control simulation data, evaluate the effects of different control strategies, improve the accuracy and reliability of control, detect overheating temperatures and perform simulated control to optimize control strategies, and respond to equipment overheating risks in a timely manner. Through adaptive advance load parameter fine-tuning and construction of an adaptive temperature control model, intelligent temperature control is achieved based on real-time data to ensure safe operation of equipment. The establishment of an adaptive temperature control model adjusts the control strategy according to actual conditions to improve the adaptability and stability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A schematic flow chart of the steps of a method for adaptively controlling temperature of a power adapter according to the present invention; Figure 2 Detailed implementation flow chart of step S1; Figure 3 Detailed implementation flow chart of step S2; Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0025] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0026] The present application example provides a method and device for adaptive temperature control of a power adapter. The execution subject of the method and device for adaptive temperature control of the power adapter includes but is not limited to: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as the general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0027] See also Figures 1 to 4 The present invention provides an adaptive temperature control method for a power adapter, the adaptive temperature control method for a power adapter comprising the following steps: Step S1: acquiring a real-time thermal imaging image of a power adapter; performing independent core heat source identification on the real-time thermal imaging image, and performing image area division processing to generate a plurality of core heat source area images; Step S2: Calculate the pixel temperature values ​​of multiple core heat source area images, perform temperature flow trend analysis, and construct a three-dimensional temperature flow distribution field; Step S3: obtaining current and voltage parameters of multiple parts of the power adapter based on the sensor node; performing periodic operation load calculation on the current and voltage parameters of the multiple parts, and performing load situation evolution, thereby obtaining the load situation of the multiple parts; Step S4: Based on the load situation of multiple parts, the three-dimensional temperature flow distribution field is subjected to multi-time point temperature trend prediction, and multiple heat source point temperature trend prediction curves are constructed; Step S5: performing overheating temperature detection on the temperature trend prediction curves of multiple heat source points based on the preset power adapter heat source temperature threshold, and performing iterative temperature control simulation to generate multiple temperature control simulation data; Step S6: obtaining multiple temperature trend prediction curves after control based on multiple temperature control simulation data; performing adaptive advance load parameter fine-tuning based on multiple temperature trend prediction curves after control, and constructing an adaptive temperature control model to perform adaptive temperature control operations.

[0028] The present invention acquires real-time thermal imaging images and identifies core heat sources, timely monitors the heat distribution of the power adapter, identifies potential hot spots, generates multiple core heat source area images, accurately locates the heat source position, and provides a basis for subsequent temperature control. Through pixel point temperature value calculation and temperature flow trend analysis, a three-dimensional temperature flow distribution field is constructed to fully understand the heat transfer situation and help predict the temperature change of the heat source. The establishment of the three-dimensional temperature flow distribution field detects temperature anomalies in advance and provides data support for temperature control. The current and voltage parameters of multiple parts are acquired and load calculations are performed. The operating status of each part of the power adapter is monitored in real time, load anomalies are identified, and the load situation of multiple parts is obtained to understand the load situation, providing a basis for temperature control. Data, predict the temperature trend based on the load situation, predict the temperature change of the heat source point in advance, help formulate the corresponding temperature control strategy, build multiple heat source point temperature trend prediction curves to dynamically adjust the temperature control parameters, improve the accuracy of overheating detection, perform overheating temperature detection based on the heat source temperature threshold to respond to temperature anomalies in time, protect the power adapter from overload damage, optimize the temperature control algorithm through the data generated by iterative temperature control simulation, improve the system's adaptability and stability, perform overheating protection operations based on the adaptive temperature control model, adjust the temperature control parameters according to the real-time situation, ensure the safe operation of the power adapter, establish an adaptive temperature control model to quickly respond to temperature anomalies, effectively prevent overheating damage, and improve the reliability and life of the equipment.

[0029] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of a method for adaptively controlling temperature of a power adapter of the present invention. In this example, the steps of the method for adaptively controlling temperature of a power adapter include: Step S1: acquiring a real-time thermal imaging image of a power adapter; performing independent core heat source identification on the real-time thermal imaging image, and performing image area division processing to generate a plurality of core heat source area images; In this embodiment, thermal imaging sensors are arranged at key positions of the power adapter to collect thermal imaging image data inside the power adapter in real time. Image processing and pattern recognition technology are used to analyze the thermal imaging image, identify independent heat source areas inside the power adapter, determine the location, size, temperature characteristics, etc. of these heat sources, and divide the thermal imaging image into multiple independent heat source areas, each area corresponding to a core heat source. According to each heat source area, it is extracted separately to form multiple independent heat source area images, which describe the detailed information of each core heat source inside the power adapter.

[0030] Step S2: Calculate the pixel temperature values ​​of multiple core heat source area images, perform temperature flow trend analysis, and construct a three-dimensional temperature flow distribution field; In this embodiment, for each pixel in each image, the corresponding temperature value is calculated based on the pixel grayscale value and other features to obtain detailed temperature data inside each heat source area, analyze the temperature change pattern of the pixels inside each heat source area, determine the flow direction and trend of heat in these areas, obtain the temperature flow characteristics inside the power adapter, and integrate the temperature data and flow information into a three-dimensional temperature distribution model to form a three-dimensional distribution field that describes the overall temperature flow inside the power adapter.

[0031] Step S3: obtaining current and voltage parameters of multiple parts of the power adapter based on the sensor node; performing periodic operation load calculation on the current and voltage parameters of the multiple parts, and performing load situation evolution, thereby obtaining the load situation of the multiple parts; In this embodiment, parameter monitoring sensors such as current and voltage are arranged in key parts of the power adapter, such as the main control chip and transformer, to collect electrical parameter data of these parts in real time, and calculate the average power load of each part in a certain time period according to the electric power formula, and obtain the operating load of each part in the time period. The load data in multiple time periods are compared and analyzed, and the changing trends and laws of the load of each part over time are studied, so as to obtain the overall load situation evolution characteristics of the power adapter, and comprehensively analyze the results to describe the load situation of each key part inside the power adapter, including the current load level and future changing trends.

[0032] Step S4: Based on the load situation of multiple parts, the three-dimensional temperature flow distribution field is subjected to multi-time point temperature trend prediction, and multiple heat source point temperature trend prediction curves are constructed; In this embodiment, for each heat source point in the three-dimensional temperature distribution field, the changing trend of its temperature value in the future period is predicted to obtain temperature trend prediction curves of multiple heat source points, and the temperature prediction results of each heat source point are integrated to form curves describing the temperature changes of multiple heat sources inside the power adapter. These curves reflect the future temperature change trends of different heat source points.

[0033] Step S5: performing overheating temperature detection on the temperature trend prediction curves of multiple heat source points based on the preset power adapter heat source temperature threshold, and performing iterative temperature control simulation to generate multiple temperature control simulation data; In this embodiment, a reasonable temperature threshold is set, such as 85 degrees Celsius, and these prediction curves are checked one by one to find out which time points may exceed the temperature threshold. These time points where overheating may occur are marked to form a set of overheating temperature prediction points. For each marked overheating temperature prediction point, the corresponding timestamp information is extracted, and the specific time points where overheating may occur are recorded to form a set of overheating prediction point timestamps. For each overheating prediction point timestamp, the time windows within a certain time range before and after the timestamp are calculated, for example, within 5 minutes before and after the prediction point, as the adjustable time window. In this way, multiple temperature adjustable time windows are obtained to provide a basis for subsequent active regulation. By using each temperature adjustable time window, combined with the temperature trend prediction value and load status information obtained in the above steps, different temperature control measures are explored in these time windows through simulation, such as changing the power supply and recording the simulation effects of these temperature control measures in each time window to form a set of temperature control simulation data.

[0034] Step S6: obtaining multiple temperature trend prediction curves after control based on multiple temperature control simulation data; performing adaptive advance load parameter fine-tuning based on multiple temperature trend prediction curves after control, and constructing an adaptive temperature control model to perform adaptive temperature control operations.

[0035] In this embodiment, temperature prediction and analysis are performed again on the generated temperature control simulation data to obtain multiple temperature trend prediction curves inside the power adapter after taking different control measures. The various temperature trend prediction curves obtained by analysis are combined with the obtained load situation characteristics to explore how to actively adjust the power supply parameters of the power adapter according to the upcoming load changes, and formulate a set of adaptive advance load fine-tuning strategies. The obtained adaptive fine-tuning strategies are input into the deep learning algorithm, and an adaptive temperature control model is constructed through training and optimization of a large amount of simulation data. The model can make autonomous decisions and execute optimal temperature control measures based on real-time temperature predictions and load situations, thereby realizing adaptive temperature control of the power adapter.

[0036] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include: Step S11: performing thermal imaging detection on the power adapter in a continuous working state, and extracting a real-time thermal imaging image of the power adapter; Step S12: performing local contrast enhancement processing on the real-time thermal imaging image to generate a local enhanced thermal imaging image; Step S13: performing independent core heat source identification on the local enhanced thermal imaging image to extract multiple core heat source areas; Step S14: performing image region division processing based on multiple core heat source regions to generate multiple core heat source region images.

[0037] In this embodiment, a high-precision infrared thermal imaging camera is used to perform continuous thermal imaging monitoring on the working power adapter, capture a real-time heat distribution image of the entire power adapter, obtain temperature information of each part of the power adapter, adjust and enhance the contrast of the local area of ​​the thermal imaging image, highlight the temperature detail information of the key parts of the power adapter through an image processing algorithm, generate a thermal imaging image with a clearer temperature distribution in the local area, analyze the local enhanced thermal imaging image, identify multiple independent core heat source areas inside the power adapter, and use algorithms such as hot spot area detection and thermal gradient analysis to accurately locate the key heat source position inside the power adapter. According to the identified multiple core heat source areas, the thermal imaging image is divided into local areas, and for each core heat source area, a corresponding local thermal imaging sub-image is generated. These local thermal imaging sub-images better reflect the temperature distribution of each key part inside the power adapter.

[0038] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include: Step S21: Calculating the temperature values ​​of pixels of multiple core heat source area images to generate multiple heat source area temperature values; Step S22: performing regional average temperature analysis on multiple heat source region temperature values ​​to obtain heat source region average temperature data; Step S23: performing temperature distribution analysis in the region according to the average temperature data of the heat source region to generate temperature distribution characteristics of each heat source region; Step S24: performing heat source region connectivity inference on multiple core heat source region images to obtain region connectivity data; Step S25: Based on the regional connectivity data, the temperature distribution characteristics of each heat source area are analyzed for temperature flow trend, and a three-dimensional temperature flow distribution field is constructed. In this embodiment, the temperature information of each pixel in the thermal imaging image is used to calculate the temperature values ​​of each divided heat source area. For each heat source area, the temperature data of all the pixels in the area are extracted as the temperature value of the heat source area. According to the temperature values ​​of each heat source area, the average temperature of each heat source area is calculated. These average temperature data of the heat source areas reflect the overall temperature level of different parts inside the power adapter. The discrete degree and change trend of the temperature value inside each heat source area are analyzed, and characteristic data describing the temperature distribution inside the heat source area are generated. The spatial relative position and temperature correlation between each heat source area are analyzed, and the physical connectivity relationship between the heat source areas is inferred. Data describing the connectivity status of the heat source areas is generated. Combined with the temperature distribution characteristics and regional connectivity, the flow direction and conduction trend of heat inside the power adapter are analyzed, and a three-dimensional temperature flow distribution field model is constructed to characterize the overall heat conduction inside the device.

[0039] In this embodiment, the specific steps of step S25 are: The temperature distribution characteristics of each heat source area are used to identify the temperature differences in multiple areas, and the temperature difference characteristic data of different areas are obtained; Extracting continuous frame core heat source area images based on multiple core heat source area images; Perform time-series fitting on the core heat source area of ​​consecutive frames to construct a heat source area image frame sequence; Based on the image frame sequence of the heat source area, the temperature difference characteristic data of different areas are used to evolve the temperature difference change trend, so as to obtain the temperature difference change trend between the areas; Based on the regional connectivity data, the temperature difference flow is mined for the core heat source area images of consecutive frames, so as to obtain the temperature difference flow direction between heat sources; According to the flow direction of temperature difference between heat sources, the temperature flow trend analysis is performed on the temperature difference change trend between regions to obtain the temperature difference flow trend change characteristics; The three-dimensional temperature distribution is fitted for the temperature difference flow trend change characteristics to construct a three-dimensional temperature flow distribution field.

[0040] In this embodiment, the temperature value of each heat source area is extracted from the previous temperature distribution characteristics, the temperature difference is calculated inside each heat source area, the temperature difference characteristics within the area are identified, and the difference between the maximum value and the minimum value, or the difference between the mean and the temperature of each point, is used to extract the core heat source area images of continuous frames from the thermal imaging video or multiple frames of thermal imaging images. The extracted core heat source area images of continuous frames are organized into a sequence for subsequent analysis and processing. Time series analysis is performed on the continuous heat source area image frames, and the change trend of the heat source area is smoothly fitted using interpolation and other methods to obtain a continuous image frame sequence describing the time series changes of the heat source area. The evolution trend of the temperature difference between different heat source areas over time is analyzed to obtain a description of the temperature difference changes between regions. Based on the characteristic data of the trend, select a suitable flow mining method, such as vector field analysis or streamline map generation. Based on the regional connectivity data, analyze the core heat source area images of continuous frames, extract the temperature difference flow direction, organize the obtained temperature difference flow direction into structured data, select a suitable flow trend analysis method, such as gradient analysis or directionality analysis, analyze the temperature difference change trend between regions according to the extracted temperature difference flow direction, generate the temperature difference flow trend change characteristics, select a suitable three-dimensional fitting method, such as spline interpolation, Kriging interpolation or deep learning model, perform three-dimensional fitting on the temperature difference flow trend change characteristics, construct a three-dimensional temperature flow distribution field, and visualize the generated three-dimensional temperature flow distribution field for analysis and understanding.

[0041] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include: Step S31: acquiring current and voltage parameters of multiple parts of the power adapter based on the sensor node; Step S32: performing cycle operation load calculation on the current and voltage parameters of the multiple parts, thereby obtaining cycle operation load parameters of the multiple parts; Step S33: performing load peak identification on the periodic operation load parameters of multiple parts, and extracting the periodic load peak of each part; Step S34: performing transient load change rate analysis on the periodic operation load parameters of multiple parts to generate transient load change characteristics within the period of each part; Step S35: performing load situation evolution on the periodic load peak of each part according to the transient load variation characteristics of each part within the period, thereby obtaining the load situations of multiple parts.

[0042] In this embodiment, current and voltage sensors are installed at multiple key parts of the power adapter (such as the input end, output end, transformer, etc.), sensor nodes are configured, sampling frequency and data recording interval are set to ensure that changes in current and voltage can be captured, a data acquisition program is started, current and voltage parameters of multiple parts are continuously monitored and recorded, a calculation cycle (such as every second, every minute) is determined, the collected parameters are divided by cycle, the current and voltage data in each cycle are calculated, and the periodic operation load parameters of each part are obtained. A suitable peak recognition algorithm is selected, such as a threshold method, a local maximum detection or a signal processing method. The peak recognition is performed as follows: the periodic operation load parameters of each part are analyzed to extract the load peak value, the change trend and fluctuation of the load of each part within a working cycle are analyzed, the instantaneous derivative of the load change is calculated to reflect the load change rate characteristics, and based on the transient load change characteristics, the periodic load peak value of each part is evolved and analyzed to identify the change trend of the load situation, and the overall situation change of the load of each part within a working cycle is analyzed to obtain characteristic data describing the load situation of each part of the power adapter.

[0043] In this embodiment, the specific steps of step S4 are: Step S41: based on the load situation of multiple parts, deep mining of temperature-load correlation is performed on the three-dimensional temperature flow distribution field to extract the temperature-load variation law; Step S42: performing multi-time point temperature trend prediction on the three-dimensional temperature flow distribution field based on the temperature-load variation law to obtain temperature trend prediction values ​​at multiple time points; Step S43: locating the heat source area based on the temperature trend prediction values ​​at multiple time points, and marking the temperature trend prediction values ​​of the heat source points; Step S44: performing step-by-step time series temperature fitting on the predicted values ​​of the temperature trend of the heat source points to construct multiple temperature trend prediction curves of the heat source points.

[0044] In this embodiment, the selected temperature-load association analysis method, such as regression analysis, principal component analysis or machine learning method, combines temperature data with load status data for deep mining, extracts the variation pattern between temperature and load, and integrates the load variation within a certain period of time in the future into the temperature distribution field model according to the temperature-load variation pattern, and calculates the temperature distribution prediction value inside the power adapter at multiple future time points. Based on the temperature prediction results at multiple time points, the hot spots inside the power adapter are identified, and the temperature trend prediction values ​​of these hot spots are marked. The temperature trend prediction values ​​of each heat source point are gradually fitted with the time series temperature by using interpolation, fitting and other methods, and a trend curve describing the temperature variation of the heat source point over time is constructed, and the temperature trend prediction curves of multiple heat source points are obtained.

[0045] In this embodiment, the specific steps of step S5 are: Step S51: performing overheat temperature detection on a plurality of heat source point temperature trend prediction curves based on a preset power adapter heat source temperature threshold, and marking overheat temperature prediction points; Step S52: extracting the timestamp of the overheat temperature prediction point to generate the timestamp of the overheat prediction point; Step S53: Calculating the front and rear adjustable time windows for the overheat prediction point timestamp to obtain multiple temperature adjustable time windows; Step S54: performing iterative temperature control simulation on multiple temperature controllable time windows to generate multiple temperature control simulation data.

[0046] In this embodiment, according to the working specifications and safety standards of the equipment, the heat source temperature threshold of the power adapter is preset, the temperature trend prediction curve data of multiple heat source points are collected, the temperature trend prediction curve of each heat source point is traversed, and its temperature value is compared with the set temperature threshold. For the temperature prediction points exceeding the set threshold, they are marked, and the specific values ​​and positions of these overheating temperature prediction points are recorded. The corresponding timestamp information is extracted from the marked overheating temperature prediction points, and the extracted timestamps are sorted into a list or an array to form an overheating prediction point timestamp data set. The length of the time window (such as 5 minutes, 10 minutes, etc.) is set according to business needs. For the timestamp of each overheating prediction point, the adjustable time windows before and after are calculated, and the start and end time of each window are determined. A suitable temperature control simulation model is selected, such as a PID control algorithm, a fuzzy control or other temperature control algorithm. The simulation parameters (such as the target temperature and the control rate) are set according to actual needs. The temperature control simulation is iteratively performed on each temperature adjustable time window to generate corresponding temperature control simulation data.

[0047] In this embodiment, the specific steps of step S6 are: Step S61: re-predicting the temperature trend of a plurality of temperature control simulation data, thereby obtaining a plurality of temperature trend prediction curves after control; Step S62: Adaptively advance load parameter fine-tuning the power adapter based on the multiple regulated temperature trend prediction curves to generate an adaptive advance fine-tuning strategy; Step S63: Perform deep learning decision-making on the adaptive advance fine-tuning strategy and build an adaptive temperature control model to perform adaptive temperature control operations.

[0048] In this embodiment, a suitable re-prediction model is selected, such as time series analysis (ARIMA), a machine learning model (such as random forest, support vector machine) or a deep learning model (such as LSTM), and the selected model is trained using temperature control simulation data, and the model parameters are adjusted to optimize the prediction performance. Based on the trained model, the temperature control simulation data is re-predicted to generate multiple temperature trend prediction curves after control, and the load parameters that need to be fine-tuned (such as current, voltage, power, etc.) are determined, and the corresponding adjustment range is set. A suitable adaptive adjustment algorithm is selected, such as adaptive control, fuzzy control or reinforcement learning. Based on the temperature trend prediction curve after control, adaptive advance load parameter fine-tuning is performed, and an adaptive fine-tuning strategy is generated. The adaptive fine-tuning strategy is input into the deep learning algorithm. Through training and optimization of a large amount of simulation data, an adaptive temperature control model is constructed. The model autonomously decides and executes the optimal temperature control measures based on real-time temperature prediction and load status, thereby realizing adaptive temperature control of the power adapter.

[0049] In this embodiment, the specific steps of step S62 are: Calculate the temperature change response amplitude of multiple temperature trend prediction curves after adjustment to obtain the temperature change amplitude value of each curve; Based on the temperature variation amplitude value of each curve, the curve with the largest temperature variation amplitude value is extracted as the optimal control window curve; Perform optimal control time point analysis on the optimal control window curve to generate the optimal temperature control time point; The power adapter is adaptively and advancely load parameter fine-tuned according to the optimal temperature control time point to generate an adaptive advance fine-tuning strategy.

[0050] In this embodiment, according to a plurality of adjusted temperature trend prediction curves, for each curve, the temperature change amplitude from the current moment to the end of the prediction time is calculated to obtain the temperature change amplitude value corresponding to each curve, and the temperature change amplitude value of each curve is compared. The temperature change amplitude values ​​of the calculated curves are selected, and the curve with the largest temperature change amplitude value is selected, and the curve is determined as the optimal temperature control time window. A suitable time point analysis method is selected, such as peak detection, key point identification or slope analysis. In the optimal control window curve, the time point with the greatest impact on the temperature change is identified, which is usually the peak or inflection point of the curve, and the time point with the most drastic temperature change on the curve is identified, and this time point is determined as the optimal temperature control time point. According to the optimal temperature control time point, a corresponding advanced load parameter fine-tuning strategy is designed, considering how to adjust the load to achieve better temperature control, and the load parameters of the power adapter are fine-tuned to ensure that they are adjusted before the optimal control time point to respond to the upcoming temperature change, and a set of adaptive advanced load parameter fine-tuning strategies for this time point are formulated. The strategy ensures that the power supply parameters of the power adapter are adjusted in advance at the most critical moment to cope with the upcoming temperature change.

[0051] In this embodiment, an adaptive temperature control system of a power adapter is provided, which is used to execute the adaptive temperature control method of the power adapter as described above, including: A region division module is used to obtain a real-time thermal imaging image of the power adapter; perform independent core heat source identification on the real-time thermal imaging image, and perform image region division processing to generate multiple core heat source region images; The temperature flow trend module is used to calculate the pixel temperature values ​​of multiple core heat source area images, perform temperature flow trend analysis, and construct a three-dimensional temperature flow distribution field; A load situation evolution module is used to obtain current and voltage parameters of multiple parts of the power adapter based on sensor nodes; perform cycle operation load calculation on the current and voltage parameters of the multiple parts, and perform load situation evolution, so as to obtain the load situation of the multiple parts; The temperature trend prediction module is used to predict the temperature trend of three-dimensional temperature flow distribution field at multiple time points based on the load situation of multiple parts, and to construct temperature trend prediction curves for multiple heat source points; A temperature control simulation module is used to detect overheating temperature of multiple heat source point temperature trend prediction curves based on a preset power adapter heat source temperature threshold, and perform iterative temperature control simulation to generate multiple temperature control simulation data; The adaptive temperature control module is used to obtain multiple temperature trend prediction curves after control based on multiple temperature control simulation data; based on the multiple temperature trend prediction curves after control, adaptive advance load parameter fine-tuning is performed to build an adaptive temperature control model to perform adaptive temperature control operations.

[0052] The present invention can monitor the heat distribution of the power adapter in real time by acquiring real-time thermal imaging images, and promptly discover hot spots. Independent core heat source identification and image area division can effectively separate multiple heat sources in the power adapter, providing an accurate data basis for subsequent temperature analysis. Through pixel point temperature value calculation and temperature flow trend analysis, a three-dimensional temperature flow distribution field inside the power adapter is constructed to help understand the heat propagation law inside the device. The establishment of the three-dimensional temperature flow distribution field identifies hot spot areas, providing a reliable basis for subsequent temperature control. By acquiring current and voltage parameters of multiple parts and performing load situation evolution analysis, the load conditions of various parts of the power adapter can be accurately understood, and the load situation of multiple parts can be obtained to evaluate the operating status of the device, providing a basis for subsequent temperature analysis. The control provides real-time load information support, predicts the temperature trend of load status at multiple time points, predicts the trend of future temperature changes, takes control measures in advance, and constructs a temperature trend prediction curve for heat source points to warn of potential overheating risks and ensure safe operation of equipment. Through iterative temperature control simulation, it can generate multiple temperature control simulation data, evaluate the effects of different control strategies, improve the accuracy and reliability of control, detect overheating temperatures and perform simulated control to optimize control strategies, and respond to equipment overheating risks in a timely manner. Through adaptive advance load parameter fine-tuning and construction of an adaptive temperature control model, intelligent temperature control is achieved based on real-time data to ensure safe operation of equipment. The establishment of an adaptive temperature control model adjusts the control strategy according to actual conditions to improve the adaptability and stability of the system.

[0053] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0054] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for adaptive temperature control of a power adapter, characterized in that: The following steps are involved: Step S1: obtaining a real-time thermal imaging image of the power adapter; Performing independent core heat source identification on the real-time thermal imaging image, and performing image area division processing to generate multiple core heat source area images; Step S2: Calculate the pixel temperature values ​​of multiple core heat source area images, perform temperature flow trend analysis, and construct a three-dimensional temperature flow distribution field; Step S3: obtaining current and voltage parameters of multiple parts of the power adapter based on the sensor node; performing periodic operation load calculation on the current and voltage parameters of the multiple parts, and performing load situation evolution, thereby obtaining the load situation of the multiple parts; Step S4: Based on the load situation of multiple parts, the three-dimensional temperature flow distribution field is subjected to multi-time point temperature trend prediction, and multiple heat source point temperature trend prediction curves are constructed; Step S5: performing overheating temperature detection on the temperature trend prediction curves of multiple heat source points based on the preset power adapter heat source temperature threshold, and performing iterative temperature control simulation to generate multiple temperature control simulation data; Step S6: obtaining a plurality of temperature trend prediction curves after control based on a plurality of temperature control simulation data; Based on multiple temperature trend prediction curves after control, adaptive advance load parameter fine-tuning is performed to build an adaptive temperature control model to perform adaptive temperature control operations.

2. The adaptive temperature control method of the power adapter according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: performing thermal imaging detection on the power adapter in a continuous working state, and extracting a real-time thermal imaging image of the power adapter; Step S12: performing local contrast enhancement processing on the real-time thermal imaging image to generate a local enhanced thermal imaging image; Step S13: performing independent core heat source identification on the local enhanced thermal imaging image to extract multiple core heat source areas; Step S14: performing image region division processing based on multiple core heat source regions to generate multiple core heat source region images.

3. The adaptive temperature control method of a power adapter according to claim 1, characterized in that: The specific steps of step S2 are: Step S21: Calculating the temperature values ​​of pixels of multiple core heat source area images to generate multiple heat source area temperature values; Step S22: performing regional average temperature analysis on multiple heat source region temperature values ​​to obtain heat source region average temperature data; Step S23: performing temperature distribution analysis in the region according to the average temperature data of the heat source region to generate temperature distribution characteristics of each heat source region; Step S24: performing heat source region connectivity inference on multiple core heat source region images to obtain region connectivity data; Step S25: Based on the regional connectivity data, the temperature distribution characteristics of each heat source area are analyzed for temperature flow trend, and a three-dimensional temperature flow distribution field is constructed.

4. The adaptive temperature control method of the power adapter according to claim 3, characterized in that: The specific steps of step S25 are: The temperature distribution characteristics of each heat source area are used to identify the temperature differences in multiple areas, and the temperature difference characteristic data of different areas are obtained; Extracting continuous frame core heat source area images based on multiple core heat source area images; Perform time-series fitting on the core heat source area of ​​consecutive frames to construct a heat source area image frame sequence; Based on the image frame sequence of the heat source area, the temperature difference characteristic data of different areas are used to evolve the temperature difference change trend, so as to obtain the temperature difference change trend between the areas; Based on the regional connectivity data, the temperature difference flow is mined for the core heat source area images of consecutive frames, so as to obtain the temperature difference flow direction between heat sources; According to the flow direction of temperature difference between heat sources, the temperature flow trend analysis is performed on the temperature difference change trend between regions to obtain the temperature difference flow trend change characteristics; The three-dimensional temperature distribution is fitted for the temperature difference flow trend change characteristics to construct a three-dimensional temperature flow distribution field.

5. The adaptive temperature control method of a power adapter according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: acquiring current and voltage parameters of multiple parts of the power adapter based on the sensor node; Step S32: performing cycle operation load calculation on the current and voltage parameters of the multiple parts, thereby obtaining cycle operation load parameters of the multiple parts; Step S33: performing load peak identification on the periodic operation load parameters of multiple parts, and extracting the periodic load peak of each part; Step S34: performing transient load change rate analysis on the periodic operation load parameters of multiple parts to generate transient load change characteristics within the period of each part; Step S35: performing load situation evolution on the periodic load peak of each part according to the transient load variation characteristics of each part within the period, thereby obtaining the load situations of multiple parts.

6. The adaptive temperature control method of a power adapter according to claim 1, characterized in that: The specific steps of step S4 are: Step S41: based on the load situation of multiple parts, deep mining of temperature-load correlation is performed on the three-dimensional temperature flow distribution field to extract the temperature-load variation law; Step S42: performing multi-time point temperature trend prediction on the three-dimensional temperature flow distribution field based on the temperature-load variation law to obtain temperature trend prediction values ​​at multiple time points; Step S43: locating the heat source area based on the temperature trend prediction values ​​at multiple time points, and marking the temperature trend prediction values ​​of the heat source points; Step S44: performing step-by-step time series temperature fitting on the predicted values ​​of the temperature trend of the heat source points to construct multiple temperature trend prediction curves of the heat source points.

7. The adaptive temperature control method of a power adapter according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: performing overheat temperature detection on a plurality of heat source point temperature trend prediction curves based on a preset power adapter heat source temperature threshold, and marking overheat temperature prediction points; Step S52: extracting the timestamp of the overheat temperature prediction point to generate the timestamp of the overheat prediction point; Step S53: Calculating the front and rear adjustable time windows for the overheat prediction point timestamp to obtain multiple temperature adjustable time windows; Step S54: performing iterative temperature control simulation on multiple temperature controllable time windows to generate multiple temperature control simulation data.

8. The adaptive temperature control method of a power adapter according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: re-predicting the temperature trend of a plurality of temperature control simulation data, thereby obtaining a plurality of temperature trend prediction curves after control; Step S62: Adaptively advance load parameter fine-tuning the power adapter based on the multiple regulated temperature trend prediction curves to generate an adaptive advance fine-tuning strategy; Step S63: Perform deep learning decision-making on the adaptive advance fine-tuning strategy and build an adaptive temperature control model to perform adaptive temperature control operations.

9. The method for adaptive temperature control of a power adapter according to claim 8, characterized in that: The specific steps of step S62 are: Calculate the temperature change response amplitude of multiple temperature trend prediction curves after adjustment to obtain the temperature change amplitude value of each curve; Based on the temperature variation amplitude value of each curve, the curve with the largest temperature variation amplitude value is extracted as the optimal control window curve; Perform optimal control time point analysis on the optimal control window curve to generate the optimal temperature control time point; The power adapter is adaptively and advancely load parameter fine-tuned according to the optimal temperature control time point to generate an adaptive advance fine-tuning strategy.

10. An adaptive temperature control device for a power adapter, characterized in that: The method for performing the adaptive temperature control of the power adapter according to claim 1 comprises: A region division module is used to obtain a real-time thermal imaging image of the power adapter; perform independent core heat source identification on the real-time thermal imaging image, and perform image region division processing to generate multiple core heat source region images; The temperature flow trend module is used to calculate the pixel temperature values ​​of multiple core heat source area images, perform temperature flow trend analysis, and construct a three-dimensional temperature flow distribution field; A load situation evolution module is used to obtain current and voltage parameters of multiple parts of the power adapter based on sensor nodes; perform cycle operation load calculation on the current and voltage parameters of the multiple parts, and perform load situation evolution, so as to obtain the load situation of the multiple parts; The temperature trend prediction module is used to predict the temperature trend of three-dimensional temperature flow distribution field at multiple time points based on the load situation of multiple parts, and to construct temperature trend prediction curves for multiple heat source points; A temperature control simulation module is used to detect overheating temperature of multiple heat source point temperature trend prediction curves based on a preset power adapter heat source temperature threshold, and perform iterative temperature control simulation to generate multiple temperature control simulation data; The adaptive temperature control module is used to obtain multiple temperature trend prediction curves after control based on multiple temperature control simulation data; based on the multiple temperature trend prediction curves after control, adaptive advance load parameter fine-tuning is performed to build an adaptive temperature control model to perform adaptive temperature control operations.

Images