Method for processing a heat sink based on force-thermal balance and heat sink

Abstract

The application relates to a heat dissipation device processing control method and a heat dissipation device based on force-heat balance in the field of information technology, and comprises the following steps: acquiring real-time force values and heat distribution parameters in a processing device through a data acquisition system, and constructing a force-heat coupling model to determine an initial state of force-heat balance; judging stress concentration risks of key positions and determining risk region coordinates according to the initial state of force-heat balance; analyzing heat transmission uniformity and predicting material deformation trends for the risk region coordinates to obtain a deformation compensation vector; adjusting processing precision parameters through the deformation compensation vector, combining cutting speed and feed amount factors to generate an adjusted cutting path planning; acquiring the adjusted cutting path planning, analyzing structure defect occurrence probability and evaluating defect suppression effects; and according to the final processing control sequence, distinguishing material deformation types and determining an optimized heat management scheme.

Description

Technical Field

[0001] This invention relates to the field of information technology, and in particular to a method for controlling the processing of heat sinks based on force-thermal balance, and a heat sink thereof. Background Technology

[0002] In modern electronic equipment and industrial fields, the performance of heat sinks directly affects the stable operation and lifespan of systems, making their importance self-evident. As a critical thermal management component, heat sinks need to efficiently dissipate the heat generated by the equipment to avoid performance degradation or damage caused by overheating. Especially in high-power equipment, the design and manufacturing process of heat sinks have a significant impact on overall efficiency, becoming a core focus of technological innovation in the industry.

[0003] However, current radiator manufacturing methods have revealed numerous limitations in practical applications. Many traditional processes, while pursuing efficiency, often neglect the comprehensive impact of the manufacturing process on material properties and product consistency. Especially when manufacturing radiators with complex structures, insufficient process control can lead to microscopic quality problems, affecting not only heat dissipation but also potentially causing long-term issues. More importantly, existing methods often fall short when facing high-precision requirements due to a lack of dynamic adjustments to machining details, making it difficult to meet the higher performance demands of modern equipment. Focusing on specific technical challenges, a prominent challenge in radiator manufacturing lies in controlling the cutting process. The interaction of force and heat during cutting can cause uncontrollable deformation of the material surface, especially when machining small structures. This deformation can directly disrupt the radiator's design shape and affect the uniformity of heat conduction.

[0004] Furthermore, this imbalance of force and heat can concentrate in certain critical areas, such as the root region where the heat sink connects to the substrate, leading to excessive local stress and even micro-cracks. This phenomenon is particularly noticeable when manufacturing high-density heat dissipation structures. For example, in scenarios requiring densely arranged heat sinks, stress issues in the root region can significantly reduce the product's durability.

[0005] Therefore, how to effectively balance the distribution of cutting force and heat during the processing, while avoiding structural defects caused by stress concentration in key parts, has become a key issue in improving the quality and reliability of radiators. Summary of the Invention

[0006] This invention provides a method for controlling the fabrication of a heat sink based on force-thermal balance, mainly including:

[0007] Real-time force and heat distribution parameters in the processing equipment are acquired through a data acquisition system to construct a force-thermal coupling model to determine the initial state of force-thermal equilibrium. Based on the initial state of force-thermal equilibrium, the stress concentration risk in key areas is assessed and the coordinates of the risk areas are determined. For the coordinates of the risk areas, the heat transfer uniformity is analyzed and the material deformation trend is predicted to obtain a deformation compensation vector. The processing accuracy parameters are adjusted using the deformation compensation vector, and combined with cutting speed and feed rate factors, an adjusted cutting path plan is generated. The adjusted cutting path plan is obtained, the probability of structural defects is analyzed, and the defect suppression effect is evaluated. If the defect suppression effect reaches a preset threshold, the force-thermal equilibrium model is updated, incorporating ambient temperature and cooling medium parameters to generate the final processing control sequence. Based on the final processing control sequence, the material deformation type is distinguished, and an optimized thermal management scheme is determined. Furthermore, the step of acquiring real-time force and heat distribution parameters in the processing equipment through a data acquisition system and constructing a force-thermal coupling model to determine the initial state of force-thermal equilibrium includes: acquiring real-time force and heat distribution parameters from the processing equipment and integrating them with vibration signals to form an extended parameter set; calculating the force equilibrium part using the mechanical equilibrium principle and the heat distribution equilibrium part using the thermal equilibrium principle for the extended parameter set, and constructing a force-thermal coupling model; determining a preliminary equilibrium index through the force-thermal coupling model; if the preliminary equilibrium index exceeds a preset threshold, adjusting the heat distribution parameters to obtain a corrected equilibrium index; and judging and determining the initial state of force-thermal equilibrium based on the corrected equilibrium index. Furthermore, the step of judging the stress concentration risk of key parts and determining the coordinates of the risk area based on the initial state of force-thermal equilibrium includes: acquiring the thermal load distribution of key parts through the initial state of force-thermal equilibrium and determining the stress peak value; comparing the stress peak value with a preset threshold to determine whether there is a stress concentration risk and obtaining a risk assessment result; combining the material mechanical properties with the risk assessment result to obtain the boundary range of the risk area and determine the coordinate point set; generating a risk area mapping layer based on the coordinate point set, judging the thermal stress expansion trend, and obtaining the final risk area coordinates. Furthermore, the step of analyzing heat transfer uniformity and predicting material deformation trends for the coordinates of the risk area to obtain a deformation compensation vector includes: extracting the temperature gradient from the coordinates of the risk area and calculating the standard deviation of the temperature gradient to obtain the heat transfer uniformity; if the heat transfer uniformity is lower than a preset threshold, activating the simulation analysis model and predicting deformation by inputting temperature field data using the finite element method; integrating the workpiece geometry and analyzing the material deformation trend using a mesh generation method; calculating the thermal stress distribution mapping using the stress tensor in conjunction with the load conditions; and fusing the coordinates of the risk area through the thermal stress distribution mapping and obtaining the deformation compensation vector using a vector superposition method.Furthermore, the step of adjusting machining accuracy parameters through the deformation compensation vector and generating an adjusted cutting path plan by combining cutting speed and feed rate factors includes: extracting micro-quality influencing factors from the deformation compensation vector, calculating weights using a particle swarm optimization algorithm to obtain an influencing factor set; adjusting machining accuracy parameters using the influencing factor set, incorporating tool wear compensation data to obtain an adjusted machining accuracy parameter set; determining a speed optimization vector by combining cutting speed factors using a vector fusion method; integrating feed rate factors, and activating a vibration suppression vector if the feed rate factors exceed a preset threshold to obtain a comprehensive cutting parameter matrix; and fusing surface roughness optimization data to generate the adjusted cutting path plan using a path simulation method. Furthermore, the step of obtaining the adjusted cutting path plan, analyzing the probability of structural defects, and evaluating the defect suppression effect includes: acquiring product durability simulation data for the adjusted cutting path plan, constructing a material stress distribution simulation using the finite element analysis method to obtain a stress distribution map; extracting the thermal strain coefficient by combining the thermal deformation impact assessment, integrating the stress distribution map using a vector weighted fusion method to determine the comprehensive thermal stress vector; analyzing the comprehensive thermal stress vector using a neural network prediction model to output a set of structural defect probabilities; extracting life curve data by combining fatigue life assessment, and determining the potential impact of defects using an integral fusion method; if the potential impact of defects exceeds a preset threshold, activating the suppression strategy vector and judging the defect suppression effect. Furthermore, if the defect suppression effect reaches a preset threshold, the force-thermal balance model is updated, incorporating ambient temperature and cooling medium parameters to generate the final processing control sequence. This includes: if the defect suppression effect reaches the preset threshold, obtaining heat dissipation simulation results, constructing a heat distribution mesh using finite element analysis to obtain a heat dissipation map; combining vibration attenuation simulation, extracting attenuation coefficients, integrating the heat dissipation map using a weighted average method to determine a vibration-thermal composite vector; updating the force-thermal balance model using the vibration-thermal composite vector, incorporating ambient temperature parameters, and fusing temperature distribution data using a vector superposition method; incorporating cooling medium parameters, extracting flow rate data, and fusing the force-thermal balance model using an integral calculation method to generate the final processing control sequence. Furthermore, the step of distinguishing material deformation types and determining optimized thermal management schemes based on the final processing control sequence includes: extracting key component strengthening instructions from the final processing control sequence, using a support vector machine classification model to distinguish material deformation types, and obtaining deformation classification results; referencing plastic and elastic deformation characteristics, incorporating vibration impact assessment, extracting attenuation coefficients, and determining deformation feature vectors; extracting heat distribution parameters from the deformation feature vectors, integrating them through finite element analysis to obtain a thermal balance model; fusing cooling medium flow data, extracting flow rates, determining deformation suppression thresholds, and determining the optimized thermal management scheme.

[0008] The radiator is manufactured using a radiator processing control method based on force-thermal balance.

[0009] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0010] By real-time acquisition of force and heat distribution parameters in the machining equipment, and combining the principles of mechanical and thermal balance, the initial state of force-thermal balance is determined. An integrated solution is proposed to address stress concentration risks and material deformation problems in key areas of machining. This invention uses a threshold comparison method to determine the coordinates of stress concentration risk areas, combines heat transfer uniformity analysis and simulation models to predict material deformation trends, generates deformation compensation vectors, and optimizes cutting path planning. Simultaneously, this invention integrates durability simulation data and fatigue life assessment to analyze the probability of structural defects, ensuring defect suppression effectiveness. Finally, the force-thermal balance model is updated, incorporating ambient temperature and cooling medium parameters to generate the final machining control sequence and optimize the thermal management scheme. The core innovation of this invention lies in achieving dynamic adjustment of machining accuracy and effective defect suppression through the combination of force-thermal coupling analysis and path optimization, thereby significantly improving workpiece quality and machining stability. Attached Figure Description

[0011] Figure 1 This is a flowchart of the processing control method for a heat sink based on force-thermal balance according to the present invention;

[0012] Figure 2 This is a schematic diagram of step S103 in the processing control method of the heat sink based on force-thermal balance of the present invention.

[0013] Figure 3 This is a schematic diagram of step S104 in the processing control method of the heat sink based on force-thermal balance of the present invention.

[0014] Figure 4 This is a schematic diagram of step S105 in the processing control method of the heat sink based on force-thermal balance of the present invention.

[0015] Figure 5 This is a schematic diagram of step S106 in the processing control method of the heat sink based on force-thermal balance of the present invention. Detailed Implementation

[0016] 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.

[0017] like Figures 1-5 The processing control method for heat sinks based on force-thermal balance in this embodiment may specifically include:

[0018] Step S101: Real-time force and heat distribution parameters are obtained from the processing equipment through the cutting process data acquisition system, and the initial state of force and heat balance is determined by combining the mechanical and thermal balance principles in the field of machining.

[0019] Real-time force and heat distribution parameters are acquired from the machining equipment through a cutting process data acquisition system, and integrated with vibration signals to obtain an extended parameter set. For this extended parameter set, the force equilibrium component is calculated using the principle of mechanical equilibrium, and the heat distribution equilibrium component is calculated using the principle of thermal equilibrium, constructing a force-thermal coupling model to determine preliminary equilibrium indices. If the preliminary equilibrium indices exceed a preset threshold, the heat distribution parameters are adjusted in real time to obtain a corrected equilibrium indices. Based on the corrected equilibrium indices, the initial state of force-thermal equilibrium is determined.

[0020] In one implementation, real-time force and heat distribution parameters are acquired from the machining equipment through a cutting process data acquisition system. This system typically integrates sensors and data transmission modules to monitor dynamic changes during the machining process.

[0021] Specifically, the data acquisition system includes force sensors and infrared thermal imagers mounted on the machine tool. These devices capture force data and heat distribution images between the cutting tool and the workpiece in real time, thus providing basic parameter input. Furthermore, combining the mechanical balance principles of machining, the force parameters are used to calculate the force balance state during the cutting process.

[0022] For example, the principle of mechanical equilibrium, based on Newton's laws of motion, considers a state where the vector sum of cutting force, friction force, and support force is zero. After acquiring real-time force values, the distribution of these forces is analyzed to ensure the system is at its initial equilibrium point. Specifically, the force value data is input into the equilibrium model, where the initial force equilibrium state is determined by comparing the real-time forces with a preset threshold. If the total force vector sum is close to zero, it is considered the initial equilibrium state. When applied in lathe machining scenarios, this method can effectively identify uneven force distribution at the start of cutting.

[0023] Preferably, the integration of the thermal equilibrium principle further enhances the accuracy of process determination. The thermal equilibrium principle refers to the balanced state of heat input and output, which in machining manifests as the dynamic equilibrium between cutting heat generation and heat dissipation.

[0024] For example, heat distribution parameters are analyzed using temperature field data acquired by a thermal imager to calculate heat flux density and temperature gradient in order to assess the thermal equilibrium point.

[0025] Specifically, determining the initial state of thermal equilibrium involves monitoring the diffusion of heat from the cutting zone to the workpiece and tool. If the temperature distribution tends to be uniform and there is no significant heat accumulation, the initial equilibrium is confirmed. Applying this principle helps prevent accuracy losses caused by thermal deformation in milling operations.

[0026] In one possible implementation, the determination of the initial state of force-thermal equilibrium combines the aforementioned mechanical and thermal principles, and parameter fusion is achieved through an integrated algorithm.

[0027] For example, force and heat distribution parameters can be input into a balance assessment module, which first calculates the force balance index, then superimposes the heat balance index, and finally outputs a comprehensive initial state value. In drilling equipment, this method can be used to adjust cutting parameters in real time to ensure stability at the start of machining.

[0028] It should be noted that the real-time performance of the data acquisition system is achieved through a high sampling rate, typically acquiring data multiple times per second to capture instantaneous changes. This real-time acquisition ensures the accuracy of force and heat distribution parameters, providing a reliable basis for subsequent equilibrium determination.

[0029] In one embodiment, the system can adjust the sensor sensitivity to accommodate differences in thermal conductivity for processing different materials such as steel or aluminum alloys, thereby maintaining the consistency of the application of the balance principle.

[0030] Specifically, when determining the initial state of force-thermal equilibrium, practical scenarios in the field of machining, such as CNC machine tool operation, are considered. The process begins with data initialization before cutting starts, acquiring force values ​​and thermal baselines under zero load. Then, deviations are monitored at the start of cutting; if the deviations are within a preset range, the initial equilibrium is established. This method has been tested at various cutting speeds, demonstrating its versatility in high-speed machining. Furthermore, this determination process can be extended to multi-axis machining equipment. In one implementation, by simultaneously acquiring multi-directional force values ​​and three-dimensional heat distribution, extended mechanical and thermal equilibrium principles are applied to calculate the multi-dimensional equilibrium state.

[0031] For example, in a five-axis machine tool, force balance involves the vector synthesis of forces along each axis, while thermal balance is achieved by simulating the heat conduction path to confirm the initial state.

[0032] For example, in precision grinding, this method is applied by using piezoelectric sensors to acquire minute force changes and combining them with a thermocouple array to monitor heat distribution. By using these parameters to determine the initial equilibrium state, vibration and thermal stress can be effectively reduced, thus improving machining quality.

[0033] Understandably, determining this initial state of force-thermal equilibrium provides a foundation for subsequent processing optimization. In practical applications, it enables early intervention in equipment conditions, thereby improving overall processing efficiency and workpiece accuracy. In another embodiment, for end milling, the system can integrate a wireless transmission module to acquire data in an interference-free manner, quickly determine the initial state based on the equilibrium principle, and support applications on continuous production lines.

[0034] Step S102: Based on the initial state of force-thermal balance, a preset threshold comparison method is used to determine whether there is a risk of stress concentration in the key parts, and the coordinates of the risk area are determined in combination with the mechanical properties of the material.

[0035] By obtaining the thermal load distribution of key components from the initial state of mechanical-thermal equilibrium, the peak stress value of the distribution is determined. A preset threshold is used to compare the peak stress value with the stress value to determine whether there is a risk of stress concentration in the key components, thus obtaining a risk assessment result. Combining the material mechanical properties with the risk assessment result, the boundary range of the risk area is obtained, and the coordinate point set of the range is determined. Based on the coordinate point set, a mapping layer of the risk area is generated, and the thermal stress propagation trend in the layer is determined to obtain the final coordinates of the risk area.

[0036] In one implementation, the initial force-thermal equilibrium state of the structural component is first obtained. This state is determined by monitoring external forces and heat distribution.

[0037] For example, in the monitoring of mechanical structures such as bridge supports, the initial state includes the equilibrium torque and temperature distribution of the structure under no additional load.

[0038] It should be noted that the initial state of mechanical and thermal equilibrium refers to the equilibrium point of mechanical stress and thermal stress of a material under static conditions, which can be calculated by collecting data from sensors.

[0039] Specifically, the data acquisition process involves installing strain gauges and temperature sensors at key locations, recording initial readings, and then calculating the overall state value based on the equilibrium equations. This initial state provides a benchmark for subsequent risk assessment, ensuring the accuracy of the analysis. Furthermore, a preset threshold comparison method is used to determine whether there is a risk of stress concentration at key locations.

[0040] For example, the preset threshold can be a stress upper limit set based on historical data, such as 80% of the material's yield strength. The judgment process includes comparing the local stress value in the initial state with the threshold, and if the local stress exceeds the threshold, it is identified as a risk.

[0041] In one possible implementation, this comparison method is achieved through a numerical algorithm. First, the stress distribution of key parts is calculated. For example, multiple monitoring points are selected on the bridge beam to obtain the stress data of each point, and then the stress data is compared point by point.

[0042] It should be noted that stress concentration risk refers to the risk of abnormally high stress in a localized area, which may lead to material fatigue or fracture. Potential problems can be quickly identified through threshold comparison. This method is limited to applications in mechanical structures, such as the periodic inspection of pipes or frames, aiming to detect potential problems early.

[0043] Preferably, after assessing the risk, the coordinates of the risk region are determined by combining the material's mechanical properties. These mechanical properties include elastic modulus, Poisson's ratio, and yield strength, and are used to quantify the boundaries of the risk region.

[0044] Specifically, the process of determining coordinates first selects points that exceed the threshold based on the risk assessment results, and then applies material properties to calculate the stress propagation range.

[0045] For example, in a bridge structure, if there is stress concentration in the middle of the beam, the stress gradient can be calculated using the elastic modulus, and then the x, y, and z coordinates of the risk area can be determined.

[0046] In one embodiment, this calculation involves stress tensor analysis, substituting material properties into the formula to derive coordinate values, ensuring positioning accuracy down to the centimeter level. This approach enhances the reliability of risk assessment and can be applied to different structural types within the same field, such as mechanical component maintenance, while maintaining consistency in the monitoring scenario.

[0047] For example, in practical applications, the initial force-thermal equilibrium state of a steel bridge beam is calculated using ambient temperature and self-weight load. Subsequently, a threshold comparison method is used to check the beam connection points; if the stress value exceeds a preset threshold, such as 200 MPa, a risk is confirmed. Then, combining the mechanical properties of steel, such as the elastic modulus of 210 GPa, the coordinates of the risk area are determined to be at 50% of the beam's length. This embodiment demonstrates the versatility of the technical solution in bridge monitoring, enabling early warning functionality. In another implementation, the acquisition of the initial force-thermal equilibrium state can be extended to dynamic monitoring, such as in mechanical frames, where the initial state includes equilibrium calculations under vibration. Based on this, the threshold comparison method is adjusted to a multi-threshold system, making judgments for different load types. This adjustment improves the method's flexibility, incorporating more material properties, such as the coefficient of thermal expansion, when determining the risk area coordinates, further refining the coordinate calculation process.

[0048] Specifically, the preset threshold for the threshold comparison method can be optimized using empirical data, for example, by pre-setting it in structural simulation software. When determining whether a risk exists in a critical area, the process includes data filtering and anomaly detection. First, noisy data is eliminated, and then the filtered stress value is compared with the threshold. This detailed process ensures the robustness of the judgment and can effectively identify hidden risks when applied in mechanical structures such as tower monitoring. Furthermore, the innovation of determining the coordinates of risk areas by combining material mechanical properties lies in the mapping relationship between properties and coordinates. The specific process is as follows: First, a mathematical model of the material properties is established, such as using Hooke's Law to describe the stress-strain relationship; then, the risk point is input into the model, and the radius of influence is calculated; finally, the specific location in the coordinate system is output.

[0049] For example, in a pipeline structure, if stress concentration is detected at a weld, the risk is extended to a 5-centimeter area by calculating the yield strength, with the coordinates defined as a specific point on the pipeline axis. This explanation clarifies the calculation details and supports the protection scope of the technical solution.

[0050] In one embodiment, the entire process is integrated into a monitoring system, with initial states updated in real time, threshold comparisons performed automatically, and coordinate determination outputting a visual report. This integrated approach demonstrates versatility in the field of mechanical structure maintenance, reducing manual intervention and improving efficiency.

[0051] For example, when monitoring concrete beams, the initial force-thermal equilibrium state takes into account the effects of thermal expansion and contraction, with the threshold set at 70% of the concrete compressive strength. After risk assessment, the coordinates are located at the bottom of the beam based on the modulus attribute. This example covers scenarios involving material variation, maintaining consistency across the domain.

[0052] Preferably, the determination of the risk area coordinates can also incorporate a safety factor adjustment, such as multiplying the material properties by a safety factor of 1.5 to expand the coordinate range. This optional feature enhances the adaptability of the solution and provides a more conservative assessment in practical engineering.

[0053] Step S103: If the heat transfer uniformity is determined to be lower than a preset threshold after the coordinates of the risk area are determined, the material deformation trend is predicted by the simulation analysis model, and the workpiece geometry and load conditions are incorporated to obtain the deformation compensation vector.

[0054] The coordinates of the risk area are obtained, and the temperature gradient is extracted from the heat transfer distribution data. The heat transfer uniformity is obtained by calculating the standard deviation of the temperature gradient. If the heat transfer uniformity is lower than a preset threshold, the simulation analysis model is activated. This simulation analysis model is constructed using the finite element method, with temperature field data as input and deformation prediction as output. The workpiece geometry is incorporated into the simulation analysis model, and a mesh generation method is used to predict the material deformation trend. The load conditions are obtained and incorporated into the material deformation trend. The thermal stress distribution mapping is obtained through stress tensor calculation, where the stress tensor is obtained by multiplying the deformation gradient and modulus based on Hooke's law. The risk area coordinates are fused through the thermal stress distribution mapping, and a deformation compensation vector is obtained using a vector superposition method.

[0055] In one implementation, once the coordinates of the risk area are determined, the heat transfer uniformity is first assessed.

[0056] Specifically, heat transfer uniformity can be calculated by measuring the temperature distribution at multiple points within the risk area. For example, temperature data can be collected using an infrared thermal imager, and the standard deviation of the temperature can be calculated as a uniformity index. If this index is below a preset threshold, such as 0.5 degrees Celsius, it indicates uneven heat transfer, which may lead to stress concentration in the material, thus triggering subsequent deformation prediction steps. This judgment process helps to identify potential problems in processing early and ensure workpiece quality. Furthermore, the material deformation trend is predicted through a simulation analysis model. This model is based on the finite element analysis principle, dividing the risk area into mesh elements and applying a thermal load to each element to simulate the heat transfer process.

[0057] For example, in a metal welding scenario, the model is input with the power and speed of the welding heat source to simulate the process of heat spreading from the weld to the surrounding area, thereby predicting deformation trends, such as the direction and magnitude of bending or twisting. This prediction takes into account the material's coefficient of thermal expansion and modulus of elasticity, avoiding the cost and time consumption of actual experiments.

[0058] In one possible implementation, incorporating the workpiece geometry and load conditions is a key step.

[0059] Specifically, the workpiece geometry can be acquired using a 3D scanner to create a digital model, such as the diameter and height data of a cylindrical workpiece. Then, load conditions, such as external pressure or gravity, are incorporated into the model, and the displacement of the mesh nodes is adjusted through iterative calculations.

[0060] It should be noted that this integration process employs a coupled algorithm, using geometric parameters as boundary conditions and the load as an external force field to progressively solve the deformation equations, thereby generating accurate trend data. In manufacturing, this method is applicable to different workpieces, such as sheet metal or pipes, ensuring the versatility of the predictions.

[0061] Preferably, the deformation compensation vector is obtained based on the above prediction. This vector is represented as a three-dimensional coordinate offset, such as (Δx, Δy, Δz), and is calculated from the model output.

[0062] Specifically, after predicting the deformation trend, the simulation analysis model compares the difference between the ideal shape and the deformed shape, and calculates the compensation value for each key point.

[0063] For example, when processing alloy workpieces in a heat treatment furnace, if a 2mm shrinkage in the z-axis direction is predicted, the compensation vector adjusts the processing parameters accordingly, such as by adding support structures. This vector facilitates subsequent correction operations, improving the workpiece's accuracy and stability.

[0064] For example, in another embodiment, for complex curved workpieces, the simulation analysis model can be extended to nonlinear deformation prediction. When incorporating geometry, parametric modeling tools are used to define the surface equations, and then loading conditions such as vibration loads are applied to predict local deformation trends. The resulting compensation vector covers not only translational components but also rotational components, thus achieving greater adaptability in precision manufacturing.

[0065] Understandably, the technical effect of this process lies in reducing actual deformation defects through simulation. For example, in the machining of aerospace parts, it avoids cracks caused by uneven heating, thereby improving overall reliability. In one implementation, the preset threshold is selected based on the material type; for example, for aluminum alloys, the threshold is set to 1 degree Celsius to match their thermal sensitivity and further optimize the accuracy of the judgment.

[0066] Step S104: Extract the micro-quality influencing factor from the deformation compensation vector, adjust the machining accuracy parameters using an optimization algorithm, and combine the cutting speed and feed rate factors to obtain the adjusted cutting path plan.

[0067] Microscopic quality influencing factors are extracted from the deformation compensation vector. Weights are calculated using a particle swarm optimization (PSO) algorithm with these factors as input. The PSO algorithm iteratively solves the problem using position and velocity updates to obtain a set of microscopic quality influencing factors. Machining accuracy parameters are adjusted using this set of microscopic quality influencing factors. Tool wear compensation data is integrated from a preset tool database to obtain an adjusted set of machining accuracy parameters. This adjusted set of machining accuracy parameters is then combined with a cutting speed factor using a vector fusion method to determine a speed optimization vector. The feed rate factor is integrated using this speed optimization vector. If the feed rate factor exceeds a preset threshold, a vibration suppression vector is activated from a preset vibration database to obtain a comprehensive cutting parameter matrix. Surface roughness optimization is then fused based on this comprehensive cutting parameter matrix. Surface roughness optimization is obtained from a preset roughness database, and an adjusted cutting path plan is obtained using a path simulation method.

[0068] In one implementation, extracting the micro-quality influence factor from the deformation compensation vector first requires decomposing the vector.

[0069] Specifically, the deformation compensation vector is usually represented as a multidimensional offset, such as displacement data in the x, y, and z directions, which originates from the aforementioned simulation analysis. During the extraction process, the vector is decomposed into multiple components, each corresponding to the influence of material microstructures, such as thermal stress components or crystal structure offset components.

[0070] For example, in the heat treatment scenario of metal workpieces, influencing factors, such as the micro-grain size variation factor, are identified by calculating the magnitude and orientation angle of the vector. This factor is obtained through a weighted average of the vector components, ensuring the accuracy of the extraction. This extraction step facilitates targeted adjustments to subsequent parameters. Furthermore, the extraction of micro-quality influencing factors involves specific algorithm implementation.

[0071] In one possible implementation, principal component analysis is used to reduce the dimensionality of the deformation compensation vector. First, the vector is converted into a matrix form, then the eigenvalues ​​and eigenvectors are calculated, and the dominant component is selected as the influencing factor.

[0072] For example, in the processing of welded workpieces, if the vector shows a significant offset along the z-axis, the extracted factors may include a micro-stress factor caused by thermal expansion, which is defined as the ratio of the square root of the offset to the elastic modulus of the material.

[0073] It should be noted that this extraction process takes into account the material's microstructure, such as grain boundary density, and adjusts the factor weights through iterative calculations to avoid extraction bias. In manufacturing applications, this method is suitable for hot bending treatment of sheet metal, ensuring that the factors reflect the true quality impact.

[0074] Preferably, when adjusting the machining accuracy parameters using an optimization algorithm, the extracted microscopic quality influencing factors are used as input.

[0075] Specifically, the optimization algorithm can be a genetic algorithm, which works by iteratively searching for the optimal combination of parameters by simulating the natural selection process. First, a set of precision parameters such as surface roughness threshold and tolerance range are initialized. Then, a fitness function is calculated based on the influence factor. This function measures the degree to which the parameters improve the quality.

[0076] For example, in the machining of precision alloy parts, the algorithm runs through multiple iterations. In each iteration, a new set of parameters is generated through crossover and mutation operations, and finally, the adjusted accuracy value is output. This adjustment process ensures the matching of parameters with microscopic factors.

[0077] In one embodiment, the optimization algorithm's adjustment steps include a detailed iterative mechanism. The algorithm begins by setting an initial population, with each individual representing a set of machining accuracy parameters, such as a roughness of 0.1 micrometers and a tolerance of 0.05 millimeters. Then, an influence factor is used to calculate the fitness value of each individual; for example, fitness is equal to the reciprocal of the factor value and the parameter deviation. Further, high-fitness individuals are retained through a selection operation, and crossover is performed to generate offspring, such as by exchanging roughness and tolerance values. Mutation is then applied to introduce random variations.

[0078] For example, in the hot extrusion of tubing, after running this algorithm for 50 generations, the accuracy parameters are adjusted to accommodate the effects of uneven micrograin size, ensuring consistent processing.

[0079] Understandably, this mechanism provides a system path for parameter optimization.

[0080] Specifically, incorporating cutting speed and feed rate factors involves integrating these machining variables into the adjusted accuracy parameters. In one implementation, cutting speed is defined as the linear velocity of the tool relative to the workpiece, typically expressed in meters per minute, while feed rate refers to the depth of cut per revolution, expressed in millimeters per revolution. These factors are combined with optimization parameters through weighted formulas, such as using speed and feed rate as multipliers to adjust the accuracy threshold.

[0081] For example, when machining metal sheets on a CNC machine tool, if the optimization algorithm outputs a roughness of 0.2 micrometers, then a combined speed of 100 meters per minute and a feed rate of 0.1 millimeters per revolution are used to generate a comprehensive parameter set to ensure the adaptability of the path planning. Furthermore, the adjusted cutting path planning is obtained based on the aforementioned combined results.

[0082] Specifically, path planning involves generating tool motion trajectories using computer-aided design software, inputting adjusted accuracy parameters, cutting speed, and feed rate into a planning model, which uses Bézier curves or non-uniform rational B-spline (NURBS) curves to describe the path.

[0083] For example, in the finishing of a heat-treated workpiece, the planning process first defines the starting and ending points, and then interpolates path points based on speed factors to ensure a smooth transition. This planning step integrates all factors to form a complete machining plan. In another embodiment, for workpieces with complex geometries, such as curved alloy parts, the process of extracting micro-quality influencing factors is extended to consider nonlinear vectors. The deformation compensation vector is analyzed as curvature-related components, and factors such as surface micro-roughness influencing factors are extracted by calculating the second derivative of the vector.

[0084] Specifically, when welding curved surface structures, factor extraction employs a mesh generation method, mapping vectors onto a surface mesh and calculating the average offset of each mesh point as the factor value. This method is suitable for precision manufacturing scenarios, ensuring comprehensive extraction.

[0085] Preferably, the optimization algorithm can use particle swarm optimization when adjusting the machining accuracy parameters. The principle is to update the position and velocity of particles by moving them in the search space based on the global optimum and the individual optimum.

[0086] For example, in metal tube machining, particles are initialized as a precision parameter vector. Based on the micro-factor update rate formula, the process iterates until convergence, outputting a value such as a tolerance adjustment to 0.02 mm. This algorithm provides an efficient adjustment path. Furthermore, this is applied when considering cutting speed and feed rate factors.

[0087] In one possible implementation, response surface methodology is used to analyze the influence of factors. First, a mathematical model of the parameters of speed, feed rate, and accuracy is established, and then the combination is optimized.

[0088] For example, in sheet metal cutting, the speed is set to 150 meters per minute and the feed rate to 0.15 millimeters per revolution. This data is then integrated with adjusted parameters to generate path data, ensuring the accuracy of the plan. In one implementation, the final output of the adjusted cutting path plan is a G-code sequence, generated based on the combined factors.

[0089] Specifically, the planning algorithm traverses the workpiece geometry model and applies speed and feed constraints to calculate the coordinates of each path segment.

[0090] For example, in the processing of hot-bent workpieces, the path starts from the edge and gradually advances along the adjustment precision, forming a closed loop. This output supports direct execution by the machine tool.

[0091] Step S105: For the adjusted cutting path planning, obtain product durability simulation data, analyze the probability of structural defects by predictive model, and judge the defect suppression effect by fatigue life assessment.

[0092] For the adjusted cutting path planning, product durability simulation data is obtained from a preset durability database. A material stress distribution simulation is constructed using finite element analysis (FEM), where the product geometric model is discretized into mesh elements, and the stress value of each element is calculated to obtain a material stress distribution map. The material stress distribution map is obtained, and combined with thermal deformation impact assessment, thermal strain coefficients are extracted from a preset thermal deformation database. A vector weighted fusion method is used to integrate the stress distribution map and thermal strain coefficients. This method assigns weights to each point in the distribution map and multiplies them with the coefficients to determine the comprehensive thermal stress vector. Using this comprehensive thermal stress vector, a neural network prediction model is employed to analyze the probability of structural defects. The neural network prediction model uses the comprehensive thermal stress vector as the input layer, calculates activation functions through hidden layers, and outputs defect probability values ​​to obtain a set of structural defect probabilities. This set of structural defect probabilities is obtained, and combined with fatigue life assessment, life curve data is extracted from a preset fatigue database. An integral fusion method is used to multiply the probability set with the life curve data. This method integrates each probability value in the set with the corresponding point on the curve to determine the potential impact of the defects. Based on the potential impact of the defect, if the potential impact exceeds a preset threshold, the suppression strategy vector is activated, compensation and adjustment data are incorporated from the preset strategy database, and the defect suppression effect is determined.

[0093] In one implementation, for the adjusted cutting path planning, product durability simulation data is first obtained.

[0094] Specifically, this simulation data is generated using finite element analysis software, and numerical simulations are performed based on the geometric model of the cutting path and material properties.

[0095] For example, in the finishing process of heat-treated metal sheets, the adjusted path parameters are input into the simulation environment to calculate the stress distribution data of the workpiece under cyclic loads. These data include strain values ​​and deformation amounts to ensure that the product's durability performance in actual use is reflected.

[0096] It should be noted that the simulation process considers the fatigue characteristics of materials, such as obtaining multiple sets of data points through iterative calculations to form a durability simulation dataset. This acquisition step helps improve the accuracy of subsequent analysis. Furthermore, the probability of structural defects occurring is analyzed using a predictive model. This predictive model typically employs a machine learning framework, such as the random forest algorithm, which works by training on historical defect data to predict the probability distribution under new scenarios.

[0097] Specifically, the model input includes the stress peak and path adjustment parameters from the durability simulation data. First, features are extracted from the data, such as calculating the average stress level, and then the model is trained to output the defect probability value.

[0098] For example, in the machining of welded metal workpieces, if simulation data shows high-stress areas, the model calculates the probability of crack occurrence based on a decision tree set. This probability is defined as the ratio of the weighted sum of defect feature vectors to a threshold. This analytical process ensures a quantitative assessment of potential structural defects.

[0099] Preferably, the defect suppression effect is determined in conjunction with fatigue life assessment. Fatigue life assessment is based on the SN curve method, which estimates the workpiece life using the material fatigue limit and simulated load cycles.

[0100] Specifically, the defect probability output by the prediction model is combined with the lifetime calculation formula, for example, the lifetime value is equal to the material strength divided by the logarithm of the stress amplitude, and then the difference in lifetime before and after adjustment is compared to judge the suppression effect.

[0101] In one possible implementation, for hot extrusion processing of precision alloy parts, the evaluation process first imports simulation data, calculates the cumulative damage value, and if the defect probability is lower than a set threshold, the suppression effect is judged to be positive. This combined approach provides a comprehensive basis for judgment.

[0102] In one embodiment, the process of acquiring product durability simulation data is extended to take into account dynamic load factors.

[0103] Specifically, in the scenario of hot bending of pipes, simulation software simulates the path response under vibration loads, generating data such as displacement time series, and calculating durability indicators through integration methods. This expansion ensures that the data covers a variety of working conditions. Furthermore, the analysis of the predictive model can be replaced by neural networks, which learn nonlinear relationships through multilayer perceptrons, outputting probabilities after inputting simulated data.

[0104] For example, in the welding of curved metal structures, gradient descent is used to optimize parameters during model training, and the probability of defects such as microcracks is analyzed to ensure the robustness of the model.

[0105] Understandably, fatigue life assessment involves setting a threshold. In the finishing of heat-treated workpieces, a life threshold of 10^6 cycles is set. If the calculated value exceeds the threshold and the defect probability is low, the suppression effect is confirmed. This setting enhances the objectivity of the assessment.

[0106] For example, the entire process is integrated and applied when CNC machine tools are used to process sheet metal. First, simulated data is acquired, then probabilities are analyzed and lifespan is assessed, forming a closed-loop judgment. This integration demonstrates the versatility of the technical solution in the manufacturing industry.

[0107] Step S106: If the defect suppression effect reaches a preset threshold, the force-thermal balance model is updated based on the heat dissipation simulation results, incorporating ambient temperature and cooling medium parameters to obtain the final processing control sequence.

[0108] If the defect suppression effect reaches a preset threshold, heat dissipation simulation results are obtained from a preset thermal simulation database. A thermal distribution mesh is constructed using the finite element method (FEM), where the processing geometry model is discretized into element meshes, and the heat value of each element is calculated to obtain a heat dissipation map. The heat dissipation map is obtained, and combined with vibration attenuation simulation, attenuation coefficients are extracted from a preset vibration database. A weighted average method is used to integrate the heat dissipation map and attenuation coefficients, where the weighted average method assigns weights to each point in the map and averages the results with the coefficients to determine the vibration-thermal composite vector. The vibration-thermal composite vector is used to update the force-thermal balance model, incorporating environmental temperature parameters. Temperature distribution data is extracted from a preset environmental database, and the composite vector and temperature distribution data are fused using a vector superposition method, where the vector superposition method adds each component of the vector to the corresponding data value to obtain the updated balance model. The updated equilibrium model is obtained, cooling medium parameters are incorporated, flow rate data is extracted from a preset medium database, and the equilibrium model and flow rate data are fused through an integral calculation method. The integral calculation method performs integral operations on each parameter of the model and the flow rate data. The integral operation uses the parameter value and the flow rate value as integral variables to multiply on the time axis to obtain the final processing control sequence.

[0109] In one implementation, if the defect suppression effect reaches a preset threshold, the subsequent model update process is initiated.

[0110] Specifically, the preset threshold is set based on historical processing data. For example, in the scenario of finishing metal sheets, the threshold is defined as the combination of a defect probability of less than 0.1 and a fatigue life exceeding a specified period. This judgment is made by comparing the evaluation results with the threshold, ensuring the effectiveness of the processing path adjustment.

[0111] It should be noted that this threshold setting takes into account material type and load intensity, providing an objective basis for decision-making. Furthermore, the force-thermal balance model is updated based on the heat dissipation simulation results. This force-thermal balance model is a mathematical framework used to describe the interaction of force and heat during machining. Its principle is to balance the heat generation and dissipation caused by cutting forces through the energy conservation equation.

[0112] Specifically, the simulation results include heat distribution maps and temperature gradient data. First, key indicators such as peak temperature are extracted, and then the model parameters are adjusted to match these data.

[0113] For example, in the machining of heat-treated alloy parts, the update process involves iterative calculations that incorporate simulated heat flow values ​​into the equilibrium equations to ensure the model reflects the actual thermal stress distribution. This update step helps optimize the accuracy of machining parameters.

[0114] Preferably, ambient temperature and cooling medium parameters are incorporated into the updated model. Ambient temperature refers to the external temperature conditions of the processing site, and cooling medium parameters include the type of medium, such as the thermal conductivity and flow rate of water-based coolant. These parameters are added to the model through a weighted integration method, for example, by calculating the correction coefficient for heat dissipation based on ambient temperature and adjusting the balance equations in conjunction with the heat transfer efficiency of the cooling medium.

[0115] In one possible implementation, for hot bending of pipes, the parameter integration process first quantifies the heat capacity of the cooling medium, and then updates the model to simulate the force-thermal interaction at different temperatures, ensuring that the model adapts to various working conditions.

[0116] Understandably, this parameter incorporation enhances the model's robustness in the context of finishing metal curved surface structures.

[0117] For example, by setting the ambient temperature to 20 degrees Celsius and inputting the cooling medium flow rate data, the model calculates the adjusted thermal equilibrium state, providing more accurate processing guidance.

[0118] For example, the final processing control sequence is obtained by processing the output of the updated model.

[0119] Specifically, the sequence includes parameters such as cutting speed, feed rate, and cooling sequence, and is generated based on the force-thermal balance results.

[0120] For example, when machining sheet metal on a CNC machine tool, the sequence generation process involves extracting optimized path data from the model to form an ordered list of control commands. This sequence ensures the stability and efficiency of the machining process.

[0121] In one embodiment, the process is extended to consider the average of multiple sets of simulation results.

[0122] Specifically, in the hot extrusion processing of precision alloy parts, the defect suppression effect is first verified to reach a threshold. Then, multiple rounds of heat dissipation simulation are used to update the model, incorporating varying environmental temperature parameters such as seasonal variations and the viscosity of different cooling media, such as oil-based liquids, to generate the final sequence. This extension demonstrates the flexibility of the technical solution in manufacturing applications. Furthermore, the update of the force-thermal balance model can employ a numerical iterative method, the principle of which is to optimize parameters by minimizing the error between the simulation results and the model predictions.

[0123] For example, in the machining of welded metal workpieces, the iterative process calculates the residual heat dissipation and gradually adjusts the balance coefficient until convergence. This method ensures the accuracy of the updates.

[0124] It should be noted that the inclusion of cooling medium parameters involves thermal convection calculations.

[0125] Specifically, parameters such as the specific heat capacity of the medium are used to estimate the heat transfer rate, and then integrated into the model to form a complete mechanical and thermal description. In the finishing of heat-treated workpieces, this integration process is achieved by simulating temperature decay curves under different media, providing a reliable equilibrium basis.

[0126] In one embodiment, the generation of the final processing control sequence includes a sequence verification step.

[0127] For example, in the finishing process of heat-treated metal sheets, after generating the sequence, its control effect on heat dissipation is checked through simulation to ensure that the sequence meets preset standards. This verification enhances the practicality of the sequence.

[0128] Step S107: Extract key component strengthening instructions from the final processing control sequence, use a classification model to distinguish material deformation types, and determine the optimized thermal management scheme by referring to the characteristics of plastic deformation and elastic deformation.

[0129] Through the final processing control sequence, strengthening instructions for key components are extracted. A support vector machine (SVM) classification model is used to distinguish material deformation types. The SVM classification model takes material deformation type data as input and outputs deformation category to obtain deformation classification results. The deformation classification results are then used to incorporate vibration impact assessment, referencing plastic and elastic deformation characteristics. Vibration impact assessment extracts attenuation coefficients from a pre-set vibration database to determine deformation feature vectors. Thermal distribution parameters are extracted from the deformation feature vectors and integrated using finite element analysis (FEM). FEM discretizes the parameters into mesh elements and calculates the heat value of each element to obtain a thermal balance model. The thermal balance model is then integrated with cooling medium flow data, where the flow rate is extracted from a pre-set medium database. A deformation suppression threshold is determined to establish the optimized thermal management scheme.

[0130] In one implementation, the key component reinforcement instructions are extracted from the final processing control sequence by parsing the sequence structure.

[0131] Specifically, the machining control sequence contains multiple parameter instructions, such as depth of cut and cooling timing. First, subsequences related to critical parts of the material are identified. For example, in sheet metal finishing, critical parts refer to easily deformable areas such as edges or bends. The extraction process involves traversing the sequence data and filtering out strengthening instructions, including increasing local cooling intensity or adjusting the feed rate to enhance part durability.

[0132] It should be noted that this extraction is based on predefined rules, such as instruction label matching, to ensure accuracy. In the scenario of precision alloy parts machining, the extracted instructions are used to guide machine tool operation, forming a reinforcement path. Furthermore, a classification model is employed to distinguish material deformation types. This classification model is a supervised learning-based framework used to classify deformation data into different types. Its principle is to calculate the probability distribution by inputting feature vectors to achieve type differentiation.

[0133] Specifically, the model can adopt a support vector machine structure, first collecting training data such as stress-strain curves, and then training the model to recognize patterns.

[0134] In one possible implementation, for hot bending of tubing, the input data includes deformation measurements, and the model outputs either plastic or elastic labels. This differentiation process facilitates accurate analysis of deformation behavior, providing a basis for optimization.

[0135] Understandably, the model's implementation enhances the targeted nature of deformation handling. Further analysis is conducted by referencing the characteristics of plastic and elastic deformation. Plastic deformation characteristics refer to the permanent deformation of a material under load, such as the increase in strain after the yield point; elastic deformation characteristics refer to recoverable deformation, such as the linear relationship described by Hooke's Law.

[0136] Specifically, in the finishing of curved metal surfaces, these features are referenced by comparing actual measurement data with standard curves, for example, to assess whether deformation exceeds the elastic limit. This reference step provides auxiliary data for the classification model, ensuring the reliability of the distinction.

[0137] Preferably, the optimized thermal management scheme is generated based on the extracted instructions and classification results.

[0138] Specifically, the solution involves adjusting heat dissipation parameters, such as cooling medium flow rate and ambient temperature correction. First, it integrates instructions for key components with deformation types; for example, if classified as plastic deformation, it increases the cooling sequence to reduce thermal stress. In the machining of heat-treated alloy parts, the solution generation process involves simulating thermal management effects and outputting a list of optimized parameters. This solution ensures thermal balance during the machining process.

[0139] In one embodiment, for CNC machine tools processing metal sheets, the solution verification achieves stable control by comparing the heat distribution data before and after processing.

[0140] For example, in the scenario of welding metal workpieces, the entire process is extended to the extraction of multiple sets of sequences. First, reinforcement instructions are extracted from the sequences, then a classification model is applied to distinguish deformations, and a scheme is determined by referring to features.

[0141] For example, after extracting instructions for weld seams and classifying deformation types in the model, the solution adjusts cooling parameters to provide thermal management guidance. This implementation demonstrates the adaptability of the technical solution in manufacturing. Furthermore, the differentiation of classification models can be achieved using feature engineering methods, which work by extracting key indicators of the deformation curve, such as slope and peak value, to separate the types.

[0142] Specifically, in the finishing process of heat treatment of sheet metal, the process includes data preprocessing followed by input into the model, and the output results used for scheme optimization. This method ensures accurate differentiation.

[0143] In one embodiment, the determination of the thermal management scheme involves iterative adjustments.

[0144] For example, in the hot extrusion processing of precision alloy parts, based on the extracted instructions and deformation characteristics, the scheme progressively optimizes thermal parameters, such as incorporating seasonal ambient temperature data, to form a final management sequence. This iterative approach enhances the practicality of the scheme.

[0145] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. The present invention has been described in detail with reference to preferred embodiments. Those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the present invention, and all such modifications and substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for controlling the fabrication of a radiator based on force-thermal balance, characterized in that, include: Real-time force and heat distribution parameters in the processing equipment are acquired through a data acquisition system, and a force-thermal coupling model is constructed to determine the initial state of force-thermal equilibrium. Based on the initial state of the force-thermal balance, the stress concentration risk in key areas is determined and the coordinates of the risk areas are identified. For the coordinates of the risk areas, the heat transfer uniformity is analyzed and the material deformation trend is predicted to obtain a deformation compensation vector. The machining accuracy parameters are adjusted using the deformation compensation vector, and combined with cutting speed and feed rate factors, an adjusted cutting path plan is generated. The adjusted cutting path plan is obtained, and the probability of structural defects is analyzed and the defect suppression effect is evaluated. If the defect suppression effect reaches a preset threshold, the force-thermal balance model is updated, incorporating ambient temperature and cooling medium parameters to generate the final machining control sequence. Based on the final machining control sequence, the material deformation type is distinguished, and an optimized thermal management scheme is determined.

2. The processing control method for a heat sink based on force-thermal balance as described in claim 1, characterized in that, The step of acquiring real-time force and heat distribution parameters in the processing equipment through a data acquisition system and constructing a force-thermal coupling model to determine the initial state of force-thermal equilibrium includes: acquiring real-time force and heat distribution parameters from the processing equipment and integrating them with vibration signals to form an extended parameter set; calculating the force equilibrium part and the heat distribution equilibrium part using the principle of mechanical equilibrium for the extended parameter set, and constructing a force-thermal coupling model; determining a preliminary equilibrium index through the force-thermal coupling model; if the preliminary equilibrium index exceeds a preset threshold, adjusting the heat distribution parameters to obtain a corrected equilibrium index; and judging and determining the initial state of force-thermal equilibrium based on the corrected equilibrium index.

3. The processing control method for a heat sink based on force-thermal balance as described in claim 1, characterized in that, The step of determining the stress concentration risk of key components and identifying the coordinates of the risk area based on the initial state of force-thermal equilibrium includes: obtaining the thermal load distribution of key components through the initial state of force-thermal equilibrium and determining the stress peak value; comparing the stress peak value with a preset threshold to determine whether there is a stress concentration risk and obtaining a risk assessment result; combining the material mechanical properties with the risk assessment result to obtain the boundary range of the risk area and determine the coordinate point set; generating a risk area mapping layer based on the coordinate point set, determining the thermal stress expansion trend, and obtaining the final risk area coordinates.

4. The processing control method for a heat sink based on force-thermal balance as described in claim 1, characterized in that, The process of analyzing heat transfer uniformity and predicting material deformation trends for the coordinates of the risk area to obtain a deformation compensation vector includes: extracting the temperature gradient from the coordinates of the risk area and calculating the standard deviation of the temperature gradient to obtain the heat transfer uniformity; if the heat transfer uniformity is lower than a preset threshold, activating the simulation analysis model and predicting deformation by inputting temperature field data using the finite element method; integrating the workpiece geometry and analyzing the material deformation trend using a mesh generation method; calculating the thermal stress distribution mapping using the stress tensor in conjunction with the load conditions; and fusing the coordinates of the risk area through the thermal stress distribution mapping and obtaining the deformation compensation vector using a vector superposition method.

5. The processing control method for a heat sink based on force-thermal balance as described in claim 1, characterized in that, The step of adjusting machining accuracy parameters using the deformation compensation vector, combined with cutting speed and feed rate factors, to generate an adjusted cutting path plan includes: extracting micro-quality influencing factors from the deformation compensation vector, calculating weights using a particle swarm optimization algorithm to obtain an influencing factor set; adjusting machining accuracy parameters using the influencing factor set, incorporating tool wear compensation data to obtain an adjusted machining accuracy parameter set; determining a speed optimization vector using a vector fusion method, combined with the cutting speed factor; integrating the feed rate factor, and activating a vibration suppression vector if the feed rate factor exceeds a preset threshold to obtain a comprehensive cutting parameter matrix; and fusing surface roughness optimization data, using a path simulation method to generate the adjusted cutting path plan.

6. The processing control method for a heat sink based on force-thermal balance as described in claim 1, characterized in that, The process of obtaining the adjusted cutting path plan, analyzing the probability of structural defects, and evaluating the defect suppression effect includes: acquiring product durability simulation data for the adjusted cutting path plan, constructing a material stress distribution simulation using finite element analysis, and obtaining a stress distribution map; extracting thermal strain coefficients based on thermal deformation impact assessment, integrating the stress distribution map using a vector weighted fusion method to determine a comprehensive thermal stress vector; analyzing the comprehensive thermal stress vector using a neural network prediction model to output a set of structural defect probabilities; extracting life curve data based on fatigue life assessment, and determining the potential impact of defects using an integral fusion method; and activating the suppression strategy vector if the potential impact of defects exceeds a preset threshold to determine the defect suppression effect.

7. The processing control method for a heat sink based on force-thermal balance as described in claim 1, characterized in that, If the defect suppression effect reaches a preset threshold, the thermal equilibrium model is updated, incorporating ambient temperature and cooling medium parameters to generate the final processing control sequence. This includes: if the defect suppression effect reaches the preset threshold, obtaining heat dissipation simulation results, constructing a heat distribution mesh using finite element analysis to obtain a heat dissipation map; combining vibration attenuation simulation, extracting attenuation coefficients, integrating the heat dissipation map using a weighted average method to determine a vibration-thermal composite vector; updating the thermal equilibrium model using the vibration-thermal composite vector, incorporating ambient temperature parameters, and fusing temperature distribution data using a vector superposition method; incorporating cooling medium parameters, extracting flow rate data, and fusing the thermal equilibrium model using an integral calculation method to generate the final processing control sequence.

8. The processing control method for a heat sink based on force-thermal balance as described in claim 1, characterized in that, The step of distinguishing material deformation types and determining an optimized thermal management scheme based on the final processing control sequence includes: extracting reinforcement instructions for key parts from the final processing control sequence, using a support vector machine classification model to distinguish material deformation types, and obtaining deformation classification results; referencing plastic and elastic deformation characteristics, incorporating vibration impact assessment, extracting attenuation coefficients, and determining deformation feature vectors; extracting heat distribution parameters from the deformation feature vectors, integrating them through finite element analysis to obtain a thermal balance model; and fusing cooling medium flow data, extracting flow rates, determining deformation suppression thresholds, and determining the optimized thermal management scheme.

9. A radiator, characterized in that, It is manufactured by the heat sink processing control method based on force-thermal balance as described in any one of claims 1-8.

Images