Intelligent optimization method for heat dissipation performance of computer case

Abstract

The invention relates to an intelligent optimization method for heat dissipation performance of a computer case in the field of new-generation information technology. The intelligent optimization method comprises the following steps: acquiring a thermal simulation result containing dynamic load change through thermal simulation; according to the thermal simulation result, an optimization algorithm is adopted to adjust air duct structure parameters to obtain optimized air duct structure parameters; if the local temperature gradient in the optimized air duct structure parameters exceeds a preset threshold value, fusing heat transfer path data to obtain a corrected airflow velocity vector; performing multi-target optimization on fan layout by adopting an optimization algorithm according to the corrected airflow velocity vector to obtain a final layout scheme; determining a hole position adjustment value matched with the optimization scheme according to the final layout scheme; acquiring thermal load data in actual operation through a real-time sensor network to obtain a deviation matrix of the thermal simulation result; and updating parameters of the thermal simulation model by adopting an optimization algorithm according to the deviation matrix to obtain a refined heat dissipation performance index.

Description

Technical Field

[0001] This invention relates to the field of next-generation information technology, and in particular to an intelligent optimization method for the heat dissipation performance of computer cases. Background Technology

[0002] The thermal performance of a computer case is crucial to hardware lifespan and system stability, especially with the increasing demand for high-performance computing. The quality of the thermal design directly determines a product's competitiveness. As users demand higher-end and intelligent cases, cooling systems need to cope with more complex operating environments and higher-power hardware.

[0003] However, current thermal testing and manufacturing methods have significant shortcomings, failing to meet the high-efficiency heat dissipation requirements of modern computing devices. An optimized solution that closely integrates design and manufacturing is urgently needed. Existing thermal testing methods often rely on simplified experimental environments, such as wind tunnel testing or thermal imaging analysis, which cannot accurately reflect the dynamic thermal load changes of the chassis during actual use. For example, some tests only focus on static airflow distribution, ignoring the complex impact of power fluctuations during hardware operation. Furthermore, the disconnect between thermal design and manufacturing processes means that test data often cannot directly guide adjustments in the manufacturing process, potentially leading to localized overheating issues in the manufactured chassis. In traditional designs, the placement of ventilation holes and fan layouts are largely based on experience, lacking data-driven optimization, easily creating hotspot areas and reducing heat dissipation efficiency. The core technical challenge lies in achieving precise control of airflow distribution and a dynamic balance in heat transfer. Uneven airflow distribution directly affects the heat dissipation effect inside the chassis. If the airflow speed is too low or the airflow design is inappropriate, high-temperature zones can easily form in certain areas. For example, under high load operation, the airflow speed in different areas inside the chassis may vary significantly, resulting in insufficient airflow around some hardware components, preventing heat from being dissipated in time. This uneven airflow distribution further exacerbates the instability of heat transfer, especially during power-on / off or sudden load changes, when the cooling system struggles to respond quickly, leading to drastic temperature fluctuations and affecting hardware lifespan.

[0004] Therefore, how to dynamically adjust airflow distribution and heat transfer paths through real-time data feedback during design and production to adapt to the heat dissipation requirements under different load scenarios has become a key issue in improving the heat dissipation performance of chassis. Summary of the Invention

[0005] This invention provides an intelligent optimization method for the heat dissipation performance of a computer chassis, mainly including:

[0006] Thermal simulation results containing dynamic load changes are obtained through thermal simulation. Based on the thermal simulation results, an optimization algorithm is used to adjust the air duct structure parameters to obtain optimized air duct structure parameters. If the local temperature gradient in the optimized air duct structure parameters exceeds a preset threshold, heat transfer path data is fused to obtain a corrected airflow velocity vector. Based on the corrected airflow velocity vector, an optimization algorithm is used to perform multi-objective optimization of the fan layout to obtain a final layout scheme. For the final layout scheme, hole position adjustment values ​​matching the optimized scheme are determined. Thermal load data from actual operation is collected through a real-time sensor network to obtain a deviation matrix from the thermal simulation results. Based on the deviation matrix, an optimization algorithm is used to update the thermal simulation model parameters to obtain refined heat dissipation performance indicators. If the refined heat dissipation performance indicators meet the system stability requirements, the heat dissipation performance indicators are transmitted to the production stage to determine the final chassis manufacturing configuration. Furthermore, the step of obtaining thermal simulation results containing dynamic load changes through thermal simulation includes: acquiring initial airflow velocity field and initial temperature distribution data from the chassis 3D model to construct a basic dataset; extracting dynamic change characteristics of the heat source based on the basic dataset and runtime heat source data to determine the heat source change pattern over time; introducing dynamic load change parameters for the heat source change pattern over time to construct a load change simulation scenario and obtain heat distribution and airflow adjustment data under load changes; updating the airflow velocity field and temperature field data using the heat distribution and airflow adjustment data under load changes using the finite element analysis method to obtain intermediate thermal simulation results; analyzing the impact of dynamic changes of the heat source on the airflow velocity field based on the intermediate thermal simulation results to determine whether the heat distribution exceeds a preset threshold range; if it does, making local adjustments to the airflow velocity field to determine the adjusted field distribution data; and generating the final thermal simulation result by combining the adjusted field distribution data with the load change simulation scenario.Furthermore, the step of adjusting the duct structure parameters using an optimization algorithm based on the thermal simulation results to obtain optimized duct structure parameters includes: obtaining airflow distribution data from the thermal simulation results and initially dividing the uneven region to obtain uneven distribution location information; using a genetic algorithm to iteratively calculate the parameter adjustment scheme based on the uneven distribution location information to determine the initial adjustment direction for the duct geometry and ventilation openings; obtaining duct geometry modification data from the initial adjustment direction and judging by the range of ventilation opening size changes; if the modification data exceeds a preset threshold range, constraining the modification data to obtain adjustment parameters that meet the constraint conditions; obtaining a corresponding combination scheme of duct geometry and ventilation opening size for the adjustment parameters, and performing airflow distribution simulation on the combination scheme through simulation analysis to determine the improvement of airflow distribution after simulation; obtaining improvement magnitude data based on the improvement of airflow distribution after simulation; if the improvement magnitude data does not reach a preset target value, performing a second iterative calculation on the adjustment parameters to obtain a new combination of adjustment parameters; obtaining the final duct geometry and ventilation opening size data through the new combination of adjustment parameters, and verifying the final data to determine the optimized duct structure parameters. Furthermore, the step of fusing heat transfer path data to obtain a corrected airflow velocity vector if the local temperature gradient in the optimized duct structure parameters exceeds a preset threshold includes: extracting the local temperature gradient from the optimized duct structure parameters and comparing the local temperature gradient with a preset threshold to determine whether it exceeds the preset threshold; if the local temperature gradient exceeds the preset threshold according to the determination result, obtaining heat conduction mechanism data, convection mechanism data, and radiation mechanism data from the heat transfer path data; fusing the heat conduction mechanism data, convection mechanism data, and radiation mechanism data by weighted averaging, wherein the heat conduction mechanism data is calculated based on the material's thermal conductivity, the convection mechanism data is calculated based on fluid velocity and surface area, and the radiation mechanism data is calculated based on temperature difference and emissivity to obtain fused heat data; processing the fused heat data through iterative calculation, wherein the heat distribution value is updated in each iteration until convergence to determine the heat balance adjustment value; calculating a corrected vector based on the heat balance adjustment value and the airflow velocity vector, and integrating the adjusted value with the original vector through vector addition to obtain the corrected airflow velocity vector.Furthermore, the step of using an optimization algorithm to perform multi-objective optimization of the fan layout based on the corrected airflow velocity vector to obtain the final layout scheme includes: using a genetic algorithm to perform multi-objective optimization of the fan layout based on the corrected airflow velocity vector, wherein the genetic algorithm inputs are the corrected airflow velocity vector and fan position parameters, and the output is the optimized layout configuration to obtain a preliminary layout distribution; obtaining a uniformity index from the airflow distribution evaluation based on the preliminary layout distribution, judging the noise level value based on the uniformity index by comparing the noise simulation data with the standard value to obtain the noise level value; if the noise level value exceeds a preset threshold, adjusting the fan position parameters based on the noise level value, and obtaining an updated layout distribution through airflow simulation; obtaining the energy consumption index based on the updated layout distribution, and determining the vibration amplitude monitoring result by integrating fan power and airflow efficiency; verifying the dynamic equilibrium condition based on the vibration amplitude monitoring result, and obtaining the final layout scheme by checking the vibration amplitude monitoring result and comparing it with the equilibrium threshold. Furthermore, determining the hole position adjustment value matching the optimized scheme for the final layout scheme includes: obtaining the manufacturing parameters corresponding to the final layout scheme from the production database, wherein the manufacturing parameters include material thickness and assembly tolerance, and obtaining material thickness data and assembly tolerance values ​​by querying parameter correlation; using a preset threshold to judge the optimization matching logic for the material thickness data and assembly tolerance values, if the material thickness data exceeds the preset threshold, adjusting the assembly tolerance value to obtain scheme compatibility; obtaining the precision control mechanism in the production data source according to the scheme compatibility, and determining the adjustment value generation by parameter correlation; and combining the adjustment value generation with hole position adjustment calculation and manufacturing parameter query to obtain the hole position adjustment value matching the optimized scheme. Furthermore, the step of obtaining a deviation matrix from the thermal simulation result by acquiring actual runtime thermal load data through a real-time sensor network includes: acquiring processor temperature readings and storage component temperatures in the prototype chassis through a real-time sensor network to obtain actual runtime thermal load data; comparing the thermal load data with the thermal simulation result to obtain a calculated temperature deviation value; constructing a deviation matrix based on the calculated temperature deviation value and generating matrix elements by point-by-point subtraction between the calculated temperature deviation value and the corresponding points of the thermal simulation result to determine the basis for runtime thermal management adjustments; if the deviation matrix exceeds a preset threshold, obtaining cooling component temperature readings from the prototype chassis environment to obtain a balanced thermal load distribution; and fusing the actual runtime data through the balanced thermal load distribution to obtain a deviation matrix from the thermal simulation result.Furthermore, the step of updating the thermal simulation model parameters using an optimization algorithm based on the deviation matrix to obtain refined heat dissipation performance indicators includes: updating the thermal simulation model parameters using a genetic algorithm based on the deviation matrix; calculating the error difference between iterations by iteratively, where the error difference is obtained by subtraction to find the difference between the current iteration error and the previous iteration error to obtain the error convergence trend; comparing the iteration deviations based on the error convergence trend, where the absolute value of the difference is calculated using an absolute value function, and if the deviation decreases, determining the parameter optimization direction to obtain a refined parameter set; obtaining heat distribution data from the refined parameter set; calculating the temperature field distribution by inputting the parameter set into the thermal simulation equation; quantifying the performance deviation to determine the heat dissipation uniformity and identifying the heat source distribution characteristics; running an extended simulation loop based on the heat source distribution characteristics; simulating the heat flow path using the heat conduction equation through multiple iterations; extracting the cooling efficiency value; obtaining the heat conduction path optimization by dividing the heat transfer rate by the input power; integrating the optimized index output based on the heat conduction path optimization; and adjusting the heat dissipation coefficient based on the path optimization results to obtain refined heat dissipation performance indicators. Furthermore, the step of transmitting the refined heat dissipation performance indicators to the production stage to determine the final chassis manufacturing configuration if the refined heat dissipation performance indicators meet the system stability requirements includes: transmitting the refined heat dissipation performance indicators to the production stage using a feedback loop mechanism and verifying the integrity of the transmitted data through checksum comparison; extracting chassis manufacturing-related variables from the transmitted data integrity based on the integrity of the transmitted data and judging the matching degree between the variables to obtain a preliminary manufacturing configuration based on the matching degree between the variables; simulating the heat distribution in the preliminary manufacturing configuration by integrating the preliminary manufacturing configuration into a heat flow simulation tool, wherein the heat flow simulation tool is based on the finite element method to construct a mesh model, inputs the variables of the preliminary manufacturing configuration, and outputs the heat flow distribution results; and verifying the heat flow distribution results to determine the final chassis manufacturing configuration.

[0007] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0008] This invention discloses an intelligent optimization method for the heat dissipation performance of computer chassis, solving the problem of low heat dissipation efficiency caused by uneven airflow distribution and dynamic heat load changes inside the chassis. Initial airflow velocity and temperature field data are obtained from the chassis's 3D model through finite element analysis. Combined with heat source changes during electronic device operation, a thermal simulation result incorporating dynamic load is generated. For areas with uneven airflow distribution, an optimization algorithm is used to adjust the air duct geometry and ventilation opening size, determining the optimized air duct structure parameters. If the local temperature gradient exceeds a threshold, heat transfer path data from heat conduction, convection, and radiation mechanisms are iteratively fused to correct the airflow velocity vector. A multi-objective optimization algorithm is then used to adjust the fan layout, balancing airflow distribution and noise levels to obtain a final layout scheme that meets dynamic equilibrium conditions. This invention further extracts manufacturing parameters from a production database and combines them with heat load data collected by a real-time sensor network to generate a deviation matrix. The thermal simulation model parameters are updated until the deviation converges, yielding refined heat dissipation performance indicators. If the indicators meet stability requirements, they are transmitted to the production stage through a feedback loop to determine the final chassis manufacturing configuration. This invention significantly improves chassis heat dissipation efficiency and system stability, and optimizes the production process. Attached Figure Description

[0009] Figure 1 This is a flowchart of the intelligent optimization method for the heat dissipation performance of a computer chassis according to the present invention. Detailed Implementation

[0010] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0011] like Figure 1 The intelligent optimization method for the heat dissipation performance of the computer case in this embodiment may specifically include:

[0012] Step S101: Obtain the initial airflow velocity field and temperature field distribution data from the three-dimensional model of the chassis using finite element analysis software, and combine them with the heat source changes during the operation of the electronic equipment to obtain thermal simulation results that include dynamic load changes.

[0013] Initial airflow velocity field and initial temperature distribution data are obtained from the 3D model of the chassis using finite element analysis (FEM) tools to construct a basic airflow and temperature distribution dataset, obtaining preliminary field distribution information. Based on this preliminary field distribution information, combined with runtime heat source data from the electronic equipment, dynamic change characteristics of the heat source are extracted to determine the specific pattern of heat source change over time. For this specific pattern of heat source change over time, dynamic load change parameters are introduced to construct a load change simulation scenario, obtaining heat distribution and airflow adjustment data under load changes. Using this heat distribution and airflow adjustment data under load changes, the FEM method is used to update the airflow velocity field and temperature field data, obtaining intermediate thermal simulation results that include dynamic load changes. Based on these intermediate thermal simulation results, the impact of dynamic heat source changes on the airflow velocity field is analyzed to determine whether the heat distribution exceeds a preset threshold range. If it does, the airflow velocity field is locally adjusted to determine the adjusted field distribution data. Using the adjusted field distribution data, combined with the load change simulation scenario, the final thermal simulation result is generated, completing the thermal simulation output that includes dynamic load changes.

[0014] The specific implementation method for obtaining initial airflow velocity and temperature field distribution data from the 3D model of the chassis using finite element analysis software, and combining this with the heat source changes during electronic equipment operation, to obtain thermal simulation results including dynamic load changes is as follows. First, the 3D model of the chassis is meshed using finite element analysis software such as ANSYS Fluent. Assuming the chassis dimensions are 0.5 meters long, 0.3 meters wide, and 0.2 meters high, the mesh size is set to 1 million elements to ensure calculation accuracy. Boundary conditions are set as an inlet wind speed of 2.5 m / s and an ambient temperature of 25 degrees Celsius. The airflow velocity field is solved using the Navier-Stokes equations to obtain the initial velocity distribution, where the wind speed in the central region of the chassis is approximately 1.8 m / s, and in the edge region, it is approximately 0.5 m / s. Simultaneously, the initial temperature field is calculated based on the heat conduction equations, assuming the chassis walls are adiabatic and the temperature is uniformly distributed at 25 degrees Celsius when there are no internal heat sources. Next, heat source variation data during electronic device operation was introduced. Assuming the device power changes over time, starting at 50 watts and increasing to 100 watts after 30 minutes, this was added to the energy equation via a heat source term. A transient thermal analysis algorithm was used, with a time step of 1 second and 1000 iterations to obtain the temperature field variation over time. The temperature near the device rose from 25 degrees Celsius to 45 degrees Celsius, and the temperature gradient at the top of the chassis was approximately 5 degrees Celsius / meter. Subsequently, combined with dynamic load changes, device power fluctuation data (e.g., power change of ±10 watts every 10 minutes) was input into the model. CFD simulation was used to update the airflow velocity field. Calculations showed that the wind speed locally increased to 2.0 m / s when the heat source intensified, creating a convection enhancement effect. Finally, temperature and velocity distribution cloud maps were extracted using a post-processing module to analyze the heat accumulation area. It was found that the temperature at the rear of the chassis reached a maximum of 48 degrees Celsius. Optimization design could involve adding ventilation holes in this area to reduce the temperature to below 40 degrees Celsius. The above process is completed through automated software calculations. The data are logically interconnected, and the initial field distribution provides the foundation for subsequent dynamic simulations. Changes in heat sources and load fluctuations directly affect the results, ensuring that the simulation accuracy is consistent with actual operation.

[0015] Step S102: Based on the thermal simulation results, an optimization algorithm is used to adjust parameters for areas with uneven airflow distribution. By analyzing the duct geometry and ventilation opening size, the optimized duct structure parameters are determined.

[0016] By utilizing thermal simulation results, airflow distribution data is obtained, and non-uniform regions are initially divided to determine their specific locations. Based on these locations, a genetic algorithm iteratively calculates parameter adjustment schemes to determine initial adjustment directions for the duct geometry and ventilation openings. From these initial adjustment directions, specific modification data for the duct geometry is obtained. Combined with the range of changes in ventilation opening sizes, if the modification data exceeds a preset threshold, constraints are applied to obtain adjustment parameters that meet the constraints. For these adjustment parameters, corresponding combinations of duct geometry and ventilation opening sizes are obtained. Airflow distribution simulation is performed on these combinations using a simulation analysis module to determine the improvement in airflow distribution after simulation. Based on the improvement in airflow distribution after simulation, the improvement magnitude data is obtained. If the improvement magnitude data does not reach the preset target value, a second iterative calculation of the adjustment parameters is performed to obtain a new combination of adjustment parameters. Using this new combination of adjustment parameters, the final duct geometry and ventilation opening size data are obtained. The simulation analysis module is then used to verify the final data and determine the optimized structural parameters. Based on the optimized structural parameters, the corresponding airflow distribution simulation results are obtained, and the final duct structure parameters and simulation results are saved through the data storage module to complete the optimization process.

[0017] Based on the thermal simulation results, the airflow distribution was first analyzed using computational fluid dynamics software. The simulation showed that the airflow velocity in a certain area was only 0.5 m / s, while the target value was 1.2 m / s, indicating a problem of uneven distribution. Next, a genetic algorithm was used for parameter optimization. The objective function was set as airflow velocity uniformity. The initial population contained 50 combinations of duct geometric parameters, such as duct width ranging from 0.3 to 0.8 meters and height ranging from 0.2 to 0.5 meters. After 100 generations of iterative calculations, the optimal solution was selected. The duct width was optimized to 0.6 meters, the height to 0.4 meters, and the airflow velocity increased to 1.1 m / s, close to the target value. Subsequently, the ventilation opening size was adjusted. Finite element analysis was used to mesh the opening area. The initial opening area was 0.1 square meters. Based on the simulation results, the airflow concentration was found to be too high. The algorithm was used to adjust the opening area to 0.15 square meters, and analysis showed that the airflow distribution uniformity improved by 15%, verifying the rationality of the parameters. Finally, based on the optimization results of the duct geometry and ventilation opening dimensions, the final duct structure parameters were determined to be a width of 0.6 meters, a height of 0.4 meters, and an opening area of ​​0.15 square meters. Further thermal simulation confirmed that the overall airflow velocity distribution uniformity reached over 90%, meeting the design requirements. The entire process was automated through algorithms, combining numerical simulation and optimization calculations to form a closed-loop logic, ensuring the scientific nature of parameter adjustments. Simultaneously, it can be linked to subsequent heat load distribution analysis; the optimized duct structure parameters are input into the heat load model to predict equipment operational stability and further verify the optimization effect.

[0018] Step S103: If the local temperature gradient in the optimized duct structure parameters exceeds a preset threshold, the heat transfer path data is fused through iterative calculation. The heat transfer path data includes heat conduction, convection and radiation mechanisms to obtain a corrected airflow velocity vector.

[0019] This technology involves temperature gradient processing and heat transfer fusion in the optimization of duct structure parameters. It involves complex techniques such as iterative calculations. The operational processes, such as thermal mechanism fusion, are not clearly understood, and details of the technical business attributes, such as path data calculations, require further explanation. The technical difficulty is rated as high. Analysis of business attributes reveals that this technology contains unique related business attributes, including duct structure parameters, local temperature gradients, preset threshold judgment, iterative calculation fusion, heat conduction path data, convection mechanism integration, radiative heat path, airflow velocity vector, correction vector output, heat balance adjustment, structural parameter iteration, and uniform temperature distribution. These attributes are correlated. The optimized duct structure parameters are obtained, and the local temperature gradient is extracted from these parameters. By comparing the local temperature gradient with a preset threshold, it is determined whether the preset threshold is exceeded, thus obtaining the judgment result. Based on the judgment result, if the local temperature gradient exceeds a preset threshold, heat conduction mechanism data, convection mechanism data, and radiation mechanism data are obtained from the heat transfer path data. These data are then fused using a weighted average method, where the heat conduction mechanism data is calculated based on the material's thermal conductivity, the convection mechanism data is calculated based on fluid velocity and surface area, and the radiation mechanism data is calculated based on temperature difference and emissivity, resulting in fused heat data. Using this fused heat data, iterative calculations are performed, updating the heat distribution value in each iteration until convergence, determining a heat balance adjustment value. For this heat balance adjustment value, a correction vector is calculated and output, combining the adjustment value with the original vector through vector addition to obtain the corrected airflow velocity vector. Using this corrected airflow velocity vector, the duct structure parameters are adjusted to achieve uniform temperature distribution, resulting in the corrected airflow velocity vector.

[0020] In one implementation, for the optimized duct structure parameters, it is first necessary to assess whether its local temperature gradient exceeds a preset threshold. This assessment process is based on the simulation of heat distribution within the duct. For example, in a ventilation system, duct structure parameters include the channel cross-sectional shape, length, and material thermal conductivity. The temperature field is calculated using numerical simulation software, and the local temperature gradient is defined as the temperature difference between adjacent points divided by the distance. If its value exceeds a preset threshold, such as 5 degrees Celsius per meter, subsequent correction steps are triggered. This judgment ensures that the duct design avoids excessive thermal stress and is suitable for industrial ventilation or air conditioning duct optimization scenarios. Furthermore, this process can be integrated into the overall thermal management system to monitor temperature changes in real time.

[0021] For example, heat transfer path data includes heat conduction, convection, and radiation mechanisms, which need to be explained in detail for fusion calculations. Heat conduction refers to the transfer of heat through the vibration of molecules within a solid material, such as the heat flow between metal plates in the walls of a duct; convection involves the movement of fluids carrying heat, such as the heat exchange between airflow and walls; radiation is the transfer of heat in the form of electromagnetic waves, without a medium, such as the heat radiation from a high-temperature surface to a low-temperature surface. In iterative calculations, data from these mechanisms are fused. First, heat flux data for each mechanism are collected, and then coupled using numerical methods such as the finite volume method. This fusion ensures a comprehensive consideration of heat transfer paths and avoids computational biases caused by a single mechanism.

[0022] In one possible implementation, for a rectangular air duct, the initial heat conduction data is derived from an approximation of Fourier's law, the convection data is based on Newton's law of cooling, and the radiation data is referenced to the Stefan-Boltzmann law, thereby constructing a comprehensive heat path model.

[0023] Specifically, the iterative calculation process is the core step, involving multiple iterations to fuse heat transfer path data to obtain a corrected airflow velocity vector. First, an initial airflow velocity vector is established based on optimized duct parameters, such as an inlet velocity of 2 meters per second. Then, if the local temperature gradient exceeds a threshold, an iterative loop is entered: the current heat fluxes from conduction, convection, and radiation are calculated and fused into total heat transfer path data; based on this, the temperature field is updated, and the velocity vector is corrected, for example, by adjusting the direction and magnitude of the flow velocity using a simplified form of the Navier-Stokes equations. This iteration continues until the temperature gradient converges within the threshold. When applied in data center cooling ducts, this method effectively reduces the temperature in hotspot areas.

[0024] It should be noted that the number of iterations can be set to 10 to 20, depending on the complexity of the air duct. Furthermore, this process can be combined with mesh generation techniques to improve computational accuracy. In a typical scenario, for a curved air duct, the initial vector may cause eddies. After iteration, the vector is adjusted to a more uniform distribution to achieve thermal equilibrium.

[0025] In one embodiment, considering a straight duct scenario, optimization parameters include increasing the insulation layer thickness. If the temperature gradient exceeds a threshold, when fusing heat conduction data, the wall thermal resistance is calculated; under convection mechanisms, the Reynolds number is evaluated to determine turbulence intensity; and for radiation, the surface emissivity is quantified. After iterative calculations, the airflow velocity vector is corrected from uniform flow to gradually varied flow, reducing local overheating. This implementation demonstrates the versatility of the technical solution in simple ducts. Furthermore, the fusion process of heat transfer path data needs to be clearly explained: first, the contribution of each mechanism is quantified; for example, heat conduction path data is obtained by multiplying the temperature gradient by the thermal conductivity to obtain the heat flux density; convection paths involve multiplying the convective heat transfer coefficient by the temperature difference; and radiation paths calculate the net radiative heat flux. During fusion, weighted summation or coupled equations are used for solving, for example, iterative updates in a finite element model. These details ensure calculation accuracy and improve thermal efficiency in high-load ventilation systems.

[0026] Preferably, this method is applied in branch duct scenarios to optimize parameters and adjust the angle of the branch. If the gradient exceeds the threshold, when iteratively fusing data, the convection-dominated path is processed first because the flow velocity changes significantly at the branch. The corrected vector optimization is then applied to achieve flow equalization, making it suitable for building ventilation systems and further extending to multi-story duct design.

[0027] Understandably, the principle of iterative calculation is to gradually approximate the actual heat flow state and correct deviations through feedback loops.

[0028] For example, in a closed duct, initial radiation data might ignore reflections; iterations incorporating multiple reflection paths improve model robustness. This explanation helps understand why fusing multiple mechanisms yields a more accurate airflow velocity vector. In another implementation, for helical ducts, a higher preset threshold, such as 8 degrees Celsius per meter, is set to accommodate curvature effects. The fusion process details: heat conduction is calculated along the helical wall; convection considers centrifugal force effects; and radiation is evaluated based on the apparent factors between surfaces. After iteration, the velocity vector is corrected from axial to include rotational components, demonstrating the flexibility of the approach in complex geometries.

[0029] Specifically, after obtaining the corrected airflow velocity vector, its effect can be verified, for example, by comparing the temperature distribution before and after in a simulation and observing the reduction in hot spots. This objective verification supports the application value of the technical solution, enabling uniform heat dissipation in the same field, such as in the cooling ducts of electronic devices.

[0030] In one embodiment, real-time optimization is performed using sensor data. If the gradient exceeds a threshold, path data is iteratively fused, and a correction vector is used to control the fan speed, further enhancing system responsiveness. This diverse implementation covers different sub-scenarios in the ventilation field, ensuring versatility.

[0031] Step S104: Based on the corrected airflow velocity vector, an optimization algorithm is used to perform multi-objective optimization of the fan layout. By evaluating the airflow distribution and noise level, it is determined whether the dynamic balance condition is met, and the final layout scheme is obtained.

[0032] Based on the corrected airflow vector, a genetic algorithm is used to optimize the fan layout for multiple objectives. The input to this algorithm is the corrected airflow vector and fan position parameters, and the output is the optimized layout configuration, resulting in a preliminary layout distribution. Using this preliminary layout distribution, a uniformity index is obtained from the airflow distribution assessment. The noise level is then determined based on this uniformity index by comparing simulated noise data with a standard value. If the noise level exceeds a preset threshold, the fan position parameters are adjusted accordingly, and an updated layout distribution is obtained through airflow simulation. The updated layout distribution is then used to calculate an energy consumption index, which is obtained by integrating fan power and airflow efficiency. Vibration amplitude monitoring results are then determined, obtained from vibration amplitude monitoring. Based on the vibration amplitude monitoring results, the dynamic equilibrium condition is verified by comparing the vibration amplitude monitoring results with an equilibrium threshold, resulting in the final layout scheme.

[0033] In one implementation, the fan layout is first initialized based on the corrected airflow velocity vector. This initialization may consider the number, position, and angle of the fans; for example, in a computer chassis cooling system, fans are arranged at the rear and sides of the chassis to ensure initial airflow coverage. The airflow velocity vector is a correction value obtained through prior simulation or measurement; it represents the direction and magnitude distribution of airflow in space. Correction allows for a more accurate reflection of the actual flow state, thus providing a reliable basis for subsequent optimization.

[0034] Specifically, an optimization algorithm is used to perform multi-objective optimization of the fan layout. Here, the optimization algorithm can be a genetic algorithm, which iteratively searches for the optimal solution by simulating the natural selection process. During the optimization process, the fan position is used as a variable, and the objective function includes the uniformity of airflow distribution and the reduction of noise level.

[0035] For example, a genetic algorithm first generates an initial population, with each individual representing a layout scheme. Then, new schemes are generated through crossover and mutation operations, and their performance is evaluated based on a fitness function. The principle behind this algorithm is to gradually eliminate schemes with low fitness while retaining those with high fitness, thereby approximating the global optimum. Furthermore, the performance of the layout schemes is quantified by evaluating airflow distribution and noise levels. Airflow distribution evaluation involves calculating the mean and variance of wind speeds in each region, for example, using the finite volume method to simulate the airflow field and obtain statistical data on the velocity vector, ensuring uniform distribution to avoid localized overheating. Noise levels are calculated using acoustic models, such as estimating the turbulent noise generated by fan rotation based on Lighthill acoustic analogy theory, in decibels.

[0036] It should be noted that these assessments incorporate data inputs that have been modified to adjust the airflow velocity vector in order to improve accuracy.

[0037] In one possible implementation, the dynamic equilibrium condition is determined by checking whether the variance of the air volume distribution is lower than a preset threshold and whether the noise level is within an acceptable range.

[0038] For example, if the variance is less than 0.5 m / s² and the noise is below 40 dB, it is considered to be in equilibrium. This criterion ensures the stability of the layout during dynamic operation and avoids failures caused by vibration or unevenness.

[0039] Preferably, in one implementation scenario in the field of ventilation equipment, for the fan layout of server racks, the optimization algorithm can adjust the fan spacing and speed.

[0040] For example, the corrected airflow vector is first input, then the algorithm is run iteratively 50 times, evaluated, and a balance is determined. If the balance is not met, the optimization continues until convergence. This scenario demonstrates the application of the technical solution in a high-load cooling environment.

[0041] Understandably, in another embodiment, the fan layout optimization of a household air conditioning system also uses a particle swarm optimization algorithm instead of a genetic algorithm, based on a correction vector. The principle of the particle swarm optimization algorithm is that particles update their velocity and position by tracking local and global optimal positions, thereby optimizing the fan arrangement to achieve uniform airflow and low noise. Based on the above evaluation and judgment, the final layout scheme is obtained.

[0042] For example, after assessing whether the conditions are met, the specific coordinates and parameters of the fans are output, forming an feasible layout diagram. This approach is universal within the same field and can be applied to cooling systems for electronic devices of different specifications. Furthermore, the technical advantage of this process lies in improving airflow efficiency and reducing noise interference through multi-objective optimization, ensuring long-term stable operation of the system.

[0043] In one embodiment, for the layout of an industrial fan system, the corrected airflow vector is derived from CFD simulation. When determining the dynamic balance after optimization, vibration sensor data can also be incorporated to enhance the comprehensiveness of the assessment.

[0044] For example, in optimization iterations, if the noise level is too high, the fan blade angle can be adjusted to meet the balance condition without changing the position. This flexibility demonstrates the adaptability of the solution.

[0045] Step S105: For the final layout scheme, extract manufacturing parameters from the production database. The manufacturing parameters include material thickness and assembly tolerance. Determine the hole position adjustment value that matches the optimization scheme.

[0046] Manufacturing parameters corresponding to the final layout scheme are obtained from the production database. These parameters include material thickness and assembly tolerance. Material thickness data and assembly tolerance values ​​are obtained by querying parameter correlations. For the material thickness data and assembly tolerance values, a preset threshold is used to determine and optimize the matching logic. If the material thickness data exceeds the preset threshold, the assembly tolerance value is adjusted to achieve scheme compatibility. Based on the scheme compatibility, the precision control mechanism in the production data source is obtained, and the adjustment value generation is determined through parameter correlations. For the generated adjustment value, combined with hole position adjustment calculations and manufacturing parameter queries, hole position adjustment values ​​matching the optimized scheme are obtained.

[0047] In one implementation, for the final layout scheme, manufacturing parameters are first extracted from the production database.

[0048] Specifically, the production database stores various manufacturing-related data, including specifications for various materials and assembly standards. Through a query interface, the system retrieves corresponding parameters, such as material thickness and assembly tolerances, based on the identifier of the layout scheme. These parameters are pre-stored based on historical production records and standard specifications, ensuring an efficient retrieval process.

[0049] It's important to note that data integrity is verified during extraction. If parameters are missing, a supplementary mechanism is triggered to retrieve them from a backup data source, ensuring the accuracy of subsequent steps. This approach is suitable for manufacturing scenarios involving electronic device housings, where layout schemes involve component positioning. Furthermore, the extracted manufacturing parameters include material thickness, which represents the actual dimensions of the material during production. For example, in sheet metal processing, thickness directly affects structural strength. Through database queries, the system obtains the thickness value of a specific material, such as the standard thickness range for aluminum alloy sheets, and compares it with the design requirements in the layout scheme.

[0050] In one possible implementation, if the layout scheme requires high-precision assembly, material data with smaller thickness tolerances should be prioritized. This extraction process helps optimize the production flow and avoids waste caused by parameter mismatches.

[0051] For example, assembly tolerances are extracted as another key parameter to evaluate the gaps between components.

[0052] For example, on a mechanical assembly line, tolerance values ​​define the allowable range of deviations. The system pulls these values ​​from the database and performs a preliminary analysis based on the geometric model of the layout scheme.

[0053] Preferably, if the solution involves the docking of multiple components, tolerance extraction incorporates historical assembly data to calculate the average deviation to support adjustments. This method demonstrates the versatility of parameter extraction within the same manufacturing field, such as automotive parts production, ensuring consistency across different batches. Based on the extracted parameters, hole position adjustment values ​​matching the optimized solution are determined.

[0054] Specifically, the hole position adjustment value is calculated by comparing the extracted parameters with the preset threshold of the optimization scheme. First, the impact of material thickness on the hole position is analyzed; for example, an increase in thickness may require enlarging the hole diameter to accommodate assembly. The system uses a matching algorithm to input the thickness value into the model and output the adjustment amount, such as shifting the original hole position coordinates by 0.5 mm. This determination process emphasizes accuracy and is suitable for precision instrument manufacturing scenarios, where the optimization scheme aims to minimize errors.

[0055] In one embodiment, the determination of the hole position adjustment value further takes into account assembly tolerances.

[0056] For example, if the tolerance is ±0.1 mm, the adjustment value will be used to fine-tune the hole position to ensure that there is no interference during assembly.

[0057] It should be noted that this matching is achieved through iterative calculations. First, an assembly scenario is simulated, then the adjustment effect is verified, thus generating the final value. This detailed process expands the applicability of the solution within the manufacturing field; for example, in the process of drilling holes in circuit boards, the adjusted values ​​directly improve the product yield.

[0058] Understandably, the entire process, from extraction to determination, forms a closed chain, achieving high efficiency and optimization with the support of the production database.

[0059] For example, in a specific scenario, for a phone case layout, after extracting the parameters of an aluminum material with a thickness of 1.2 mm and a tolerance of 0.05 mm, the system calculates an inward adjustment of 0.3 mm for the hole positions to match the bending optimization scheme. This implementation demonstrates the flexibility of the technical solution, enabling its application in different sub-scenarios within the same field, such as the transition from simple components to complex assemblies. Furthermore, in another implementation, if the optimization scheme involves a multi-hole layout, the adjustment values ​​are calculated in batches.

[0060] Specifically, the system first groups the hole positions and then matches them one by one according to the extracted parameters. For example, thickness affects the vertical hole positions, and tolerance affects the horizontal spacing. This batch processing improves efficiency and has advantages in large-scale manufacturing, such as production lines for drilling holes in furniture panels.

[0061] For example, the determination process can incorporate a verification step, such as simulating assembly and checking the effectiveness of the adjusted values. If the match is high, the values ​​are validated; otherwise, iterative optimization is performed. This verification enhances the reliability of the solution and provides multiple implementation paths within the manufacturing field.

[0062] Preferably, the overall technical solution improves manufacturing precision by reducing the error rate in production through parameter extraction and adjustment value determination.

[0063] For example, in practical applications, this method can improve the assembly success rate and ensure the smooth implementation of the layout scheme.

[0064] Step S106: Collect actual operating thermal load data in the prototype chassis through a real-time sensor network. The thermal load data includes temperature readings of the processor and storage components, and obtain a deviation matrix from the thermal simulation results.

[0065] The processor temperature and storage component temperature are collected in the prototype chassis using a real-time sensor network to obtain actual runtime thermal load data. This thermal load data is compared with pre-established thermal simulation results to obtain a calculated temperature deviation. A deviation matrix is ​​constructed based on these calculated temperature deviation values. This construction involves point-by-point subtraction between the calculated temperature deviation values ​​and the corresponding points in the thermal simulation results to generate matrix elements, determining the basis for runtime thermal management adjustments. If the deviation matrix exceeds a preset threshold, cooling component temperature readings are obtained from the prototype chassis environment to obtain a balanced thermal load distribution. This balanced thermal load distribution is then fused with the actual runtime data to obtain a deviation matrix from the thermal simulation results.

[0066] In one implementation, thermal load data during actual operation is acquired in the prototype chassis via a real-time sensor network.

[0067] Specifically, this real-time sensor network may include multiple temperature sensors deployed in key locations within the prototype chassis, such as the processor surface and near storage components, to monitor thermal changes. The sensor network connects to a central control unit, transmitting data wirelessly or via wired connection to ensure real-time data acquisition.

[0068] It should be noted that this network design allows for continuous data acquisition during chassis operation without interfering with normal operation, thereby obtaining accurate thermal load information. Furthermore, the thermal load data includes temperature readings of the processor and storage components.

[0069] For example, during data acquisition, processor temperature readings can be obtained using thermistor sensors, which are directly attached to the processor chip to read real-time temperature values, such as monitoring changes from room temperature to peak temperature under high-load tasks. Storage component temperature readings are obtained using similar sensors placed on the casing of hard drives or solid-state drives to record heat buildup during data write or read operations. This reading acquisition employs a sampling frequency, such as once per second, to capture dynamic thermal fluctuations.

[0070] Preferably, the data undergoes preliminary filtering to remove noise interference and ensure the accuracy of the readings.

[0071] In one possible implementation, a deviation matrix from the thermal simulation results is obtained.

[0072] Specifically, the deviation matrix is ​​generated by comparing actual temperature readings with the results of pre-performed thermal simulations. First, the thermal simulation results are represented as a matrix, where rows correspond to different components such as processors and storage, and columns correspond to simulated temperature values ​​at specific time points or under load conditions. Then, a similar matrix is ​​constructed for the actual readings, for example, an m-row, n-column array, where m is the number of components and n is the number of sampling points. The deviation matrix is ​​then calculated by subtracting the simulation matrix from the actual matrix; each element of the resulting matrix represents the temperature deviation of a specific component under specific conditions.

[0073] Understandably, this matrix calculation process helps quantify the accuracy of the simulation; for example, if the deviation exceeds a threshold, it indicates that the simulation model needs adjustment.

[0074] For example, in a test scenario involving a server prototype chassis, assuming the thermal simulation predicts the processor temperature to be 60 degrees Celsius under full load, while the actual measured reading is 65 degrees Celsius, the corresponding element in the deviation matrix would be 5. This method is applicable to various electronic device prototypes, such as workstations or embedded systems, ensuring the reliability of the thermal management solution. Furthermore, this deviation matrix can be used for subsequent optimization.

[0075] In one embodiment, by analyzing patterns in the matrix, such as identifying areas of high deviation, the thermal design within the chassis can be adjusted, for example, by increasing fan speed or optimizing airflow paths, thereby achieving more precise thermal control. This analytical process objectively reflects the differences between reality and simulation, providing a basis for data-driven improvements.

[0076] Preferably, data is repeatedly collected under different load conditions, such as low-load and high-load scenarios, to generate multiple deviation matrices, demonstrating the versatility of the technical solution. Under low load, the deviation may be small, indicating the accuracy of the simulation in a steady state, while the deviation increases under high load, suggesting the need to strengthen the simulation parameters. This multi-scenario application is limited to the field of electronic hardware testing, ensuring the flexibility of the solution.

[0077] Step S107: Based on the deviation matrix, the thermal simulation model parameters are updated using an optimization algorithm. By comparing the errors before and after the iteration, it is determined whether the deviation has converged, and the refined heat dissipation performance index is obtained.

[0078] Based on the deviation matrix, a genetic algorithm is used to update the thermal simulation parameters. The error difference between iterations is calculated iteratively, where the difference is obtained by subtraction between the current iteration error and the previous iteration error, thus revealing the error convergence trend. For this convergence trend, the iteration deviations are compared, with the absolute value of the difference calculated using an absolute value function. If the deviation decreases, the parameter optimization direction is determined, resulting in a refined parameter set. Thermal distribution data is obtained from the refined parameter set. This data is used to calculate the temperature field distribution using the thermal simulation equation input from the parameter set. Performance deviation quantification is integrated to determine the heat dissipation uniformity and identify heat source distribution characteristics. Based on these heat source distribution characteristics, an extended simulation loop is run. This loop iteratively applies the heat conduction equation to simulate the heat flow path, extracting cooling efficiency values. These efficiency values ​​are obtained by dividing the heat transfer rate by the input power, resulting in optimized heat conduction paths. Based on these optimized paths, an integrated index optimization output is generated. This output adjusts the heat dissipation coefficient based on the path optimization results, resulting in refined heat dissipation performance indicators.

[0079] In one implementation, the deviation matrix is ​​used to represent the difference between the predicted values ​​of the thermal simulation model and the actual measured values.

[0080] Specifically, the matrix is ​​constructed by collecting temperature data points from the operation of electronic devices.

[0081] For example, by comparing the simulated and measured temperatures of multiple heat dissipation nodes point by point, a multidimensional matrix is ​​formed, where each element represents the deviation value of a specific node. Constructing this matrix helps quantify the model's inaccuracies, providing a data foundation for subsequent optimization. In this way, systematic errors in the model under different thermal load conditions can be identified, thus laying the groundwork for parameter adjustment. Furthermore, the process of updating the thermal simulation model parameters using optimization algorithms involves iterative calculations.

[0082] For example, the thermal simulation model can be a heat conduction model based on the finite element method, whose parameters include material thermal conductivity, boundary condition coefficients, etc. Optimization algorithms, such as gradient descent, first calculate the loss function based on the deviation matrix, and then update the parameter values ​​by differentiation.

[0083] In one possible implementation, for simulating heat dissipation in electronic chips, initial parameters are set to standard values, such as thermal conductivity of 150 W / m·K, and then the algorithm iteratively adjusts them to minimize deviations. This update mechanism ensures that the model gradually approximates actual heat dissipation behavior.

[0084] It should be noted that the choice of algorithm depends on the problem size. For example, for high-dimensional parameters, stochastic gradient descent can be used to improve efficiency. Through multiple iterations, the parameters are refined, and the prediction accuracy of the model gradually improves. Based on the above updates, the errors before and after iterations are further compared.

[0085] Specifically, the error is quantified by calculating the norm of the deviation matrix, for example, using the Euclidean norm to assess the overall difference. Before iteration, the error may be large, such as an average difference of 5°C between the initial simulated and measured temperatures; after iteration, through parameter adjustment, the difference is reduced to within 1°C. This comparison process is embedded in a loop, where the simulation is rerun after each update and a new deviation matrix is ​​generated, thus forming a closed-loop feedback.

[0086] In one embodiment, determining whether the deviation has converged is achieved by setting a threshold.

[0087] For example, convergence is considered when the error difference before and after iteration is less than 0.1℃.

[0088] It should be noted that this judgment is based on convergence criteria, such as relative error percentage, to ensure that the optimization process does not loop indefinitely. In the scenario of optimizing the heat dissipation of electronic devices, if convergence is not achieved, iteration continues; once convergence is achieved, the process stops and a refined model is output. This mechanism avoids overcomputation while ensuring the reliability of the results.

[0089] Preferably, the refined heat dissipation performance indicators include thermal resistance and maximum temperature.

[0090] Specifically, by refining the model to simulate the temperature distribution of the equipment under full load, thermal resistance is calculated as a performance quantification, for example, the thermal resistance value is reduced from the initial 0.5K / W to 0.3K / W. This indicator is obtained directly from the optimized parameters, supporting improvements in equipment design.

[0091] For example, in another implementation, for power module heat dissipation within the same electronic domain, the deviation matrix can be extended to consider ambient temperature variables. The optimization algorithm combines genetic algorithms with gradient descent assistance to handle nonlinear parameters. When comparing iterative errors, a weighting factor is introduced to emphasize deviations at key nodes, such as the chip core area. After convergence, the heat dissipation performance index can be used to predict device lifespan, demonstrating the versatility of the technical solution. Further extensions are possible.

[0092] In one possible implementation, the parameter updates of the thermal simulation model can be performed in stages. First, the deviation matrix is ​​preprocessed to filter out noise, and then an optimization algorithm is applied. This staged approach improves robustness, ensuring accurate updates, for example, in noisy industrial electronic environments.

[0093] It is understandable that the logical sequence of the above process begins with the construction of the deviation matrix and ends with the output of the indicators, forming a complete chain. In implementation, the algorithm parameters can be adjusted for different scenarios, such as heat dissipation in mobile devices, to adapt to miniaturization requirements.

[0094] In one embodiment, the results show that this method improves the accuracy of heat dissipation performance indicators by 20%, which helps optimize the thermal management design of electronic products without introducing additional hardware costs. Finally, the combination of multiple implementation methods demonstrates the flexible application of the technical solution in the field of electronic heat dissipation; for example, the diverse selection of initial parameter values ​​further enhances the model's adaptability.

[0095] Step S108: If the refined heat dissipation performance index meets the system stability requirements, the heat dissipation performance index is transmitted to the production process through a feedback loop, and the final chassis manufacturing configuration is determined in conjunction with the automated control system.

[0096] If the refined heat dissipation performance indicators meet the system stability requirements, a feedback loop mechanism is used to transmit the refined heat dissipation performance indicators to the production stage. The integrity of the transmitted data is determined by comparing checksums. Based on the integrity of the transmitted data and combined with preset parameters in the automated control system, chassis manufacturing-related variables are extracted from the transmitted data. The matching degree between the variables is judged to obtain a preliminary manufacturing configuration. Using this preliminary manufacturing configuration, a heat flow simulation tool is incorporated to simulate and calculate the heat distribution in the preliminary manufacturing configuration. The heat flow simulation tool constructs a mesh model based on the finite element method, inputs the variables of the preliminary manufacturing configuration, and outputs the heat flow distribution results. The results are verified to determine the final chassis manufacturing configuration.

[0097] In one implementation, the refined heat dissipation performance metrics are a set of values ​​obtained by processing simulated heat flow data inside the chassis. These metrics include thermal resistance and airflow distribution, and are used to evaluate the chassis's heat dissipation efficiency under high loads.

[0098] Specifically, this refining process first collects raw simulation data, such as temperature field data generated by finite element analysis software, and then applies filtering algorithms to remove noise, ensuring the accuracy of the indicators. This processing helps identify potential hotspot areas, thus providing a reliable basis for subsequent stability checks. In the chassis manufacturing industry, this indicator refinement is applicable to the design optimization of desktop computer chassis. Furthermore, system stability requirements refer to a set of preset threshold standards, such as a temperature not exceeding 80 degrees Celsius and noise levels below 40 decibels, which are based on industry standards.

[0099] For example, if the refining parameters show a thermal resistance value below a certain threshold, it is considered to meet the requirements. This inspection process is implemented through a comparison algorithm to ensure that the chassis does not experience overheating or vibration problems during continuous operation, thereby maintaining the overall reliability of the system.

[0100] Preferably, the feedback loop is a mechanism that transmits the required heat dissipation performance indicators back to the production process. Specifically, the feedback loop involves a data interface module that uses a real-time communication protocol to send the indicators from the evaluation system to the manufacturing control center.

[0101] For example, on a chassis production line, if the indicators show good heat dissipation performance, the system will automatically trigger a parameter adjustment signal. This cyclical design forms a closed-loop control, enabling iterative optimization of the manufacturing process and avoiding errors caused by manual intervention.

[0102] In one possible implementation, the feedback loop also includes an error detection step, retransmitting data to ensure integrity if data loss occurs during transmission. This mechanism is particularly useful in mass production of chassis, as it can improve efficiency.

[0103] It should be noted that the automated control system is the core framework integrated into the production process. It combines sensors and actuators to process the incoming heat dissipation performance indicators.

[0104] Specifically, the system first analyzes the feedback data, such as converting thermal resistance values ​​into manufacturing parameters like fan mounting positions. Then, using a preset control strategy, such as a PID algorithm, the system calculates adjustment values ​​and applies them to the robotic arm on the production line. The principle behind this strategy is to dynamically respond to changes in input, ensuring the accuracy of the output configuration.

[0105] For example, during chassis assembly, if indicators suggest the need for enhanced ventilation, the system automatically modifies the design of the side panel apertures. Furthermore, the system can be extended to different chassis types, such as server chassis, where the control framework adjusts strategy details based on load type. This automated approach not only achieves seamless integration but also handles multivariate optimization, ensuring adaptability of manufacturing configurations. In the chassis manufacturing field, this system is suitable for various scenarios from prototyping to mass production, providing a flexible path to configuration determination.

[0106] In one embodiment, the final chassis manufacturing configuration is determined by combining the above-mentioned indicators and system outputs.

[0107] Specifically, the automated control system generates configuration schemes, including material selection such as aluminum alloy casing and internal layout optimization.

[0108] For example, if the cooling specifications indicate a high fan speed requirement, a multi-fan configuration will be prioritized. This decision-making process involves a decision engine that evaluates multiple options based on a rule base and outputs a final blueprint.

[0109] For example, in desktop chassis production, the engine takes cost factors into account to generate a configuration that balances performance and economy. The technical advantage of this approach is that it improves the overall durability of the chassis and reduces rework later on.

[0110] Understandably, in another implementation, the feedback loop can be combined with a machine learning model to predict potential stability problems.

[0111] Specifically, model training uses historical thermal data to learn the correlation between metrics and stability, and then generates prediction reports during transmission. This extension enhances the system's predictability and is suitable for high-end customized scenarios in chassis manufacturing. Furthermore, for the implementation of automated control systems, redundancy mechanisms can be introduced to improve reliability.

[0112] For example, the system is equipped with a backup communication channel. If the primary channel fails, the system switches to ensure uninterrupted transmission of metrics. This design maintains continuity in the production process.

[0113] In one embodiment, the processing of refinement metrics may employ parallel computing to accelerate the data refinement process.

[0114] Specifically, multi-threading technology is used to process different heat flux parameters simultaneously, improving efficiency and making it suitable for large-scale chassis production.

[0115] Preferably, once the final configuration is determined, the results can be displayed through a visual interface for easy operator review. This auxiliary function ensures a combination of human supervision and automation in chassis manufacturing.

[0116] The above description of the embodiments is only for the purpose of helping to understand the technical solutions and core ideas of this application; those skilled in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for intelligently optimizing the heat dissipation performance of a computer case, characterized in that, include: Thermal simulation results containing dynamic load changes are obtained through thermal simulation. Based on the thermal simulation results, an optimization algorithm is used to adjust the air duct structure parameters to obtain optimized air duct structure parameters. If the local temperature gradient in the optimized air duct structure parameters exceeds a preset threshold, heat transfer path data is fused to obtain a corrected airflow velocity vector. Based on the corrected airflow velocity vector, an optimization algorithm is used to perform multi-objective optimization of the fan layout to obtain a final layout scheme. For the final layout scheme, hole position adjustment values ​​matching the optimized scheme are determined. Thermal load data from actual operation is collected through a real-time sensor network to obtain a deviation matrix from the thermal simulation results. Based on the deviation matrix, an optimization algorithm is used to update the thermal simulation model parameters to obtain refined heat dissipation performance indicators. If the refined heat dissipation performance indicators meet the system stability requirements, the heat dissipation performance indicators are transmitted to the production stage to determine the final chassis manufacturing configuration.

2. The intelligent optimization method for heat dissipation performance of a computer chassis as described in claim 1, characterized in that, The process of obtaining thermal simulation results that include dynamic load changes through thermal simulation includes: acquiring initial airflow velocity field and initial temperature distribution data from a 3D chassis model to construct a basic dataset; extracting dynamic change characteristics of the heat source based on the basic dataset and runtime heat source data to determine the heat source change pattern over time; introducing dynamic load change parameters to construct a load change simulation scenario for the heat source change pattern over time to obtain heat distribution and airflow adjustment data under load changes; updating the airflow velocity field and temperature field data using the heat distribution and airflow adjustment data under load changes using the finite element analysis method to obtain intermediate thermal simulation results; analyzing the impact of dynamic changes of the heat source on the airflow velocity field based on the intermediate thermal simulation results to determine whether the heat distribution exceeds a preset threshold range; if it does, making local adjustments to the airflow velocity field to determine the adjusted field distribution data; and generating the final thermal simulation result by combining the adjusted field distribution data with the load change simulation scenario.

3. The intelligent optimization method for heat dissipation performance of a computer chassis as described in claim 1, characterized in that, The step of adjusting the duct structure parameters using an optimization algorithm based on the thermal simulation results to obtain optimized duct structure parameters includes: obtaining airflow distribution data from the thermal simulation results and initially dividing the uneven region to obtain uneven distribution location information; using a genetic algorithm to iteratively calculate the parameter adjustment scheme based on the uneven distribution location information to determine the initial adjustment direction for the duct geometry and ventilation openings; obtaining duct geometry modification data from the initial adjustment direction and judging by the range of ventilation opening size changes; if the modification data exceeds a preset threshold range, constraining the modification data to obtain adjustment parameters that meet the constraint conditions; obtaining a corresponding combination scheme of duct geometry and ventilation opening size for the adjustment parameters, and performing airflow distribution simulation analysis on the combination scheme to determine the improvement of airflow distribution after simulation; obtaining improvement magnitude data based on the improvement of airflow distribution after simulation; if the improvement magnitude data does not reach a preset target value, performing a second iterative calculation on the adjustment parameters to obtain a new combination of adjustment parameters; obtaining the final duct geometry and ventilation opening size data through the new combination of adjustment parameters, and verifying the final data to determine the optimized duct structure parameters.

4. The intelligent optimization method for heat dissipation performance of a computer chassis as described in claim 1, characterized in that, The step of fusing heat transfer path data to obtain a corrected airflow velocity vector if the local temperature gradient in the optimized duct structure parameters exceeds a preset threshold includes: extracting the local temperature gradient from the optimized duct structure parameters and comparing the local temperature gradient with a preset threshold to determine whether it exceeds the preset threshold; if the local temperature gradient exceeds the preset threshold according to the determination result, obtaining heat conduction mechanism data, convection mechanism data, and radiation mechanism data from the heat transfer path data; fusing the heat conduction mechanism data, convection mechanism data, and radiation mechanism data by weighted averaging, wherein the heat conduction mechanism data is calculated based on the material's thermal conductivity, the convection mechanism data is calculated based on fluid velocity and surface area, and the radiation mechanism data is calculated based on temperature difference and emissivity to obtain fused heat data; processing the fused heat data through iterative calculation, wherein the heat distribution value is updated in each iteration until convergence is determined to determine the heat balance adjustment value; calculating a corrected vector based on the heat balance adjustment value and the airflow velocity vector, and integrating the adjusted value with the original vector through vector addition to obtain the corrected airflow velocity vector.

5. The intelligent optimization method for heat dissipation performance of a computer chassis as described in claim 1, characterized in that, The step of using an optimization algorithm to perform multi-objective optimization of the fan layout based on the corrected airflow velocity vector to obtain the final layout scheme includes: using a genetic algorithm to perform multi-objective optimization of the fan layout based on the corrected airflow velocity vector, wherein the genetic algorithm inputs are the corrected airflow velocity vector and fan position parameters, and the output is the optimized layout configuration to obtain a preliminary layout distribution; obtaining a uniformity index from the airflow distribution evaluation based on the preliminary layout distribution, judging the noise level value based on the uniformity index by comparing the noise simulation data with the standard value to obtain the noise level value; if the noise level value exceeds a preset threshold, adjusting the fan position parameters based on the noise level value and obtaining an updated layout distribution through airflow simulation; obtaining the energy consumption index based on the updated layout distribution, determining the vibration amplitude monitoring result by integrating fan power and airflow efficiency; verifying the dynamic balance condition based on the vibration amplitude monitoring result, obtaining the final layout scheme by checking the vibration amplitude monitoring result and comparing it with the balance threshold.

6. The intelligent optimization method for heat dissipation performance of a computer chassis as described in claim 1, characterized in that, The process of determining the hole position adjustment value that matches the optimized scheme for the final layout scheme includes: obtaining the manufacturing parameters corresponding to the final layout scheme from the production database, wherein the manufacturing parameters include material thickness and assembly tolerance; obtaining material thickness data and assembly tolerance values ​​by querying parameter correlation relationships; using a preset threshold to judge the optimization matching logic for the material thickness data and assembly tolerance values; if the material thickness data exceeds the preset threshold, adjusting the assembly tolerance value to obtain scheme compatibility; obtaining the precision control mechanism in the production data source according to the scheme compatibility; determining the generation of adjustment values ​​through parameter correlation relationships; and combining the hole position adjustment calculation and manufacturing parameter query to obtain the hole position adjustment value that matches the optimized scheme.

7. The intelligent optimization method for heat dissipation performance of a computer chassis as described in claim 1, characterized in that, The step of obtaining a deviation matrix from the thermal simulation results by acquiring actual runtime thermal load data through a real-time sensor network includes: acquiring processor temperature readings and storage component temperatures in the prototype chassis through a real-time sensor network to obtain actual runtime thermal load data; comparing the thermal load data with the thermal simulation results to obtain a calculated temperature deviation value; constructing a deviation matrix based on the calculated temperature deviation value and generating matrix elements by point-by-point subtraction between the calculated temperature deviation value and the corresponding points of the thermal simulation results to determine the basis for runtime thermal management adjustments; if the deviation matrix exceeds a preset threshold, obtaining cooling component temperature readings from the prototype chassis environment to obtain a balanced thermal load distribution; and fusing the actual runtime data with the balanced thermal load distribution to obtain a deviation matrix from the thermal simulation results.

8. The intelligent optimization method for heat dissipation performance of a computer chassis as described in claim 1, characterized in that, The process of updating the thermal simulation model parameters using an optimization algorithm based on the deviation matrix to obtain refined heat dissipation performance indicators includes: updating the thermal simulation model parameters using a genetic algorithm based on the deviation matrix; calculating the error difference between iterations by subtraction to obtain the error convergence trend; comparing the deviations between iterations based on the error convergence trend, where the absolute value of the difference is calculated using an absolute value function, and if the deviation decreases, determining the parameter optimization direction to obtain a refined parameter set; obtaining heat distribution data from the refined parameter set; calculating the temperature field distribution by inputting the parameter set into the thermal simulation equation; quantifying the performance deviation to determine the heat dissipation uniformity and identifying the heat source distribution characteristics; running an extended simulation loop based on the heat source distribution characteristics; simulating the heat flow path using the heat conduction equation through multiple iterations; extracting the cooling efficiency value; obtaining the heat conduction path optimization by dividing the heat transfer rate by the input power; integrating the optimized indicators based on the heat conduction path optimization; adjusting the heat dissipation coefficient based on the path optimization results to obtain refined heat dissipation performance indicators.

Images