CN-122018656-A - Intelligent optimization method for heat dissipation performance of computer case

CN122018656ACN 122018656 ACN122018656 ACN 122018656ACN-122018656-A

Abstract

The invention relates to an intelligent optimization method of heat dissipation performance of a computer case in the technical field of new generation information, which comprises the steps of obtaining a thermal simulation result containing dynamic load change through thermal simulation, adjusting air duct structural parameters by adopting an optimization algorithm according to the thermal simulation result to obtain optimized air duct structural parameters, fusing heat transfer path data to obtain corrected airflow velocity vectors if local temperature gradients in the optimized air duct structural parameters exceed a preset threshold value, carrying out multi-objective optimization on fan layout by adopting an optimization algorithm according to the corrected airflow velocity vectors to obtain a final layout scheme, determining hole position adjustment values 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 an offset matrix with the thermal simulation result, and updating the thermal simulation model parameters by adopting the optimization algorithm according to the offset matrix to obtain a refined heat dissipation performance index.

Inventors

WANG KAI
KUANG JIANMIN

Assignees

东莞市展誉科技有限公司

Dates

Publication Date: 20260512
Application Date: 20260126

Claims (8)

1. The intelligent optimization method for the heat dissipation performance of the computer case is characterized by comprising the steps of obtaining a thermal simulation result containing dynamic load change through thermal simulation, adjusting air duct structural parameters according to the thermal simulation result by adopting an optimization algorithm to obtain optimized air duct structural parameters, fusing heat transfer path data to obtain corrected airflow velocity vectors if local temperature gradients in the optimized air duct structural parameters exceed a preset threshold value, carrying out multi-objective optimization on fan layout according to the corrected airflow velocity vectors to obtain a final layout scheme, determining hole position adjustment values 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 with the thermal simulation result, updating the thermal simulation model parameters according to the deviation matrix to obtain refined heat dissipation performance indexes, and transmitting the heat dissipation performance indexes to a production link to determine final case manufacturing configuration if the refined heat dissipation performance indexes meet system stability requirements.
2. The intelligent optimization method for the heat dissipation performance of the computer case according to claim 1 is characterized by comprising the steps of obtaining a thermal simulation result containing dynamic load variation through thermal simulation, obtaining an initial airflow velocity field and initial temperature distribution data from a three-dimensional model of the case to construct a basic data set, extracting dynamic change characteristics of a heat source according to the heat source data when the basic data set is combined with the heat source data in operation to determine a time change mode of the heat source, introducing dynamic load change parameters into the time change mode of the heat source to construct a load change simulation scene to obtain thermal distribution and airflow adjustment data under the load change, updating airflow velocity field and temperature field data through the thermal distribution and the airflow adjustment data under the load change by adopting a finite element analysis method to obtain an intermediate thermal simulation result, analyzing the influence of the dynamic change of the heat source on the airflow velocity field according to the intermediate thermal simulation result to judge whether the thermal distribution exceeds a preset threshold range, locally adjusting the airflow velocity field to determine adjusted field distribution data if the thermal distribution exceeds the preset threshold range, and combining the load change simulation scene to generate a final thermal simulation result.
3. The intelligent optimization method for the heat dissipation performance of the computer case according to claim 1 is characterized in that the method comprises the steps of adjusting air duct structural parameters by adopting an optimization algorithm according to the thermal simulation result to obtain optimized air duct structural parameters, obtaining air flow distribution data from the thermal simulation result, carrying out preliminary division on uneven areas to obtain uneven distribution position information, carrying out iterative computation on parameter adjustment schemes according to the uneven distribution position information to determine preliminary adjustment directions for air duct geometric shapes and ventilation openings, obtaining air duct geometric shape modification data from the preliminary adjustment directions, carrying out constraint processing on the modification data to obtain adjustment parameters meeting constraint conditions if the modification data exceeds a preset threshold range in combination with a ventilation opening size change range, obtaining corresponding air duct geometric shapes and ventilation opening size combination schemes through simulation analysis to determine simulated air flow distribution improvement conditions of the combination schemes, obtaining improvement amplitude data according to the simulated air flow distribution improvement conditions, carrying out secondary iterative computation on adjustment parameters to obtain new adjustment parameter combinations if the improvement amplitude data do not reach preset target values, obtaining final air duct geometric shapes and final air duct opening size adjustment parameters through the new adjustment parameter combinations, and carrying out verification on the final air duct structural optimization parameters.
4. The intelligent optimization method of the heat dissipation performance of a computer case according to claim 1, wherein the method is characterized in that if a local temperature gradient in the optimized air duct structural parameter exceeds a preset threshold value, heat transfer path data are fused to obtain a corrected airflow velocity vector, the method comprises the steps of extracting the local temperature gradient from the optimized air duct structural parameter, judging whether the local temperature gradient exceeds the preset threshold value by comparing the local temperature gradient with the preset threshold value to obtain a judging result, acquiring heat transfer mechanism data, convection mechanism data and radiation mechanism data from the heat transfer path data according to the judging result if the local temperature gradient exceeds the preset threshold value, fusing the heat transfer mechanism data, the convection mechanism data and the radiation mechanism data in a weighted average mode, calculating the radiation mechanism data based on a fluid velocity and a surface area by using the fused heat data, processing the fused heat data by iterative calculation, updating a heat distribution value until convergence is determined, combining the heat balance adjustment value with the airflow velocity vector, calculating a corrected airflow velocity vector by integrating a vector and a vector, and obtaining the corrected airflow velocity vector by using the vector.
5. The intelligent optimization method for the heat dissipation performance of the computer case according to claim 1 is characterized in that the method comprises the steps of carrying out multi-objective optimization on a fan layout by adopting an optimization algorithm according to the corrected airflow velocity vector to obtain a final layout scheme, carrying out multi-objective optimization on the fan layout by adopting a genetic algorithm according to the corrected airflow velocity vector, wherein the genetic algorithm is input into the corrected airflow velocity vector and output of fan position parameters to obtain a preliminary layout distribution, obtaining a uniformity index from air volume distribution evaluation through the preliminary layout distribution, judging a noise level value according to the uniformity index, obtaining a noise level value by comparing noise simulation data with a standard value, adjusting fan position parameters according to the noise level value if the noise level value exceeds a preset threshold value, obtaining updated layout distribution through air flow simulation, obtaining updated layout distribution calculation energy consumption indexes, obtaining vibration amplitude monitoring results by integrating fan power and air flow efficiency, verifying dynamic balance conditions according to the vibration amplitude monitoring results, and obtaining the final layout scheme by comparing vibration amplitude monitoring results with a balance threshold value.
6. The intelligent optimization method for the heat dissipation performance of the computer case according to claim 1, wherein the determining of the hole site adjustment value matched with the optimization scheme for the final layout scheme is characterized by comprising the steps of obtaining manufacturing parameters corresponding to the final layout scheme from a production database, wherein the manufacturing parameters comprise material thickness data and assembly tolerance values obtained by inquiring parameter association relations, judging optimization matching logic for the material thickness data and the assembly tolerance values by a preset threshold value, adjusting the assembly tolerance values to obtain scheme compatibility if the material thickness data exceeds the preset threshold value, determining adjustment value generation by parameter association relations according to an accuracy control mechanism in a scheme compatibility obtaining production data source, and generating the hole site adjustment value matched with the optimization scheme by combining hole site adjustment calculation and manufacturing parameter inquiry for the adjustment value.
7. The intelligent optimization method for the heat dissipation performance of the computer case according to claim 1 is characterized in that the method comprises the steps of acquiring heat load data in actual operation through a real-time sensor network to obtain a deviation matrix with a thermal simulation result, acquiring processor temperature readings and storage component temperatures in a prototype case through the real-time sensor network to obtain the heat load data in actual operation, comparing the heat load data with the thermal simulation result to obtain a temperature deviation calculated value, constructing a deviation matrix according to the temperature deviation calculated value, generating matrix elements through point-by-point subtraction of the temperature deviation calculated value and the thermal simulation result to determine a thermal management adjustment basis in operation, acquiring cooling component temperature readings from the prototype case environment to obtain thermal load balance distribution if the deviation matrix exceeds a preset threshold, and fusing the actual operation data to obtain the deviation matrix with the thermal simulation result.
8. The intelligent optimization method of the heat dissipation performance of the computer case according to claim 1 is characterized in that the method comprises the steps of updating parameters of a thermal simulation model by an optimization algorithm according to a deviation matrix to obtain refined heat dissipation performance indexes, updating parameters of the thermal simulation model by a genetic algorithm according to the deviation matrix, obtaining error convergence trends by calculating the difference between a current iteration error and a previous iteration error through subtraction operation, comparing the iteration errors before and after the error convergence trends, determining parameter optimization directions to obtain refined parameter groups if the deviation is reduced by absolute value function calculation of the absolute value of the deviation, obtaining heat distribution data from the refined parameter groups, inputting the heat distribution data into the thermal simulation equation through parameter groups, calculating temperature field distribution fusion performance deviation quantification, judging heat dissipation balance, determining heat source distribution characteristics by using a thermal conduction equation simulation heat flow path through multiple iterations to extract cooling efficiency values, obtaining heat conduction path optimization by dividing heat transfer rates by input power, and obtaining refined performance indexes according to heat conduction path optimization integration index optimization output.

Description

Intelligent optimization method for heat dissipation performance of computer case Technical Field The invention relates to the technical field of new generation information, in particular to an intelligent optimization method for heat dissipation performance of a computer case. Background The heat dissipation performance of the computer case is critical to the service life of hardware and the stability of a system, and particularly in the background of increasing high-performance computing demands, the advantages and disadvantages of heat dissipation design directly determine the competitiveness of products. As the user demand for high-end and smart chassis increases, the heat dissipation system needs to cope with more complex operating environments and higher power hardware. However, the current heat dissipation test and production method have significant drawbacks, and it is difficult to meet the requirement of the modern computing device on efficient heat dissipation, and an optimization scheme capable of tightly combining design and manufacture is needed. The existing heat dissipation test method is mostly dependent on simplified experimental environments, such as wind tunnel test or thermal imaging analysis, and is difficult to accurately reflect dynamic thermal load change of the chassis in actual use. For example, some tests focus only on static airflow distribution, ignoring the complex effects of power fluctuations when the hardware is running. In addition, the heat dissipation design is disjointed from the production process, and the test data cannot directly guide the adjustment of the manufacturing link, so that the produced chassis may have a problem of local overheating. In the traditional design, the positions of the radiating holes and the fan layout are based on experience, data-driven optimization is lacked, hot spot areas are easy to form, and radiating efficiency is reduced. The core technical difficulty is how to realize the accurate control of the air flow distribution and the dynamic balance of heat transfer. The uneven air flow distribution directly affects the heat dissipation effect in the case, and if the air speed is too low or the air duct is improperly designed, a local area is easy to form a high-temperature area. For example, in high load operation, the air flow rates in different areas inside the chassis may vary greatly, resulting in insufficient air flow around certain hardware components and heat being unable to dissipate in time. This uneven airflow distribution further exacerbates heat transfer instability, particularly when the power is on or off or the load is suddenly changed, and the heat dissipation system is difficult to respond quickly, resulting in severe temperature fluctuations, which affect hardware life. Therefore, how to dynamically adjust the airflow distribution and the heat transfer path through real-time data feedback in the design and the production to adapt to the heat dissipation requirements under different load scenes becomes a key problem of improving the heat dissipation performance of the chassis. Disclosure of Invention The invention provides an intelligent optimization method for heat dissipation performance of a computer case, which mainly comprises the following steps: The method comprises the steps of obtaining a thermal simulation result containing dynamic load change through thermal simulation, adjusting air duct structural parameters according to the thermal simulation result to obtain optimized air duct structural parameters, fusing heat transfer path data to obtain corrected airflow velocity vectors if local temperature gradients in the optimized air duct structural parameters exceed a preset threshold value, carrying out multi-objective optimization on fan layout according to the corrected airflow velocity vectors to obtain a final layout scheme, determining hole position adjustment values matched with the optimization scheme according to the final layout scheme, acquiring heat load data in actual operation through a real-time sensor network to obtain a deviation matrix with the thermal simulation result, updating the thermal simulation model parameters according to the deviation matrix to obtain refined heat dissipation performance indexes, and transmitting the heat dissipation performance indexes to production links to determine final chassis manufacturing configuration if the refined heat dissipation performance indexes meet system stability requirements. The method comprises the steps of obtaining a thermal simulation result containing dynamic load change through thermal simulation, obtaining an initial airflow velocity field and initial temperature distribution data from a chassis three-dimensional model to construct a basic data set, extracting heat source dynamic change characteristics according to heat source data when the basic data set is combined and operated to determine a heat source time change mode, building a load ch