Electronic component heat insulation sheath multi-parameter monitoring and heat diffusion inhibition linkage system

Abstract

The invention relates to the technical field of thermal safety protection and temperature control of electronic equipment, and particularly discloses a multi-parameter monitoring and thermal diffusion suppression linkage system for a thermal insulation sheath of an electronic component. According to the invention, thermal field distribution, pressure change and heat flow rate data in a thermal insulation sheath are synchronously collected in real time, a multi-dimensional thermal state vector is generated through time sequence fusion and is input into a thermal anomaly judgment model to comprehensively evaluate a coupling relationship, and a linkage control instruction is output to drive an execution module to execute a cooperative inhibition action in a corresponding thermal diffusion path. The method solves the problems of response time delay and difficulty in rapid intervention at the initial stage of thermal runaway caused by insufficient monitoring dimension of traditional off-line detection or single temperature sensing and lack of cooperation of monitoring and suppression, realizes rapid linkage response of thermal anomaly recognition and suppression action, timely blocks a thermal diffusion path, avoids accumulation and spreading of heat, and improves the reliability of thermal anomaly recognition and suppression. And the thermal safety protection capability and the stable operation guarantee level of the electronic component and the whole system are improved.

Description

Technical Field

[0001] This invention relates to the field of thermal safety protection and temperature control technology for electronic equipment, and in particular to a multi-parameter monitoring and thermal diffusion suppression linkage system for thermal insulation sheaths of electronic components. Background Technology

[0002] As electronic devices evolve towards high-density integration and high power, the thermal insulation jackets of electronic components, as key components in thermal management, face higher demands on their safety and reliability. Existing technologies primarily rely on offline detection or single temperature sensors for status monitoring, limiting the monitoring dimensions and making it difficult to comprehensively reflect key parameters such as the internal thermal field distribution, pressure changes, and heat flux rates. Furthermore, the lack of a coordinated linkage mechanism between the monitoring unit and the thermal suppression actuator leads to a general time delay between thermal anomaly identification and suppression response, failing to promptly block heat diffusion paths. This fragmented architecture of monitoring and suppression measures makes rapid intervention difficult in the early stages of thermal runaway, easily causing heat accumulation and spread, thereby threatening the stable operation of electronic components and the entire system. Therefore, there is an urgent need to improve thermal safety protection capabilities through multi-parameter fusion sensing and coordinated control technologies.

[0003] Therefore, there is an urgent need to provide a technical solution to address the above problems. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides a multi-parameter monitoring and thermal diffusion suppression linkage system for electronic component thermal insulation sheaths. The technical solution of this system is as follows: The multi-parameter sensing module is used to collect in real time the thermal field distribution parameters, internal pressure parameters, and heat flow rate parameters inside the thermal insulation sheath of electronic components. The data acquisition and monitoring control module is used to perform time-series fusion of the thermal field distribution parameters, the internal pressure parameters, and the heat flow rate parameters to generate a multi-dimensional fused thermal state vector characterizing the real-time thermal state of the insulation sheath. The multi-dimensional fused thermal state vector is input into a preset thermal anomaly determination model. The thermal anomaly determination model comprehensively evaluates the coupling relationship between the thermal field gradient, pressure change trend, and heat flow anomaly rate to determine the thermal anomaly state. When the thermal anomaly state is determined, the thermal anomaly determination model outputs a linkage control command containing the suppression position and suppression intensity. The heat diffusion suppression execution module is used to perform a coordinated suppression action on the corresponding heat diffusion path of the thermal insulation sleeve according to the suppression position and suppression intensity in the linkage control command.

[0005] The technical solution of this invention collects data on the thermal field distribution, pressure changes, and heat flow rate inside the thermal insulation sheath in real time, fuses them in a time sequence to generate a multi-dimensional thermal state vector, and inputs it into a thermal anomaly judgment model to comprehensively evaluate the coupling relationship. It then outputs a linkage control command to drive the execution module to perform coordinated suppression actions on the corresponding thermal diffusion path. This solves the problems of insufficient dimensions in traditional offline detection or single temperature sensor monitoring, lack of coordination between monitoring and suppression leading to response delays, and difficulty in rapid intervention in the early stages of thermal runaway. It achieves rapid linkage response between thermal anomaly identification and suppression actions, timely blocks the thermal diffusion path, avoids the accumulation and spread of heat, and improves the thermal safety protection capability and stable operation guarantee level of electronic components and the entire system.

[0006] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0007] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0008] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 This is a schematic diagram of an embodiment of the multi-parameter monitoring and thermal diffusion suppression linkage system for electronic component thermal insulation sheaths according to the present invention. Detailed Implementation

[0009] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0010] Figure 1 This diagram illustrates a structural schematic of an embodiment of a multi-parameter monitoring and thermal diffusion suppression linkage system for electronic component thermal insulation sheaths provided by the present invention. Figure 1 As shown, the system includes: The multi-parameter sensing module 110 is used to collect in real time the thermal field distribution parameters, internal pressure parameters, and heat flow rate parameters inside the thermal insulation sheath of electronic components.

[0011] Electronic components refer to physical devices that constitute the basic functional units of electronic circuits or equipment; for example, a high-power processor mounted on a main circuit board. Thermal insulation refers to an encapsulation structure that wraps around electronic components to impede heat transfer; for example, a sleeve-like structure made of aerogel composite material that tightly encloses a high-power processor. Thermal field distribution parameters refer to a set of parameters describing the temperature values ​​at various points within the thermal insulation casing and their relative relationships; for example, a set of measurement data reflecting temperatures of 85℃, 72℃, and 61℃ at 1cm, 2cm, and 3cm above the processor core, respectively. Internal pressure parameters refer to a physical quantity characterizing the pressure of a gas or medium in the closed or semi-closed space inside the thermal insulation casing; for example, a pressure reading of 102.5 kPa generated by the thermal expansion of air inside the casing due to processor heat. Heat flow rate parameters refer to a physical quantity characterizing the amount of heat energy passing vertically through a set cross-section inside the thermal insulation casing per unit time; for example, the amount of heat energy passing through 1cm directly above the processor in 1 second. 2 The heat capacity of the cross section is 15J, which means the heat flux rate is 15W.

[0012] The data acquisition and monitoring control module 120 is used to perform time-series fusion of the thermal field distribution parameters, the internal pressure parameters, and the heat flow rate parameters to generate a multi-dimensional fused thermal state vector characterizing the real-time thermal state of the insulation sheath. The multi-dimensional fused thermal state vector is input into a preset thermal anomaly determination model. The thermal anomaly determination model comprehensively evaluates the coupling relationship between the thermal field gradient, pressure change trend, and heat flow anomaly rate to determine the thermal anomaly state. When the thermal anomaly state is determined, the thermal anomaly determination model outputs a linkage control command containing the suppression position and suppression intensity.

[0013] The multidimensional fused thermal state vector refers to a mathematical vector that comprehensively describes the instantaneous thermal state of the insulation sheath by combining feature values ​​extracted from different physical parameters in a predetermined order at the same sampling moment; for example, a vector [2.5, 0.3, 18] containing three elements: "thermal gradient 2.5℃ / cm", "pressure change rate 0.3kPa / s", and "instantaneous heat flux 18W". The thermal anomaly judgment model refers to a pre-defined algorithm or rule program used to analyze the input thermal state information and determine whether it exceeds the safe range; for example, a software algorithm that receives the multidimensional fused thermal state vector as input and outputs a "normal" or "abnormal" judgment result through internal calculation rules. The thermal gradient refers to the rate of change of the internal temperature of the insulation sheath in the spatial direction; for example, the temperature decreases by an average of 12℃ for every 1cm away from the processor surface. The pressure change trend refers to the dynamic characteristics of the internal pressure parameters of the insulation sheath evolving over time; for example, the internal pressure continuously increases from 101.0kPa to 103.0kPa over three consecutive sampling periods. An abnormal heat flux rate refers to a heat flux rate value or change characteristic that exceeds the preset normal range; for example, a normal heat flux rate is usually between 10W and 20W, while a currently measured instantaneous 25W is considered an abnormal rate. Coupling relationship refers to the interaction and correlation mechanism between multiple physical parameters such as thermal field distribution, internal pressure, and heat flux rate; for example, a sudden increase in processor temperature may lead to an increase in internal pressure of the insulation jacket, and simultaneously, a rapid increase in heat flux rate. A thermal anomaly state refers to a state indicator determined by the thermal anomaly judgment model, indicating that the internal thermal behavior of the insulation jacket has deviated from the safe operating range; for example, after comprehensive analysis, the model determines that the current thermal state has a risk of runaway and outputs a "thermal anomaly" flag. A linkage control command refers to a digital command containing specific execution information generated by the thermal anomaly judgment model after determining a thermal anomaly state; for example, a data packet containing the command "Initiate suppression at coordinates (x1, y1), intensity level 5".

[0014] The heat diffusion suppression execution module 130 is used to perform a coordinated suppression action on the corresponding heat diffusion path of the heat insulation sleeve according to the suppression position and suppression intensity in the linkage control command.

[0015] Here, "suppression location" refers to the specific spatial coordinates specified in the linkage control command where heat diffusion suppression action needs to be implemented inside the thermal insulation jacket; for example, the three-dimensional coordinates corresponding to the point of maximum thermal gradient (10mm, 5mm, 2mm). "Suppression intensity" refers to the numerical level or physical quantity quantified in the linkage control command, representing the required force for heat diffusion suppression action; for example, an integer level ranging from 1 to 10, with larger values ​​indicating higher cooling power. "Heat diffusion path" refers to the main direction or channel of heat transfer from high-temperature to low-temperature regions inside the thermal insulation jacket; for example, heat is conducted outward from the processor core area along a vertically upward direction through the jacket material. "Coordinated suppression action" refers to the coordinated physical intervention operation performed by multiple execution units at specific locations with specific intensities according to the same command; for example, three micro-cooling chips distributed along the heat diffusion path are simultaneously activated and operate at 75% of their maximum power.

[0016] The technical solution of this embodiment collects data on the thermal field distribution, pressure changes, and heat flow rate inside the thermal insulation sheath in real time, fuses them in a time sequence to generate a multi-dimensional thermal state vector, and inputs it into a thermal anomaly judgment model to comprehensively evaluate the coupling relationship. It then outputs a linkage control command to drive the execution module to perform coordinated suppression actions on the corresponding thermal diffusion path. This solves the problems of insufficient dimensions of traditional offline detection or single temperature sensor monitoring, lack of coordination between monitoring and suppression leading to response delays, and difficulty in rapid intervention in the early stage of thermal runaway. It realizes rapid linkage response of thermal anomaly identification and suppression actions, timely blocks the thermal diffusion path, avoids the accumulation and spread of heat, and improves the thermal safety protection capability and stable operation guarantee level of electronic components and the entire system.

[0017] In an alternative embodiment, the multi-parameter sensing module 110 is specifically used for: By deploying a distributed temperature sensor array inside the thermal insulation sheath, temperature data at multiple spatial locations inside the thermal insulation sheath are collected synchronously, and the thermal field distribution parameters are calculated and generated based on the temperature data at these multiple spatial locations.

[0018] In this context, a distributed temperature sensor array refers to a collection of temperature sensors arranged in a spatially ordered manner at multiple points inside a thermal insulation sheath; for example, nine miniature temperature sensors arranged in a grid pattern with 5mm intervals inside the sheath above the processor. A spatial location point refers to the specific three-dimensional coordinates of each sensor in the distributed temperature sensor array; for example, a measurement point with coordinates (0mm, 0mm, 1mm). Temperature data refers to the instantaneous temperature values ​​collected by the distributed temperature sensor array at its respective spatial location points; for example, at a certain moment, the nine sensors read nine temperature values: 80.1℃, 78.5℃, 76.0℃, etc.

[0019] By using micro-pressure sensors installed inside the thermal insulation sheath, the environmental pressure data inside the thermal insulation sheath is collected synchronously and used as the internal pressure parameter.

[0020] Among them, a micro-pressure sensor refers to a sensing device used to precisely measure minute pressure changes inside the thermal insulation sheath; for example, a thin-film piezoresistive sensor with a range of 90 kPa to 110 kPa and an accuracy of 0.1 kPa. Ambient pressure data refers to the numerical value characterizing the overall air pressure inside the thermal insulation sheath, collected by the micro-pressure sensor; for example, a pressure reading of 101.3 kPa in real time.

[0021] By using heat flux sensors installed inside the heat insulation sheath, heat power data flowing through a designated cross-section inside the heat insulation sheath is collected synchronously and used as the heat flow rate parameter.

[0022] A heat flux sensor refers to a sensing device used to directly measure the heat energy passing through a unit area per unit time; for example, a sensor based on the thermopile principle attached to a specific cross-section of the inner wall of the insulation jacket. A specified cross-section refers to a predefined virtual planar region inside the insulation jacket used to monitor heat flow; for example, a 1cm² area parallel to the processor surface and 2mm away from the surface. 2 The circular area. Thermal power data refers to the numerical value obtained by a heat flux sensor, representing the instantaneous thermal power passing through a specified cross section; for example, the sensor outputs a digital quantity corresponding to a voltage signal indicating that the current heat flux is 16.5W.

[0023] In the above-mentioned optional methods, the coordinated deployment of distributed temperature sensor arrays, micro-pressure sensors and heat flux sensors further enables the synchronous and accurate acquisition of internal thermal field distribution parameters, internal pressure parameters and heat flow rate parameters of the thermal insulation jacket, providing multi-dimensional basic data support for subsequent thermal state assessment.

[0024] In an alternative embodiment, the data acquisition and monitoring control module 120 is specifically used for: Based on a unified time reference, the synchronously acquired thermal field distribution parameters, internal pressure parameters, and heat flow rate parameters are aligned within the same sampling time window.

[0025] The sampling time window refers to a specific time period used for the synchronous acquisition and alignment of data from multiple sensors; for example, a time period lasting 100ms starting from 10:00:00:000 on the system clock.

[0026] Spatial thermal field gradient features are extracted from the aligned thermal field distribution parameters, temporal pressure change rate features are extracted from the aligned internal pressure parameters, and instantaneous heat flux values ​​are extracted from the aligned heat flux rate parameters.

[0027] Among them, the spatial thermal field gradient characteristic refers to the feature value extracted from the thermal field distribution parameters to quantify the severity of spatial temperature changes; for example, the average gradient value "13℃ / cm" obtained by differential calculation of temperature data from multiple spatial locations. The temporal pressure change rate characteristic refers to the feature value extracted from the internal pressure parameters to quantify how quickly the pressure changes over time; for example, the change rate "0.15kPa / s" obtained by differentiating the pressure data from two consecutive sampling windows. The instantaneous heat flux value refers to the feature value directly obtained from the heat flux rate parameter, characterizing the magnitude of the heat flux at the current sampling moment; for example, the value "17.8W" output by the heat flux sensor within the current sampling time window.

[0028] The spatial thermal field gradient characteristics, the temporal pressure change rate characteristics, and the instantaneous heat flux value are combined in a preset dimensional order to form a multidimensional fused thermal state vector that characterizes the comprehensive thermal state of the thermal insulation sheath within the sampling time window.

[0029] The preset dimensional order refers to the pre-defined arrangement of different feature values ​​to construct a vector; for example, the first dimension of the vector is the spatial thermal field gradient feature, the second dimension is the temporal pressure change rate feature, and the third dimension is the instantaneous heat flux value. The comprehensive thermal state refers to the overall thermal behavior of the insulation sheath, characterized by a multi-dimensional fused thermal state vector, encompassing information from multiple physical fields; for example, the vector [14.2, 0.2, 19.5] represents a state of "high thermal gradient, slow pressure increase, and high heat output".

[0030] In the above-mentioned optional methods, the three types of parameters are further aligned in time based on a unified time reference, and the spatial thermal field gradient features, time-series pressure change rate features and instantaneous heat flux values ​​are extracted respectively. They are then combined according to preset dimensions to form a multi-dimensional fused thermal state vector, realizing a structured and unified representation of multi-physical quantity information.

[0031] In an alternative embodiment, the data acquisition and monitoring control module 120 is specifically used for: The multidimensional fused thermal state vector is input into the thermal anomaly determination model. The thermal anomaly determination model analyzes the spatial thermal field gradient features, the temporal pressure change rate features, and the instantaneous heat flux value in the multidimensional fused thermal state vector. Based on a preset coupling weight coefficient, the spatial thermal field gradient features, the temporal pressure change rate features, and the instantaneous heat flux value are weighted and fused to generate a comprehensive anomaly score. When the comprehensive anomaly score exceeds a preset anomaly threshold, the thermal anomaly state is determined to have occurred.

[0032] The preset coupling weight coefficients refer to parameters pre-set in the thermal anomaly determination model to adjust the contribution of different features to the final determination result; for example, the weight parameters α, β, and γ assigned to the spatial thermal field gradient feature, the temporal pressure change rate feature, and the instantaneous heat flux value. The comprehensive anomaly score refers to the comprehensive numerical value output by the thermal anomaly determination model after calculation, used to quantify the degree of thermal anomaly; for example, a score of "85.6" calculated by the model based on the input vector and weights. The preset anomaly threshold refers to the pre-set numerical boundary used to compare with the comprehensive anomaly score to determine whether a thermal anomaly state has occurred; for example, setting the threshold to "75.0", a determination is triggered when the comprehensive anomaly score exceeds 75.0.

[0033] In the above-mentioned optional methods, a multi-dimensional fused thermal state vector is further input into the thermal anomaly determination model. Based on the preset coupling weight coefficient, the three features are weighted and fused to generate a comprehensive anomaly score. The thermal anomaly state is objectively determined by threshold comparison, which improves the quantitative accuracy and configurability of anomaly detection.

[0034] In one alternative approach, the thermal anomaly determination model is specifically used for: Based on the historical operating data of the thermal insulation sleeve, the baseline weights corresponding to the spatial thermal field gradient features, the temporal pressure change rate features, and the instantaneous heat flux values ​​are established through offline training, and the baseline weights are used as the initial values ​​of the dynamic coupling weight coefficients.

[0035] Historical operational data refers to the collection and storage of multi-parameter sensing data during the system's previous normal operation; for example, all thermal field, pressure, and heat flow data recorded by the system under normal operating conditions over the past month. Offline training refers to the process of learning and optimizing the parameters in the thermal anomaly judgment model using historical operational data without participating in real-time control; for example, using one month's historical data to adjust the model's coupling weight coefficients through machine learning algorithms. Baseline weights refer to the initial reference values ​​of the coupling weight coefficients corresponding to each feature, preliminarily determined through the offline training process; for example, the initial weights obtained after training are α=0.5, β=0.3, γ=0.2. The initial values ​​of the dynamic coupling weight coefficients refer to the initial values ​​assigned to each dynamic coupling weight coefficient when the real-time monitoring system starts, usually derived from the baseline weights; for example, when the system starts, the dynamic weight ω_G of the spatial thermal field gradient feature is set to the baseline value of 0.5 obtained from offline training.

[0036] During real-time operation, the dynamic coupling weight coefficient is dynamically adjusted based on the numerical changes of adjacent sampling time windows in the multidimensional fused thermal state vector. The greater the change amplitude of the spatial thermal field gradient feature, the higher the adjustment gain of its corresponding dynamic coupling weight coefficient. The more significant the cumulative change trend of the time-series pressure change rate feature, the higher the adjustment gain of its corresponding dynamic coupling weight coefficient. The greater the degree to which the instantaneous heat flux value exceeds the preset normal threshold, the higher the adjustment gain of its corresponding dynamic coupling weight coefficient.

[0037] Adjacent sampling time windows refer to two consecutive sampling time periods on the time axis; for example, the currently processed sampling window "10:00:00.100-10:00:00.200" and its predecessor window "10:00:00.000-10:00:00.100". Adjustment gain refers to a proportional factor used to control the magnitude and rate of change of the dynamic coupling weight coefficient; for example, when the pressure change rate is significant, the corresponding weight adjustment gain is set to 1.2, meaning the weight will be increased at a rate of 1.2 times. Cumulative change trend refers to the pattern of continuous increase or decrease of a certain characteristic parameter over multiple consecutive sampling time windows; for example, the internal pressure maintaining an upward trend of more than 0.1 kPa per second for five consecutive windows. Preset normal threshold refers to the upper or lower limit set for a specific characteristic parameter to define its normal value range; for example, setting the normal upper limit of instantaneous heat flux to 20 W and the lower limit to 5 W.

[0038] Using the adjusted dynamic coupling weight coefficients, the spatial thermal field gradient features, the temporal pressure change rate features, and the instantaneous heat flux values ​​are nonlinearly weighted and fused, and a correction factor based on the cross-influence between features is introduced to calculate the comprehensive anomaly score.

[0039] Among them, the correction factor based on the cross-influence between features refers to the parameter introduced into the calculation model to characterize and correct the mutual influence between different features.

[0040] In the above-mentioned optional methods, the baseline weights are further determined by offline training based on historical data, and the coupling weight coefficients are dynamically adjusted according to the numerical changes of adjacent sampling windows during real-time operation. The comprehensive anomaly score is calculated by combining nonlinear weighted fusion and feature cross-influence correction factor, which enhances the model's adaptive recognition ability for complex thermal anomaly patterns.

[0041] In one alternative approach, the comprehensive anomaly score The calculation formula is: in, The spatial thermal field gradient characteristics, The time-series pressure change rate characteristic, The instantaneous heat flux value, , , These are the dynamic coupling weighting coefficients for the spatial thermal field gradient characteristics, the time-series pressure change rate characteristics, and the instantaneous heat flux value, respectively. , , These are preset exponents greater than 1. As the first nonlinear correction factor, This is the second nonlinear correction factor. This represents the cross-influence coefficient.

[0042] In the above-mentioned optional methods, a mathematical model is further constructed by using the spatial thermal field gradient characteristics, the temporal pressure change rate characteristics, and the exponential operation and nonlinear correction term of the instantaneous heat flow value. This model transforms the multi-physics coupling relationship into an accurate and calculable comprehensive anomaly score, thereby realizing the quantitative characterization of the degree of thermal anomaly.

[0043] In one alternative approach, the thermal anomaly determination model is specifically used for: When the thermal anomaly is determined, the spatial coordinates corresponding to the maximum value of the thermal field gradient inside the insulation sheath are determined based on the spatial thermal field gradient characteristics in the multidimensional fused thermal state vector, and the spatial coordinates are mapped to the suppression position.

[0044] The maximum value of the thermal field gradient refers to the highest value among the spatial thermal field gradient characteristics calculated from all spatial locations inside the insulation sheath within a specific sampling time window; for example, the maximum value selected from all current gradient values ​​is "18℃ / cm". Spatial coordinates refer to the three-dimensional values ​​used to uniquely determine the location of a point inside the insulation sheath; for example, using a coordinate system with a certain corner of the sheath as the origin, the coordinates of a point are represented as (15mm, 8mm, 3mm).

[0045] The suppression intensity is calculated based on the comprehensive anomaly score, the maximum value in the spatial thermal field gradient characteristics, the temporal pressure change rate characteristics, and the instantaneous heat flux value.

[0046] The suppression position and the suppression intensity are combined to form the linkage control command.

[0047] In the above-mentioned optional methods, when determining the thermal anomaly state, the suppression position is determined based on the maximum value of the spatial thermal field gradient, and the suppression intensity is calculated based on the comprehensive anomaly score, the maximum gradient value, the pressure change rate and the heat flow value. The combined control commands are then generated, realizing an automated decision mapping from detection to suppression.

[0048] In one alternative approach, the formula for calculating the suppression intensity is: in, The suppression intensity, The maximum value among the spatial thermal field gradient features is... The instantaneous heat flux value, , , , This is the preset adjustment coefficient.

[0049] Among the above-mentioned optional methods, the suppression intensity is further quantified by coupling the comprehensive anomaly score with the maximum value of the spatial thermal field gradient, the pressure change rate and the heat flow value, so as to achieve a precise match between the suppression intensity and the severity of the anomaly and optimize the suppression resource allocation strategy.

[0050] In an alternative embodiment, the thermal diffusion suppression execution module 130 is specifically used for: Receive the linkage control command and parse the suppression position and suppression intensity in the linkage control command.

[0051] Based on the suppression location, activate one or more local suppression units located inside the thermal insulation sheath corresponding to the heat diffusion path.

[0052] Among them, the local suppression unit refers to a basic physical unit that is placed in a specific position inside the heat insulation sheath and can independently and controllably perform the function of heat suppression; for example, a miniature Peltier cooling plate embedded in the sheath material.

[0053] Based on the suppression intensity, the operating parameters of the one or more local suppression units are dynamically adjusted, including the cooling power of the local suppression unit or the triggering rate of the phase change material.

[0054] Cooling power refers to the ability of a local suppression unit to absorb or transfer heat per unit time; for example, a miniature Peltier thermostat operating at its rated voltage has a maximum cooling power of 5W. Phase change material (PCM) refers to a material that undergoes a phase change (e.g., from solid to liquid) at a specific temperature and absorbs or releases a large amount of latent heat in the process; for example, paraffin-based composite materials with a melting point of 45°C. Trigger rate refers to a parameter that controls the speed at which PCM is activated or undergoes a phase change process; for example, adjusting the rate at which PCM melts from a solid to a liquid state by controlling the current of a miniature heating wire.

[0055] The one or more local suppression units are controlled to start synchronously according to the operating parameters, forming a directional blocking area on the heat diffusion path of the thermal insulation sheath, and performing the coordinated suppression action.

[0056] Among them, the directional barrier region refers to a local spatial region formed on the heat diffusion path through coordinated suppression actions, which can specifically reduce heat transfer; for example, three micro-cooling chips work together to form a low-temperature "barrier" region directly above the processor.

[0057] In the above-mentioned optional methods, the local suppression unit on the corresponding thermal diffusion path is further activated by parsing the linkage control command, and the cooling power or phase change material triggering rate is dynamically adjusted to form a directional barrier region on the thermal diffusion path, thereby realizing the precise spatial positioning and intensity adaptive execution of the suppression action.

[0058] In an alternative embodiment, the data acquisition and monitoring control module 120 is further configured to perform a feedback optimization process, the feedback optimization process including: After the thermal diffusion suppression execution module 130 performs the coordinated suppression action, it acquires the updated thermal field distribution parameters, internal pressure parameters, and heat flow rate parameters synchronously collected by the multi-parameter sensing module 110.

[0059] The updated parameters are used to generate a subsequent multidimensional fusion thermal state vector, and the state difference between the subsequent multidimensional fusion thermal state vector and the multidimensional fusion thermal state vector used when the linkage control command is triggered is calculated.

[0060] The subsequent multidimensional fused thermal state vector refers to the multidimensional fused thermal state vector generated based on newly acquired parameter data after the thermal diffusion suppression execution module takes action; for example, a vector [10.5, 0.05, 12.0] generated based on new data 100ms after the suppression action is executed. The state difference degree refers to a metric used to quantify the difference between the subsequent multidimensional fused thermal state vector and the historical vector used to trigger the linkage control command; for example, a difference degree value of "15.3" obtained by calculating the Euclidean distance between the two vectors.

[0061] Based on the state difference degree and the suppression strength, at least one dynamic coupling weight coefficient in the thermal anomaly determination model is dynamically adjusted using a preset gradient descent algorithm.

[0062] Among them, gradient descent algorithm refers to an optimization algorithm that finds the minimum value of a function by iteratively calculating and adjusting parameters in the opposite direction of the gradient of the objective function; for example, in the feedback optimization process, the algorithm calculates the loss function based on the state difference and fine-tunes the value of the dynamic coupling weight coefficient along the gradient direction.

[0063] In the above-mentioned optional methods, after the suppression is performed, the updated parameters are obtained and the state difference is calculated. Based on the difference and the suppression strength, the model coupling weight coefficient is dynamically adjusted through the gradient descent algorithm, and a closed-loop feedback optimization mechanism is established, realizing the continuous learning and performance improvement of the thermal anomaly judgment model.

[0064] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this invention.

[0065] It should be noted that the terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and do not imply a specific order or sequence. Where appropriate, the order of use for similar objects can be interchanged so that the embodiments of this application described herein can be implemented in an order other than that shown or described.

[0066] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A multi-parameter monitoring and thermal diffusion suppression linkage system for thermal insulation sheaths of electronic components, characterized in that, The system includes: The multi-parameter sensing module is used to collect in real time the thermal field distribution parameters, internal pressure parameters, and heat flow rate parameters inside the thermal insulation sheath of electronic components. The data acquisition and monitoring control module is used to perform time-series fusion of the thermal field distribution parameters, the internal pressure parameters, and the heat flow rate parameters to generate a multi-dimensional fused thermal state vector characterizing the real-time thermal state of the insulation sheath. The multi-dimensional fused thermal state vector is input into a preset thermal anomaly determination model. The thermal anomaly determination model comprehensively evaluates the coupling relationship between the thermal field gradient, pressure change trend, and heat flow anomaly rate to determine the thermal anomaly state. When the thermal anomaly state is determined, the thermal anomaly determination model outputs a linkage control command containing the suppression position and suppression intensity. The heat diffusion suppression execution module is used to perform a coordinated suppression action on the corresponding heat diffusion path of the thermal insulation sleeve according to the suppression position and suppression intensity in the linkage control command.

2. The multi-parameter monitoring and thermal diffusion suppression linkage system for electronic component thermal insulation sheaths according to claim 1, characterized in that, The multi-parameter sensing module is specifically used for: By deploying a distributed temperature sensor array inside the thermal insulation sheath, temperature data at multiple spatial locations inside the thermal insulation sheath are collected synchronously, and the thermal field distribution parameters are calculated and generated based on the temperature data at the multiple spatial locations. By using micro-pressure sensors installed inside the thermal insulation sheath, the environmental pressure data inside the thermal insulation sheath is collected synchronously and used as the internal pressure parameter; By using heat flux sensors installed inside the heat insulation sheath, heat power data flowing through a designated cross-section inside the heat insulation sheath is collected synchronously and used as the heat flow rate parameter.

3. The multi-parameter monitoring and thermal diffusion suppression linkage system for electronic component thermal insulation sheaths according to claim 1, characterized in that, The data acquisition and monitoring control module is specifically used for: Based on a unified time reference, the synchronously acquired thermal field distribution parameters, internal pressure parameters and heat flow rate parameters are aligned within the same sampling time window. Spatial thermal field gradient features are extracted from the aligned thermal field distribution parameters; temporal pressure change rate features are extracted from the aligned internal pressure parameters; and instantaneous heat flux values ​​are extracted from the aligned heat flux rate parameters. The spatial thermal field gradient characteristics, the temporal pressure change rate characteristics, and the instantaneous heat flux value are combined in a preset dimensional order to form a multidimensional fused thermal state vector that characterizes the comprehensive thermal state of the thermal insulation sheath within the sampling time window.

4. The multi-parameter monitoring and thermal diffusion suppression linkage system for electronic component thermal insulation sheaths according to claim 3, characterized in that, The data acquisition and monitoring control module is specifically used for: The multidimensional fused thermal state vector is input into the thermal anomaly determination model. The thermal anomaly determination model analyzes the spatial thermal field gradient features, the temporal pressure change rate features, and the instantaneous heat flux value in the multidimensional fused thermal state vector. Based on a preset coupling weight coefficient, the spatial thermal field gradient features, the temporal pressure change rate features, and the instantaneous heat flux value are weighted and fused to generate a comprehensive anomaly score. When the comprehensive anomaly score exceeds a preset anomaly threshold, the thermal anomaly state is determined to have occurred.

5. The multi-parameter monitoring and thermal diffusion suppression linkage system for electronic component thermal insulation sheaths according to claim 4, characterized in that, The thermal anomaly determination model is specifically used for: Based on the historical operating data of the thermal insulation sleeve, the baseline weights corresponding to the spatial thermal field gradient characteristics, the temporal pressure change rate characteristics, and the instantaneous heat flux value are established through offline training, and the baseline weights are used as the initial values ​​of the dynamic coupling weight coefficients. During real-time operation, the dynamic coupling weight coefficient is dynamically adjusted according to the numerical changes of adjacent sampling time windows in the multidimensional fused thermal state vector. The greater the change amplitude of the spatial thermal field gradient feature, the higher the adjustment gain of the corresponding dynamic coupling weight coefficient. The more significant the cumulative change trend of the time-series pressure change rate feature, the higher the adjustment gain of the corresponding dynamic coupling weight coefficient. The greater the degree to which the instantaneous heat flux value exceeds the preset normal threshold, the higher the adjustment gain of the corresponding dynamic coupling weight coefficient. Using the adjusted dynamic coupling weight coefficients, the spatial thermal field gradient features, the temporal pressure change rate features, and the instantaneous heat flux values ​​are nonlinearly weighted and fused, and a correction factor based on the cross-influence between features is introduced to calculate the comprehensive anomaly score.

6. The multi-parameter monitoring and thermal diffusion suppression linkage system for electronic component thermal insulation sheaths according to claim 5, characterized in that, The comprehensive anomaly score The calculation formula is: in, The spatial thermal field gradient characteristics, The time-series pressure change rate characteristic, The instantaneous heat flux value, , , These are the dynamic coupling weighting coefficients for the spatial thermal field gradient characteristics, the time-series pressure change rate characteristics, and the instantaneous heat flux value, respectively. , , These are preset exponents greater than 1. As the first nonlinear correction factor, This is the second nonlinear correction factor. This represents the cross-influence coefficient.

7. The multi-parameter monitoring and thermal diffusion suppression linkage system for electronic component thermal insulation sheaths according to claim 6, characterized in that, The thermal anomaly determination model is specifically used for: When the thermal anomaly is determined, the spatial coordinates corresponding to the maximum value of the thermal field gradient inside the insulation sheath are determined based on the spatial thermal field gradient characteristics in the multidimensional fused thermal state vector, and the spatial coordinates are mapped to the suppression position. The suppression intensity is calculated based on the comprehensive anomaly score, the maximum value in the spatial thermal field gradient characteristics, the temporal pressure change rate characteristics, and the instantaneous heat flux value. The suppression position and the suppression intensity are combined to form the linkage control command.

8. The multi-parameter monitoring and thermal diffusion suppression linkage system for electronic component thermal insulation sheaths according to claim 7, characterized in that, The formula for calculating the suppression intensity is: in, The suppression intensity, The maximum value among the spatial thermal field gradient features is... The instantaneous heat flux value, , , , This is the preset adjustment coefficient.

9. The multi-parameter monitoring and thermal diffusion suppression linkage system for electronic component thermal insulation sheaths according to claim 8, characterized in that, The thermal diffusion suppression execution module is specifically used for: Receive the linkage control command and parse the suppression position and suppression intensity in the linkage control command; Based on the suppression location, activate one or more local suppression units arranged inside the heat insulation sheath on the corresponding heat diffusion path; Based on the suppression intensity, the operating parameters of the one or more local suppression units are dynamically adjusted, and the operating parameters include the cooling power of the local suppression unit or the triggering rate of the phase change material; The one or more local suppression units are controlled to start synchronously according to the operating parameters, forming a directional blocking area on the heat diffusion path of the thermal insulation sheath, and performing the coordinated suppression action.

10. The multi-parameter monitoring and thermal diffusion suppression linkage system for electronic component thermal insulation sheaths according to any one of claims 5 to 9, characterized in that, The data acquisition and monitoring control module is also used to execute a feedback optimization process, which includes: After the thermal diffusion suppression execution module performs the coordinated suppression action, it acquires the updated thermal field distribution parameters, internal pressure parameters, and heat flow rate parameters synchronously collected by the multi-parameter sensing module. The updated parameters are used to generate a subsequent multidimensional fusion thermal state vector, and the state difference between the subsequent multidimensional fusion thermal state vector and the multidimensional fusion thermal state vector used when the linkage control command is triggered is calculated. Based on the state difference degree and the suppression strength, at least one dynamic coupling weight coefficient in the thermal anomaly determination model is dynamically adjusted using a preset gradient descent algorithm.

Images