In-line storage control method based on state monitoring and active heat dissipation

Abstract

The invention relates to the technical field of direct insertion type storage control, and discloses a direct insertion type storage control method based on state monitoring and active heat dissipation. The method comprises the following steps: acquiring state data of storage equipment, and executing a thermal distribution diagram construction operation according to the data; key state parameter extraction operation is executed based on the constructed thermal distribution diagram, and thermal abrupt change nodes are identified from the key state parameter extraction operation; and finally, dividing a heat dissipation area based on the extracted key state parameters, and fitting the identified thermal abrupt change nodes into an area boundary line. Through the method, the thermal distribution condition of the in-line storage device can be accurately mastered, the heat dissipation area is specifically divided, the area boundary is defined, the active heat dissipation operation can be dynamically adjusted according to the actual thermal state of the device, the heat dissipation requirements of different areas of the device are effectively met, local heat accumulation is avoided, and the service life of the device is prolonged. The stability of the storage equipment in the operation process is guaranteed, the equipment operation abnormity caused by the heating power problem is reduced, and the use requirements of the direct insertion type storage equipment under various working conditions are met.

Description

Technical Field

[0001] This invention relates to the field of through-hole memory control technology, specifically to a through-hole memory control method based on status monitoring and active heat dissipation. Background Technology

[0002] In today's digital age, through-hole storage devices are widely used in various scenarios such as servers, industrial control equipment, and personal computers due to their convenient connection and high data transmission efficiency, undertaking the task of storing and reading / writing large amounts of data. With the continuous growth of data volume and the increasing frequency of device operation, through-hole storage devices generate a lot of heat during operation. If the heat cannot be dissipated effectively and in a timely manner, it will have a significant impact on the stable operation of the device. Current DIP (Dual-channel memory) storage devices primarily rely on passive cooling. While some devices incorporate active cooling mechanisms, their related thermal control logic suffers from significant limitations. Most active cooling solutions operate based on a single temperature parameter, such as setting a fixed temperature threshold and activating fans or increasing cooling power when the device reaches that threshold. This approach fails to consider the varying heat distribution across different areas of the storage device. In actual operation, the heat generation of components within a DIP storage device is uneven. Some core chips and interface areas become localized hotspots due to higher power consumption. Traditional cooling methods struggle to precisely cool these high-temperature areas, leading to wasted cooling resources and the inability to dissipate heat effectively. Over time, this can result in performance degradation and increased read / write errors. Current technologies lack effective monitoring and analysis methods for the overall thermal distribution of storage devices, making it impossible to accurately identify thermal abrupt change nodes. Thermal abrupt change nodes typically refer to areas where the temperature rises rapidly or fluctuates abnormally within a short period during device operation. The occurrence of these nodes is often related to precursors to component failures or sudden load changes. Because thermal abrupt change nodes cannot be identified in a timely manner, thermal control cannot dynamically adjust according to the actual thermal changes of the device. When thermal abrupt changes occur, traditional cooling methods struggle to respond quickly, potentially leading to increased localized heat accumulation, which in turn affects the device's lifespan and may even cause serious consequences such as device downtime and data loss. Furthermore, existing heat dissipation zone divisions are often based on simple partitions of the device's physical structure without considering the actual thermal distribution. This mismatch between the defined heat dissipation zones and the key areas requiring cooling further reduces cooling efficiency and fails to meet the heat dissipation needs of through-hole storage devices under high load and long-term operation scenarios. Summary of the Invention

[0003] The purpose of this invention is to provide a through-hole memory control method based on state monitoring and active heat dissipation to solve the problems mentioned in the background art.

[0004] To achieve the above objectives, the present invention provides a through-hole memory control method based on state monitoring and active heat dissipation, the method comprising: Acquire storage device status data, and perform a heat map construction operation based on the storage device status data; Based on the heat distribution map, key state parameters are extracted to identify nodes of thermal abrupt change. The heat dissipation area is divided based on the key state parameters, and the thermal abrupt change node is fitted into the boundary line of the area.

[0005] Preferably, the step of performing the heat map construction operation based on the storage device status data includes: Set the temperature reference value and allowable fluctuation threshold; The thermal anomaly boundary is determined based on the temperature reference value and the allowable fluctuation threshold. A dynamic heat distribution map is generated based on the aforementioned thermal anomaly boundary.

[0006] Preferably, the step of performing key state parameter extraction based on the heat distribution map includes: Temperature sampling values ​​are detected at preset intervals along the normal direction of the boundary line of the region. The thermal abrupt change node is determined based on the gradient change of three consecutive temperature sampling values.

[0007] Preferably, the step of dividing the heat dissipation area based on the key state parameters includes: The closed interval formed by two adjacent thermal abrupt change nodes is defined as an independent heat dissipation region; Heat dissipation vector coordinates are generated based on the geometric center point of each of the independent heat dissipation areas.

[0008] Preferably, the method further includes: The heat dissipation vector coordinates are normalized and scaled to generate a standard heat dissipation parameter matrix; The heat dissipation stability margin is calculated based on the aforementioned standard heat dissipation parameter matrix.

[0009] Preferably, the method further includes: A dynamic heat dissipation model is established based on the heat dissipation stability margin, and the convergence domain boundary of the dynamic heat dissipation model is verified by Lyapunov analysis.

[0010] Preferably, the method further includes: When the convergence domain boundary exceeds a preset safety threshold, switch to forced cooling mode and reconstruct the heat dissipation vector coordinates in forced cooling mode.

[0011] Preferably, the method further includes: The feedback signal of the heat dissipation execution unit is monitored in real time. When the deviation between the feedback signal of the heat dissipation execution unit and the predicted value of the dynamic heat dissipation model exceeds the fault tolerance limit, the heat dissipation abnormality interruption mechanism is triggered.

[0012] Preferably, the method further includes: A pulse width modulation (PWM) command sequence is generated based on the reconstructed heat dissipation vector coordinates, and the tracking control of the PWM command sequence is executed using a sliding mode variable structure algorithm.

[0013] Preferably, the method further includes: The control trajectories of each independent heat dissipation area are spatiotemporally aligned, and a global heat dissipation strategy mapping table is generated based on the alignment results.

[0014] Compared with the prior art, the beneficial effects of the present invention are: This method acquires storage device status data and constructs a thermal distribution map, providing a comprehensive and intuitive view of the overall thermal distribution of through-hole storage devices. It breaks through the limitations of traditional cooling methods that rely solely on a single temperature parameter, allowing for more than just a rough assessment of the overall device temperature. Instead, it enables the development of cooling strategies that better meet actual needs based on complete thermal distribution information. Compared to traditional methods, this thermal distribution map-based cooling control logic can more accurately grasp the differences in heat generation across different areas of the device, providing a foundation for subsequent targeted cooling and avoiding cooling deviations caused by incomplete understanding of the thermal distribution. In terms of extracting key state parameters and identifying thermal abrupt change nodes, this method can accurately extract key information reflecting the thermal state of equipment from the thermal distribution map, and promptly detect thermal abrupt change nodes during equipment operation. Accurate identification of thermal abrupt change nodes enables heat dissipation control to quickly detect abnormal changes in the equipment's thermal state. Unlike traditional technologies that only respond passively after thermal anomalies have already affected the equipment, this method allows for targeted measures to be taken in the early stages of thermal abrupt changes, effectively curbing further heat accumulation, reducing the possibility of equipment failure caused by thermal abrupt changes, and ensuring the continuity of equipment operation.

[0015] This method of dividing heat dissipation zones based on key state parameters and fitting thermal abrupt change nodes as zone boundary lines fully integrates the actual thermal state of the equipment, resulting in heat dissipation zones that highly match the actual heat dissipation requirements of the equipment. Traditional heat dissipation zone division is often based on physical structure, which may group areas that do not require focused heat dissipation with high-temperature areas into the same heat dissipation unit, leading to unreasonable allocation of heat dissipation resources. In contrast, the heat dissipation zones divided by this method allow heat dissipation operations to be precisely applied to areas that require heat dissipation, especially areas containing thermal abrupt change nodes. The heat dissipation range can be clearly defined by boundary lines, avoiding waste of heat dissipation resources while ensuring heat dissipation effectiveness. In practical applications, this method enables more dynamic and targeted active cooling for through-hole storage devices. When the device is operating under low load, with low overall temperature and no significant thermal fluctuations, the cooling system can maintain low operating power, reducing energy consumption. When the device load increases, and localized areas experience temperature rises or thermal fluctuations, the cooling system can increase its cooling power for the corresponding areas, quickly dissipating heat. This dynamically adjusted cooling method not only ensures stable operation of the device under different operating conditions but also extends the lifespan of the cooling system while reducing unnecessary energy consumption, meeting the current demand for energy-efficient operation. Furthermore, this method is highly adaptable to through-hole storage devices. Whether the device is used in high-load scenarios such as servers or ordinary scenarios such as personal computers, it can achieve efficient cooling based on the actual device status, ensuring data read / write stability, reducing data read / write errors caused by thermal issues, and providing strong support for the long-term reliable operation of the device. Attached Figure Description

[0016] Figure 1 This is a schematic diagram illustrating the working principle of the through-hole storage control method based on state monitoring and active heat dissipation described in this invention. Figure 2 A diagram illustrating the working principle of the heat map construction operation; Figure 3 This is a schematic diagram illustrating the working principle of the key state parameter extraction operation. Figure 4 This diagram illustrates the working principle of heat dissipation vector coordinate processing and heat dissipation stability margin calculation. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Please see Figure 1 This invention provides a through-hole memory control method based on status monitoring and active heat dissipation, the method comprising: Acquire storage device status data, including but not limited to temperature sensor readings, device workload parameters, and ambient temperature information. Based on this status data, perform a thermal distribution map construction operation to generate a dynamic map reflecting the temperature distribution on the device's surface or internal structure. Subsequently, based on the thermal distribution map, perform a key status parameter extraction operation to identify nodes with significant thermal abrupt changes in temperature. Finally, divide the heat dissipation areas according to the key status parameters and fit the thermal abrupt change nodes to area boundary lines, forming the basis for zoned heat dissipation control.

[0019] Example 1: See Figure 2 During implementation, the setting of the temperature reference value is a dynamic adjustment process. The system establishes corresponding thermal characteristic models for different types of through-hole storage devices, such as NAND flash-based solid-state drives or new non-volatile memories. This model comprehensively considers factors such as the material, packaging, power consumption, and operating frequency of the storage chip. For a typical storage module, its temperature reference value is not a fixed value but fluctuates within a temperature range called the "comfort zone." The lower limit of this comfort zone is usually determined by the minimum temperature requirement for the storage medium to maintain data integrity, while the upper limit is constrained by the electron migration effect threshold of the semiconductor material. During system initialization, a thermal parameter table provided by the device manufacturer is loaded, which defines the expected base temperature values ​​under different operating conditions. In actual operation, the reference value is also adaptively adjusted based on the device's historical workload and changes in ambient temperature, forming a dynamically changing reference target.

[0020] Setting the allowable fluctuation threshold is also a multi-factor decision-making process. The system considers not only the device's thermal tolerance but also the intensity and duration of the current workload. For example, during continuous large-volume write operations, the heat generated by the storage controller chip and flash memory chips increases significantly. In this case, the system will appropriately relax the upper limit of the allowable fluctuation threshold to avoid unnecessary thermal intervention affecting write performance. The fluctuation threshold is set asymmetrically, with the tolerance range for upward fluctuations typically narrower than that for downward fluctuations. This is mainly because high temperatures have a more significant impact on device reliability. The threshold value is determined through a weighted algorithm that comprehensively considers real-time operating current, ambient temperature sensor readings, and the current state of the cooling system. These thresholds are not static values ​​but are updated in real time as the device's operating state changes, forming a dynamic protection boundary that matches the actual condition of the device.

[0021] The process of determining the thermal anomaly boundary based on a temperature baseline and an allowable fluctuation threshold involves complex thermodynamic calculations. The system divides the surface of the storage device into multiple virtual grids, with each grid cell corresponding to the monitoring area of ​​one or more temperature sensors. For each grid cell, the system calculates the deviation of its current temperature value from the baseline value and compares this deviation with the allowable fluctuation threshold. When the deviation exceeds the threshold, the area is marked as a potential thermal anomaly region. The system then performs spatial clustering analysis on these anomaly regions, merging adjacent anomaly regions into larger anomaly regions, thus forming a complete thermal anomaly boundary. This boundary is actually a dynamically changing contour that clearly identifies which areas of the device surface require special attention and potential heat dissipation interventions.

[0022] The generation of thermal anomaly boundaries also considers changes over time. The system maintains a historical record of temperature changes within a time window, analyzing the formation rate and movement trajectory of anomaly regions. For example, if a high-temperature region is rapidly expanding or moving towards a critical component, the system will adjust the anomaly boundary prediction model in advance, enabling earlier warnings and interventions. This spatiotemporal joint analysis ensures that thermal anomaly boundaries not only reflect the current state but also include predictions of short-term thermal development trends.

[0023] Generating a dynamic thermal distribution map based on thermal anomaly boundaries is a multi-step data visualization process. The system first maps the physical coordinate system of the equipment surface to a standardized two-dimensional coordinate system, with each coordinate point corresponding to a temperature data acquisition point. This temperature data undergoes filtering and smoothing to eliminate errors caused by sensor noise and transient interference. The processed data is then used to generate a continuous temperature field distribution through interpolation algorithms, forming the basic thermal distribution map.

[0024] On top of this base map, the system overlays the previously calculated thermal anomaly boundaries, using clear visual markers (such as red outlines) to identify the anomalous areas. The map also uses color gradients to represent temperature levels, typically employing a gradient from blue (low temperature) to red (high temperature). The map's refresh rate is synchronized with the data acquisition system, usually set at intervals of several hundred milliseconds to several seconds, depending on the device's thermal time constant and the required response speed.

[0025] The dynamic thermal distribution map not only displays the current state but also provides historical data backtracking capabilities. The system can display time-series animations of temperature changes, showcasing the formation and development of thermal anomaly areas. This historical perspective is particularly valuable for analyzing intermittent heat dissipation problems. Furthermore, the map supports multi-layer information overlay; for example, it can simultaneously display the device's workload distribution map on top of the thermal distribution map, helping to analyze the correlation between heat generation and workload. The map generation process also includes a data integrity verification mechanism. When some sensor data is lost or abnormal, the system uses a prediction algorithm based on neighboring sensor data and historical patterns to fill in the missing data, ensuring the continuity of the map. Simultaneously, the system assesses the reliability of each data point and appropriately marks low-reliability areas on the map, alerting users to the potential uncertainty of the data in these areas.

[0026] The setting of temperature baselines and fluctuation thresholds provides evaluation criteria for the system, the identification of thermal anomaly boundaries marks areas requiring attention, and the dynamic thermal distribution map provides an intuitive monitoring interface. This system continuously cycles, adjusting various parameters in real time to ensure that the through-hole storage devices always operate within a safe temperature range, while optimizing the energy efficiency of the cooling system.

[0027] Example 2: See Figure 3 Regional boundary lines are typically composed of continuous line segments with significant temperature gradients in a thermal distribution map, marking the boundaries between different temperature regions. The system first discretizes each boundary line, dividing it into several equally spaced segments, and then extends a normal line at each division point. The length of the normal extension is determined based on the thermal conductivity and physical dimensions of the device, typically extending to the center of adjacent temperature regions. Along these normal directions, the system arranges virtual temperature sampling points at preset intervals. The spacing of these sampling points is carefully calculated to ensure that details of temperature changes are captured while avoiding data redundancy. The sampling interval is determined by considering the thermal diffusivity of the material and the response time of the sensor, ensuring that the sampling frequency keeps pace with the dynamic process of temperature changes. In actual operation, the system obtains the temperature values ​​of these virtual sampling points from the existing sensor network using an interpolation algorithm; these values ​​are calculated based on measured data from nearby physical sensors.

[0028] The temperature sampling process employs a layered, progressive approach. The system first performs coarse-grained sampling along the normal direction to identify the general trend of temperature changes. If a significant temperature change is detected in a certain segment, the system automatically increases the sampling density in that segment for fine-grained sampling. This adaptive sampling strategy ensures data integrity while improving sampling efficiency. Temperature data from all sampling points are timestamped, forming a time-series dataset that provides a foundation for subsequent gradient analysis.

[0029] Identifying thermodynamic abrupt change nodes based on the gradient change of three consecutive temperature samples is a multi-stage analysis process. The system sequentially takes three consecutive sampling points along each normal direction to calculate the temperature gradient. The gradient calculation employs the central difference method, considering both forward and backward temperature change trends. For each sampling triplet, the system calculates the rate of temperature change between two adjacent point pairs and then analyzes the difference between these two rates. When the difference between two consecutive temperature rates of change exceeds a preset threshold, the location is marked as a potential thermodynamic abrupt change node.

[0030] Threshold setting is a dynamic adjustment process based on the device's historical operating data and current operating status. The system maintains a threshold adjustment algorithm that considers multiple factors such as ambient temperature, device workload, and the state of the cooling system. For each potential thermal abrupt change node, the system also performs a confidence assessment, evaluating factors including the magnitude, duration, and spatial consistency of the gradient change. Only nodes that pass the confidence test are ultimately confirmed as thermal abrupt change nodes.

[0031] The identification of nodes exhibiting thermal abrupt changes is based not only on instantaneous gradient changes but also on their persistence over time. The system observes the behavior of these nodes over several consecutive sampling periods, and only those nodes that consistently show significant gradient changes are ultimately confirmed. This time-domain verification helps to eliminate false positives caused by transient interference.

[0032] Defining the closed region formed by two adjacent thermal abrupt change nodes as an independent heat dissipation area is a spatial clustering and analysis process. The system first projects all identified thermal abrupt change nodes onto a two-dimensional coordinate system on the device surface. Then, based on the spatial distance and temperature characteristic similarity between nodes, clustering analysis is performed, grouping nodes that are spatially close and have similar temperature characteristics into the same group. For each group of nodes, the system finds the two closest node pairs; the line segments formed by these node pairs constitute the potential region boundaries.

[0033] The system uses a polygon fitting algorithm to connect these nodes, forming closed polygonal regions. Each polygonal region represents an area with relatively uniform temperature characteristics; these regions are called independent heat dissipation regions. Region closure checks ensure that each region has a clear boundary, avoiding unclosed or overlapping areas. For complex region shapes, the system may decompose a large irregular region into several smaller, regular-shaped regions to facilitate subsequent heat dissipation management. Generating heat dissipation vector coordinates based on the geometric center points of each independent heat dissipation region is a geometric calculation and parameterization process. For each independent heat dissipation region, the system calculates its geometric center point coordinates. This calculation is based on the vertex coordinates of the region polygon, using a weighted average algorithm, with weights determined according to the temperature characteristics represented by each vertex. The geometric center point not only contains spatial location information but also carries the temperature characteristic data of that region.

[0034] The generation of heat dissipation vector coordinates incorporates parameters across multiple dimensions. Spatial coordinate components represent the physical location of the center point, temperature components represent the average temperature of the region, gradient components represent the temperature change trend of the region, and weight components represent the importance of the region in the overall heat dissipation strategy. These parameters collectively constitute a multi-dimensional heat dissipation vector, with each vector uniquely corresponding to an independent heat dissipation area. The system assigns a unique identifier to each heat dissipation vector and establishes a vector database. This database records the historical trajectory of each vector, including location movement, temperature changes, and weight adjustments. The vector coordinates are updated synchronously with temperature sampling to ensure real-time reflection of changes in the device's thermal state. The generation of heat dissipation vector coordinates also considers the device's operating status information. The system integrates current workload information, power consumption data, and ambient temperature data into the vector coordinates, forming comprehensive thermal management parameters. These vector coordinates not only guide current heat dissipation operations but also provide a data foundation for predicting future thermal development trends.

[0035] The entire implementation process forms a complete chain from temperature sampling to region partitioning and vector generation. Temperature sampling provides raw data, gradient analysis identifies key nodes, region partitioning constructs management units, and vector generation provides operational guidelines. This system continuously cycles, updating the heat dissipation area partitioning and vector coordinates in real time to ensure the accuracy and adaptability of heat dissipation control. Through this refined region management, the system can achieve precise temperature control of through-hole storage devices, improving heat dissipation efficiency while reducing energy consumption.

[0036] Example 3: See Figure 4 The heat dissipation vector coordinates originate from the geometric center point parameters of multiple independent heat dissipation regions. These parameters originally have different dimensions and numerical ranges. Normalization aims to eliminate these differences, bringing all parameters to a uniform numerical scale for easier subsequent matrix operations and comparative analysis. The system first analyzes the numerical distribution characteristics of all heat dissipation vector coordinates, including the maximum, minimum, and average values ​​for each parameter dimension. Based on these statistical characteristics, the system designs corresponding scaling functions for each parameter dimension. These scaling functions typically employ linear transformations or nonlinear mappings to transform the original parameter values ​​to a specified standard range. Nonlinear mappings are more suitable in certain situations, especially when the parameter value distribution exhibits non-uniform characteristics; in such cases, the system uses nonlinear transformation methods such as logarithmic scaling or exponential scaling.

[0037] During the normalization process, the system pays special attention to maintaining the relative relationships between parameters. Although the absolute values ​​of the parameters are scaled, their proportional and ordering relationships are preserved. This process ensures that the mathematical properties of subsequent analyses are not affected. After normalizing all parameters, the system reorganizes the processed data into a matrix form, generating a standard heat dissipation parameter matrix. The rows of this matrix correspond to different independent heat dissipation regions, and the columns correspond to different parameter dimensions. Each matrix element represents a standardized value for a specific region along a specific parameter dimension.

[0038] The generation of the standard heat dissipation parameter matrix is ​​a dynamically adjusted process; the matrix's dimensions and content are updated in real time as independent heat dissipation areas are identified and changed. The system maintains a matrix version management system, recording the timestamp and changes for each matrix update, facilitating the tracking of parameter change history. Calculating the heat dissipation stability margin based on the standard heat dissipation parameter matrix involves matrix analysis and eigenvalue calculation. The system first performs covariance analysis on the parameter matrix to calculate the correlation between different parameter dimensions. Through eigenvalue decomposition, the main eigenvectors and eigenvalues ​​of the matrix are extracted. These eigenvalues ​​reflect the main change patterns of the parameter matrix and their corresponding energy distribution. The calculation of the heat dissipation stability margin is based on the distribution characteristics of the eigenvalues, particularly the relative proportion between the minimum and maximum eigenvalues. This proportion reflects the stability of the system in the parameter space.

[0039] The calculation of heat dissipation stability margin also considers mathematical properties such as the condition number of the parameter matrix. The system evaluates numerical stability by analyzing the distribution of singular values ​​of the matrix. These analyses provide a mathematical basis for subsequent heat dissipation control decisions. The stability margin is a dimensionless index, and its value directly reflects the stability of the heat dissipation system.

[0040] Establishing a dynamic heat dissipation model based on the heat dissipation stability margin is a system identification process. This model uses a state-space representation to describe the dynamic characteristics of the heat dissipation system. System state variables include the temperature values ​​and rates of temperature change of each heat dissipation zone, as well as the control variables of the heat dissipation equipment. Model parameters are extracted from historical operating data using system identification techniques and updated online as new data is acquired. The dynamic heat dissipation model considers the thermal inertia characteristics of the equipment, the response characteristics of the heat dissipation equipment, and the influence of ambient temperature. The model contains multiple differential equations describing the dynamic relationship between temperature changes and heat dissipation control. The parameters of these equations are identified from measured data using least squares or recursive estimation methods.

[0041] Verifying the convergence domain boundary of a dynamic heat dissipation model using Lyapunov analysis is a stability proof process. A candidate Lyapunov function is constructed, typically chosen as a quadratic form of the system's state variables. The stability characteristics of the system are determined by analyzing the time derivative of this function along the system's trajectory. The design of the Lyapunov function considers the physical characteristics of the heat dissipation system, and a function form with clear physical meaning is usually chosen.

[0042] The boundary of the region of convergence is determined by analyzing the region of negative definiteness of the Lyapunov function. The system solves the optimization problem under inequality constraints to find the maximum region in which the Lyapunov function remains negative definite; this region is the system's region of convergence. The boundary of the region of convergence describes the range of states within which the system can maintain stable operation.

[0043] The mathematical expression used in this analysis is: ; in: This represents the constructed Lyapunov function used to analyze system stability. Representing the The heat capacity weighting coefficient of each heat dissipation area is determined by the material properties and geometry of the area. Indicates the first The current temperature value of each heat dissipation area is real-time data obtained through temperature sampling. Corresponding to the The target temperature value for each heat dissipation area is dynamically adjusted according to the equipment's operating status. It is the first The damping coefficient of the temperature change rate term reflects the sensitivity of the system to the rate of temperature change. Indicates the first The rate of temperature change of each heat dissipation area is obtained by differential calculation of the temperature time series data. and These represent the number of heat dissipation areas and the number of items considered for temperature change rate, respectively.

[0044] The entire implementation process forms a complete chain from parameter preprocessing to stability analysis. Normalization provides a standardized data foundation for subsequent analysis, parameter matrix operations extract system characteristics, stability margin calculation quantifies the system's stability, dynamic modeling describes system behavior, and Lyapunov analysis verifies system stability. This analytical framework provides a theoretical basis and mathematical tools for the design and adjustment of thermal control systems. Through this systematic analytical method, accurate modeling and stability assurance of the thermal management system for through-hole storage devices can be achieved.

[0045] Example 4: The system calculates the relative distance between the current state and the convergence domain boundary in real time. This distance reflects the degree to which the system's operating state approaches the stability boundary. The preset safety threshold is a dynamic value determined based on the equipment's thermal design specifications and historical operating data. This threshold considers the temperature tolerance limits of the equipment materials, the reliability requirements of electronic components, and the maximum capacity of the heat dissipation system. When the monitoring system detects that the convergence domain boundary exceeds the preset safety threshold, it indicates that the system's thermal state is approaching or may exceed the range of stable operation.

[0046] The decision-making process for switching to forced cooling mode involves multiple verification steps. The system first confirms that the current thermal state indeed requires enhanced cooling measures. This confirmation process includes checking the consistency of readings from multiple sensors, analyzing the persistence of thermal trends, and assessing the intensity of the current workload. Once a mode switch is confirmed, the system sends a mode switch command to all cooling execution units. This switchover process employs a smooth transition to avoid sudden mode changes impacting the system. During the transition, the system gradually adjusts the operating parameters of the cooling equipment, ensuring a smooth transition from normal mode to forced cooling mode.

[0047] Reconstructing the heat dissipation vector coordinates in forced cooling mode is a crucial adjustment process. The system re-evaluates the priority ranking of each heat dissipation area, allocating heat dissipation resources preferentially to the area with the highest heat load. The new heat dissipation vector coordinate calculation employs a weighted allocation algorithm that comprehensively considers the area's current temperature, rate of temperature change, and heat capacity characteristics. The reconstructed coordinates not only reflect the instantaneous thermal state of each area but also include predictive adjustment components calculated based on the heat conduction model.

[0048] Real-time monitoring of feedback signals from thermal actuators is a multi-channel data acquisition and analysis process. The system maintains real-time data exchange with each thermal actuator through a dedicated communication interface. Monitored parameters include fan speed, pump flow rate, heatsink temperature, and power consumption readings, among others. These feedback signals are uploaded to the main control system at fixed time intervals, forming a time-series data stream. The system incorporates a data quality check mechanism for each feedback signal, including range checks, continuity checks, and consistency checks, to ensure data reliability.

[0049] Generating dynamic cooling model predictions is a complex computational process. Based on the current system state, environmental conditions, and historical data, the model predicts the expected feedback signal values ​​for each cooling unit. These predictions represent the ideal operating state of the cooling system. The model's prediction process considers the dynamic characteristics, response delays, and nonlinear factors of the equipment to ensure the predicted values ​​are as close as possible to reality.

[0050] Setting the fault tolerance upper limit is a decision-making process based on statistical analysis and empirical data. The system analyzes the distribution characteristics of the deviation between feedback signals and predicted values ​​in historical operating data, and determines a reasonable fault tolerance range based on this distribution. The fault tolerance upper limit is not a fixed value, but is dynamically adjusted as operating conditions change. Under high temperature and high load conditions, the fault tolerance range may be appropriately tightened to improve the system's sensitivity.

[0051] When the system detects that the deviation between the feedback signal from the heat dissipation execution unit and the predicted value of the dynamic heat dissipation model exceeds the fault tolerance limit, it triggers the heat dissipation anomaly interruption mechanism. This triggering process includes multiple confirmation steps; the system checks the persistence of the deviation, the correlation of multiple signals, and changes in environmental conditions. The interruption mechanism adopts a tiered response approach, taking different levels of interruption measures according to the severity of the deviation. The heat dissipation anomaly interruption mechanism includes multiple levels of response actions: a primary interruption may only issue a warning signal and record abnormal information; a medium-level interruption will adjust the heat dissipation control parameters to attempt to eliminate the abnormality; and a high-level interruption will suspend the current heat dissipation strategy and activate a backup heat dissipation scheme. The system selects an appropriate response level based on the severity and duration of the deviation. See Table 1 for the monitoring and analysis of the heat dissipation execution unit feedback signal.

[0052] Table 1: Feedback Signal Monitoring Table for Thermal Actuation Unit.

[0053]

[0054] The interrupt mechanism also includes anomaly diagnosis functionality. The system analyzes the characteristics of abnormal signals to attempt to identify the cause of the anomaly—whether it's a sensor malfunction, an actuator problem, or an incompatible control strategy. This diagnostic process is based on rule-based reasoning and pattern recognition techniques to help quickly pinpoint the root cause of the problem.

[0055] The system continuously monitors its operational status, assesses stability boundaries, switches operating modes when necessary, monitors execution performance in real time, and takes interruption measures in case of anomalies. This closed-loop system ensures that the through-hole storage device receives appropriate thermal management under various operating conditions, guaranteeing both device safety and optimized heat dissipation efficiency. Through this multi-layered safety mechanism, the system can effectively cope with various abnormal situations, ensuring the stable and reliable operation of the device.

[0056] Example 5: The heat dissipation vector coordinates contain spatial location information, temperature characteristic parameters, and heat dissipation priority data. These parameters need to be converted into specific control commands. The system first analyzes each component of the heat dissipation vector coordinates, including geometric location coordinates, temperature values, thermal gradient vectors, and region weighting coefficients. Based on these parameters, the system calculates the required heat dissipation intensity level for each independent heat dissipation region. The heat dissipation intensity level is a comprehensive index that reflects the degree of heat dissipation resource allocation required for that region.

[0057] The generation of pulse width modulation (PWM) command sequences employs a hierarchical design approach. The system first determines the base modulation frequency, which is based on the dynamic response characteristics of the heat dissipation actuator. For fan-type actuators, the frequency is typically set in the kilohertz range; for pump-type actuators, the frequency is set relatively lower. Within each command cycle, the system calculates the required duty cycle value, which is positively correlated with the heat dissipation intensity level. The duty cycle is adjusted gradually to avoid sudden changes impacting the actuator.

[0058] The generation of instruction sequences also considers the operating characteristic curves of the actuators. The system incorporates performance models for various heat-dissipating actuators, which describe the relationship between the actuator's output characteristics and the input instructions. Based on these models, the system preprocesses the raw instructions to compensate for the nonlinear characteristics of the actuators. For example, for certain fan models, there may be dead zones in the low-speed range; the system will make corresponding compensation adjustments during instruction generation.

[0059] Tracking control of pulse-width modulation (PWM) command sequences using a sliding mode variable structure (SMLS) algorithm is a dynamic adjustment process. The design of the sliding mode variable structure controller is based on a dynamic model of the heat dissipation system, which describes the mapping relationship between control commands and actual heat dissipation effects. The controller first defines a sliding surface function, which represents the difference between the actual and desired states of the system. The design of the sliding surface considers both the accuracy requirements of temperature control and the dynamic response characteristics of the system.

[0060] The control algorithm implementation comprises two main stages: approaching mode and sliding mode. In the approaching mode stage, the controller drives the system state towards the sliding surface; in the sliding mode stage, the controller allows the system state to slide along the sliding surface towards the equilibrium point. The control law design ensures that the system maintains good tracking performance even under parameter uncertainties and external disturbances. The sliding mode variable structure controller is implemented in discrete time, synchronized with the sampling period of the control system. Within each control cycle, the controller calculates the required control output, which is directly converted into an adjustment command for the pulse width modulation parameters. The control algorithm includes anti-chattering measures, reducing high-frequency jitter in the control output through boundary layer methods or continuous approximation methods.

[0061] Spatiotemporal alignment of the control trajectories for each independent heat dissipation zone is a complex coordination process. The system maintains a control trajectory record for each independent heat dissipation zone, containing information such as timestamps, spatial coordinates, and control parameters. The first step in spatiotemporal alignment is time synchronization. The system uses a unified clock source to timestamp all control events, ensuring that control actions in different zones are time-coordinated. Spatial alignment involves the unification and transformation of coordinate systems. Different heat dissipation zones may use different local coordinate systems, which the system transforms to a global coordinate system. The coordinate transformation matrix is ​​determined based on the physical layout of the equipment and the installation position of the heat dissipation actuators. Through spatial alignment, the system can clearly understand the positional significance of each control action within the overall equipment layout. Control trajectory alignment also includes parameter standardization. Control parameters in different zones may have different dimensions and value ranges; the system normalizes these parameters to a unified standard range. Standardization allows for direct comparison and coordination of control effects in different zones. Generating a global heat dissipation strategy mapping table based on the alignment results is a systematic knowledge organization process. The mapping table uses a multi-dimensional data structure to record the optimal heat dissipation strategy corresponding to various operating states. The table's dimensions include multiple factors such as ambient temperature, equipment workload, and cooling system status. Each dimension is further subdivided into multiple levels, forming a discretized state space.

[0062] The global heat dissipation strategy mapping table is constructed based on the analysis of a large amount of historical operating data. The system uses machine learning methods to extract the optimal combination of heat dissipation parameters under different operating conditions from historical data. These parameter combinations include the operating mode, output intensity, and coordination relationship of each heat dissipation actuator. The content of the mapping table is continuously updated and optimized as operating experience accumulates, gradually improving its strategy library.

[0063] The querying and use of the mapping table is a real-time matching process. The system monitors the current operating status parameters, matches these parameters with the indexes in the mapping table, and finds the most suitable heat dissipation strategy for the current state. The matching process uses the nearest neighbor algorithm to find the known state point closest to the current state and adopt its corresponding heat dissipation strategy. For new states that have not been encountered before, the system uses interpolation methods to derive suitable control parameters from the strategies of neighboring state points.

[0064] From instruction generation to tracking control, from regional coordination to global strategy formulation, each link works closely together. Through this refined control method, the system can precisely manage the heat dissipation process of through-hole storage devices, ensuring that the devices remain within a suitable temperature range under various operating conditions. This control method not only improves heat dissipation efficiency but also optimizes energy consumption allocation, achieving a good balance between heat dissipation performance and energy consumption.

[0065] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0066] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for controlling through-hole memory based on state monitoring and active heat dissipation, characterized in that, include: Acquire storage device status data, and perform a heat map construction operation based on the storage device status data; Based on the heat distribution map, key state parameters are extracted to identify nodes of thermal abrupt change. The heat dissipation area is divided based on the key state parameters, and the thermal abrupt change node is fitted into the boundary line of the area.

2. The through-hole storage control method based on state monitoring and active heat dissipation as described in claim 1, characterized in that, The step of performing a heat map construction operation based on the storage device status data includes: Set the temperature reference value and allowable fluctuation threshold; The thermal anomaly boundary is determined based on the temperature reference value and the allowable fluctuation threshold. A dynamic heat distribution map is generated based on the aforementioned thermal anomaly boundary.

3. The through-hole storage control method based on state monitoring and active heat dissipation as described in claim 1, characterized in that, The step of performing key state parameter extraction based on the heat distribution map includes: Temperature sampling values ​​are detected at preset intervals along the normal direction of the boundary line of the region. The thermal abrupt change node is determined based on the gradient change of three consecutive temperature sampling values.

4. The through-hole storage control method based on state monitoring and active heat dissipation as described in claim 1, characterized in that, The step of dividing the heat dissipation area based on the key state parameters includes: The closed interval formed by two adjacent thermal abrupt change nodes is defined as an independent heat dissipation region; Heat dissipation vector coordinates are generated based on the geometric center point of each of the independent heat dissipation areas.

5. The through-hole storage control method based on state monitoring and active heat dissipation as described in claim 4, characterized in that, Also includes: The heat dissipation vector coordinates are normalized and scaled to generate a standard heat dissipation parameter matrix; The heat dissipation stability margin is calculated based on the aforementioned standard heat dissipation parameter matrix.

6. The through-hole storage control method based on state monitoring and active heat dissipation as described in claim 5, characterized in that, Also includes: A dynamic heat dissipation model is established based on the heat dissipation stability margin, and the convergence domain boundary of the dynamic heat dissipation model is verified by Lyapunov analysis.

7. The through-hole storage control method based on state monitoring and active heat dissipation as described in claim 6, characterized in that, Also includes: When the convergence domain boundary exceeds a preset safety threshold, switch to forced cooling mode and reconstruct the heat dissipation vector coordinates in forced cooling mode.

8. The through-hole storage control method based on state monitoring and active heat dissipation as described in claim 7, characterized in that, Also includes: The feedback signal of the heat dissipation execution unit is monitored in real time. When the deviation between the feedback signal of the heat dissipation execution unit and the predicted value of the dynamic heat dissipation model exceeds the fault tolerance limit, the heat dissipation abnormality interruption mechanism is triggered.

9. The through-hole storage control method based on state monitoring and active heat dissipation as described in claim 8, characterized in that, Also includes: A pulse width modulation (PWM) command sequence is generated based on the reconstructed heat dissipation vector coordinates, and the tracking control of the PWM command sequence is executed using a sliding mode variable structure algorithm.

10. The through-hole storage control method based on state monitoring and active heat dissipation as described in claim 9, characterized in that, Also includes: The control trajectories of each independent heat dissipation area are spatiotemporally aligned, and a global heat dissipation strategy mapping table is generated based on the alignment results.

Images