Rubber sealing ring multi-field coupling intelligent simulation optimization system

Abstract

The invention belongs to the field of rubber, and relates to a rubber sealing ring multi-field coupling intelligent simulation optimization system which comprises a working condition and rubber material performance coupling module, a virtual assembly model construction module, a local finite element model generation module, a dynamic sealing performance simulation module, a simulation and test data calibration module and an intelligent optimization design module. According to the system, basic parameters are provided through coupling modeling of working conditions and rubber material performance, a simulation carrier is formed through virtual assembly and local finite element model construction, core performance analysis is achieved through dynamic sealing performance simulation, parameter precision is corrected by combining simulation and test calibration, and finally an optimal scheme is output through intelligent optimization design. And the whole process integration of simulation, calibration and optimization of the rubber sealing ring is realized.

Description

Technical Field

[0001] This invention belongs to the field of rubber, and in particular to a multi-field coupling intelligent simulation optimization system for rubber sealing rings. Background Technology

[0002] Existing rubber seal simulation technologies are mostly based on fixed operating parameters and material properties for modeling, without considering the dynamic coupling effect of multiple field parameters such as temperature and pressure. Furthermore, the synergistic characterization of rubber material performance degradation and sealing performance is insufficient, resulting in a large deviation between the simulation model and the actual service scenario, and making convergence difficult.

[0003] Meanwhile, in traditional technologies, simulation, testing, and optimization are isolated from each other. Simulation results lack calibration with experimental data, and optimization design relies solely on empirical parameter adjustments. This makes it impossible to achieve precise optimization for key performance influencing factors, and thus fails to meet the design requirements for high-precision and high-efficiency rubber seals.

[0004] Therefore, the existing technology has the following problems: 1. Existing simulations do not achieve dynamic linkage between working conditions, rubber materials, and sealing performance, resulting in low simulation accuracy and poor convergence stability; 2. The lack of a complete process mechanism for simulation, testing, and optimization results in insufficient targeted optimization design and an inability to efficiently output rubber sealing ring structure and parameter schemes that meet the actual application requirements. Summary of the Invention

[0005] This invention proposes a multi-field coupling intelligent simulation optimization system for rubber sealing rings.

[0006] A multi-field coupled intelligent simulation optimization system for rubber sealing rings includes: a working condition and rubber material performance coupling module that collects and transforms raw working condition data through multi-field coupled working condition parameter modeling, calculates and outputs basic working condition and material parameters; and collects and transforms raw working condition data such as temperature and pressure, constructs a dynamic attenuation law of synergistic aging and fatigue of rubber materials, and performs parameter calibration based on experimental deviation linkage. Virtual assembly model construction module: Based on basic working conditions and material parameters, it constructs a basic geometric model through parametric geometry generation and complex structure refinement, dynamically allocates assembly tolerances and verifies deformation by combining multi-field coupled working condition parameters, and outputs a virtual assembly model containing tolerance and constraint information. Local finite element model generation module: Based on the constraint information and multi-field coupled working condition parameters of the virtual assembly model, it intelligently identifies key areas such as sealing contact and stress concentration, smoothly cuts the boundaries, adaptively adjusts the mesh density according to the stress gradient, verifies the mechanical consistency of the model, and outputs a local finite element model. Dynamic sealing performance simulation module: Through local finite element model and dynamic working conditions and material parameters, it adaptively optimizes the step size, dynamically adjusts the load gradient, and achieves a smooth transition of load application; it adjusts the loading step size, corrects the contact pressure and couples wear prediction, adapts to the nonlinear constitutive model and corrects calculation deviations, and outputs sealing performance simulation data; Simulation and experimental data calibration module: Collects multi-dimensional experimental data and performs noise reduction and standardization processing; compares simulation data and experimental data to locate the source of deviation and quantifies the degree of influence; sorts parameters by weight, corrects them, iteratively verifies them, and provides feedback on the corrected parameters; Intelligent optimization design module: Receives calibrated sealing performance simulation data, determines weighting coefficients and selects an appropriate optimization algorithm, identifies key design parameters and predicts their fluctuation effects, selects several optimization schemes and adjusts key parameters, and finally outputs the optimal design scheme.

[0007] Preferably, the working condition and rubber material performance coupling module includes a multi-field coupled working condition parameter modeling unit, which collects raw working condition data such as temperature, pressure, and medium type, converts physical working condition parameters into simulation input parameters, realizes the time-series synchronization and coupled application of multiple field parameters, and allocates loading priority based on the weight of the influence of each field parameter on the sealing performance.

[0008] Preferably, the working condition and rubber material performance coupling module includes a rubber material performance dynamic decay modeling unit. Based on the basic properties of rubber materials, the decay law of rubber material performance with the duration of working conditions is obtained through the material aging factor dynamic calculation module. Combined with the fatigue damage accumulation coupling module, the aging and fatigue are modeled collaboratively.

[0009] Preferably, the virtual assembly model construction module includes a complex structure adaptive modeling unit. The unit constructs a basic geometric model through a parametric geometry generation module and uses an adaptive mesh generation algorithm to refine the geometry of complex structural areas such as rubber sealing ring grooves and lips, ensuring the consistency between the geometric model and the actual structure.

[0010] Preferably, the local finite element model generation module includes a key area intelligent identification and cutting unit and a mesh density adaptive optimization unit. The key area intelligent identification and cutting unit uses a machine learning algorithm to identify key areas, including rubber sealing contact and stress concentration, and performs mesh smoothing on the cutting surface. The mesh density adaptive optimization unit adjusts the mesh density according to the stress gradient distribution of the key areas to verify the consistency of mechanical properties between the reconstructed model and the original assembly model.

[0011] Preferably, the dynamic sealing performance simulation module includes a loading step size adaptive unit, which receives dynamic rubber material parameters, dynamically optimizes the step size according to the changing trends of the elastic modulus and hardness of the rubber material, and achieves a smooth transition of load application with the help of a load gradient dynamic adjustment module.

[0012] Preferably, the dynamic sealing performance simulation module includes a contact pressure linkage calculation unit, which corrects the contact pressure calculation model based on the hardness value in the dynamic rubber material parameters, and converts the contact pressure distribution into the wear rate through the contact area wear prediction coupling module.

[0013] Preferably, the simulation and test data calibration module includes a multi-dimensional test data synchronization unit and a deviation source location unit. The multi-dimensional test data synchronization unit collects multi-dimensional raw test data, including leakage, contact pressure, and wear, removes data noise, and converts the test data into dimensions consistent with the simulation data. The deviation source location unit compares the simulation results with the standardized test data to determine the main sources of deviation and quantifies the influence of each source.

[0014] Preferably, the intelligent optimization design module includes a multi-objective optimization weight dynamic allocation unit, which determines the weight coefficients of the objectives, including leakage, sealing life, and manufacturing cost, according to the sealing performance requirements of the rubber sealing ring, and selects the corresponding optimization algorithm according to the type of optimization objective.

[0015] Preferably, the intelligent optimization design module includes a key parameter identification unit. Based on the sealing performance simulation results, this unit determines the design parameters that significantly affect the sealing performance through sensitivity analysis, and uses a parameter fluctuation impact prediction module to predict the impact of parameter fluctuations on performance. The present invention has the following beneficial effects: 1. By coupling modeling and dynamic correction of working conditions and rubber material properties, the accuracy and convergence stability of rubber seal simulation are effectively improved, making the simulation results more consistent with the actual service conditions and reducing the deviation between simulation and actual scenarios.

[0016] 2. Through the simulation and test data calibration module and the multi-module intelligent linkage mechanism, the entire process of simulation, calibration and optimization is integrated, ensuring that the optimized design scheme can accurately match the sealing performance target of the rubber sealing ring, and improving the reliability and pertinence of the rubber sealing ring design.

[0017] 3. By using intelligent optimization algorithms and sensitivity analysis of key parameters, the complex parameter debugging process in traditional design is simplified, the reliance on physical tests is reduced, the R&D cost of rubber seals is lowered, and the product design cycle is shortened. Attached Figure Description

[0018] Figure 1This is a schematic diagram of the structure of a multi-field coupling intelligent simulation optimization system for rubber sealing rings according to the present invention. Detailed Implementation

[0019] To enable those skilled in the art to better understand the technical solutions of this invention, the technical solutions in the embodiments of this invention will be clearly described below in conjunction with the examples.

[0020] like Figure 1 As shown, this invention proposes a multi-field coupled intelligent simulation optimization system for rubber sealing rings, comprising the following modules: a coupling module for working conditions and rubber material properties, a virtual assembly model construction module, a local finite element model generation module, a dynamic sealing performance simulation module, a simulation and experimental data calibration module, and an intelligent optimization design module. The system provides basic parameters through coupled modeling of working conditions and rubber material properties, forms a simulation carrier through virtual assembly and local finite element model construction, achieves core performance analysis based on dynamic sealing performance simulation, corrects parameter accuracy through simulation and experimental calibration, and finally outputs the optimal solution through intelligent optimization design, realizing the integrated process of rubber sealing ring simulation, calibration, and optimization.

[0021] In one feasible embodiment, the working condition and rubber material performance coupling module further includes a multi-field coupled working condition parameter modeling module. Specifically, this module collects raw working condition data such as temperature, pressure, and medium type; converts physical working condition parameters into simulation input parameters through a real-time working condition parameter acquisition and mapping module; and uses a multi-field parameter collaborative loading module to achieve temporal synchronization and coupled application of multiple field parameters. The multi-field parameter collaborative loading employs a coupling coefficient allocation model, allocating loading priority based on the weight of each field parameter's influence on sealing performance. The model expression is as follows: In the formula For the first Loading weights of field parameters, For sealing performance parameters For the first field parameters The partial derivatives, For the first The operating condition adaptation coefficient of the field parameters.

[0022] Based on the sensitivity analysis of sealing performance and multiple field parameters, the influence of a single field parameter on performance is quantified by partial derivatives, and an operating condition adaptation coefficient is introduced. The value ranges from 0.1 to 1.0. It is set according to the actual working conditions and intensity, corrects the theoretical sensitivity, realizes the priority quantification allocation of multi-field parameter loading, and ensures that the loading order is consistent with the actual working conditions and influence laws.

[0023] In one feasible embodiment, the working condition and rubber material performance coupling module further includes a rubber material performance dynamic degradation modeling module. Specifically, based on the fundamental properties of the rubber material, the degradation law of the rubber material performance with the duration of working conditions is obtained through a material aging factor dynamic calculation module, and combined with a fatigue damage accumulation coupling module to achieve collaborative modeling of aging and fatigue; wherein, the material aging factor calculation adopts a modified Arrhenius equation. In the formula for Temperature at any time Under the aging factors, The initial aging factor. The activation energy of rubber materials The gas constant is For aging rate index, a value of 0.3-0.8 is used for rubber materials; fatigue damage accumulation is performed using the Miner linear accumulation criterion. In the formula To accumulate damage, For the first Cycle count under load level For the first Fatigue life of rubber materials under load level.

[0024] Introducing a time factor based on the Arrhenius equation It adapts to the aging patterns of rubber sealing materials during long-term service; the Miner criterion is directly used for damage accumulation calculation under load cycles, and the two are coupled through weighting coefficients. The values ​​range from 0.4 to 0.6, and the summation yields the total attenuation coefficient. This enables the synergistic characterization of aging and fatigue.

[0025] In one feasible embodiment, the working condition and rubber material performance coupling module further includes a working condition and rubber material parameter linkage calibration module, specifically: receiving test deviation data from the simulation and test data calibration module, using the test data to back-calculate rubber material parameters to correct the basic properties of the rubber material based on the deviation value, and using the working condition fluctuation and rubber material parameter adaptation module to achieve real-time matching between dynamic changes in working conditions and rubber material parameters; wherein, the parameter back-calculation adopts a least squares optimization model. In the formula For the first Group simulation performance parameters, For the first Group test performance parameters.

[0026] With the goal of minimizing the sum of squared deviations between simulation and experimental performance parameters, an optimization model is constructed to solve for the optimal rubber material parameters. The constraint condition is the physical range of the rubber material parameters to ensure that the back-derived parameters conform to the inherent characteristics of the rubber material.

[0027] In one feasible embodiment, the virtual assembly model construction module further includes a complex structure adaptive modeling module, specifically: based on the dynamic rubber material parameters of the working condition and rubber material performance coupling module, combined with the rubber sealing ring structural parameters, a basic geometric model is constructed through a parametric geometry generation module. An adaptive mesh generation algorithm is used to geometrically refine complex structural areas such as the rubber sealing ring grooves and lips, ensuring consistency between the geometric model and the actual structure. The virtual assembly model construction module also includes an assembly tolerance dynamic allocation module, specifically: based on the multi-field coupled working condition parameters and the tolerance and performance influence model, the tolerance levels of each assembly surface are allocated. The constraint and deformation collaborative verification module verifies whether the deformation of the rubber sealing ring under assembly constraints meets the design requirements. The tolerance allocation model expression is as follows: In the formula For the first Tolerance values ​​of assembly surfaces, This is the total tolerance allowable value. For the first The sensitivity of the assembly surface to the sealing performance was obtained through simulation experiments, with a value ranging from 0 to 1.

[0028] The influence weight of each assembly surface was determined through sensitivity analysis. The total tolerance is allocated according to weight to ensure that key assembly surfaces obtain higher tolerance accuracy, balancing assembly difficulty and rubber sealing performance.

[0029] In one feasible embodiment, the local finite element model generation module further includes a key area intelligent identification and cutting module, specifically: based on the constraint information of the virtual assembly model and the multi-field coupling working condition parameters, a machine learning algorithm is used to identify key areas such as rubber seal contact and stress concentration; the cutting surface is smoothed by a cutting boundary smoothing module to avoid abrupt changes in boundary stress; the local finite element model generation module also includes a mesh density adaptive optimization module, specifically: according to the stress gradient distribution of the key areas, an adaptive densification algorithm is used to adjust the mesh density; the consistency of the mechanical properties of the reconstructed model and the original assembly model is verified by a reconstructed model compatibility verification module; the mesh density adjustment model is... In the formula For the target mesh density, Based on grid density, This is a density adjustment factor, with a value ranging from 0.5 to 2.0. The stress gradient is given.

[0030] Based on stress gradient The degree of stress change is quantified by adjusting the coefficient. By controlling the mesh refinement level, the mesh in critical areas is refined while the mesh in non-critical areas is simplified, balancing simulation accuracy and efficiency, and adapting to the nonlinear mechanical properties of rubber materials.

[0031] In one feasible embodiment, the dynamic sealing performance simulation module further includes a loading step size adaptive module based on rubber material properties. Specifically, it receives dynamic rubber material parameters from the dynamic attenuation module of rubber material properties, dynamically optimizes the step size through a loading step size adjustment model based on the changing trends of the rubber material's elastic modulus and hardness, and achieves a smooth transition of load application with the help of a load gradient dynamic adjustment module. The dynamic sealing performance simulation module also includes a contact pressure and rubber material hardness linkage calculation module. Specifically, based on the hardness value in the dynamic rubber material parameters, it uses Hertz contact theory to correct the contact pressure calculation model, and converts the contact pressure distribution into wear rate through a contact area wear prediction coupling module. The contact pressure correction model is... In the formula To correct the contact pressure, Initial contact pressure, For real-time rubber material hardness, This represents the initial hardness of the rubber material.

[0032] Based on the Hertz contact theory, which states that contact pressure is proportional to the square root of the hardness of rubber materials, a real-time hardness is introduced. For initial contact pressure Make corrections to ensure that the contact pressure calculation matches the dynamic properties of the rubber material.

[0033] In one feasible embodiment, the dynamic sealing performance simulation module further includes a nonlinear rubber material constitutive adaptive correction module, specifically: receiving contact data from the contact area dynamic calculation module and the dynamic rubber material parameters; selecting an appropriate nonlinear constitutive model through a constitutive parameter real-time matching module; using the Mooney-Rivlin model for rubber-type sealing rings; and correcting the calculation deviation of the constitutive model using a nonlinear error compensation module; wherein, the error compensation adopts a polynomial fitting model. In the formula This is the error compensation value. The strain value, The fitting coefficients are denoted as .

[0034] By fitting a polynomial relationship between strain and error using experimental data, the fitting coefficients are obtained, and the compensation value is... The results are superimposed on the constitutive model calculations to correct the calculation errors caused by the nonlinear deformation of the rubber material.

[0035] In one feasible embodiment, the simulation and test data calibration module further includes a multi-dimensional test data synchronization module, specifically: collecting multi-dimensional raw test data such as leakage, contact pressure, and wear, removing data noise using a Gaussian filtering algorithm through a data noise filtering and standardization sub-module, and converting the test data into dimensions consistent with the simulation data; the simulation and test data calibration module further includes a deviation source location module, specifically: comparing the simulation results of the dynamic sealing performance simulation module with the standardized test data, determining the main sources of deviation through variance analysis, and quantifying the influence degree of each source using a deviation weight allocation module; the simulation and test data calibration module further includes a correction parameter priority ranking module, specifically: ranking correction parameters based on the degree of deviation influence, and iteratively verifying the consistency between the corrected simulation results and test data through a correction effect iterative verification module until the deviation is less than a set threshold.

[0036] In one feasible embodiment, the intelligent optimization design module further includes a multi-objective optimization weight dynamic allocation module, specifically: based on the sealing performance target requirements of the rubber sealing ring, the weight coefficients of targets such as leakage, sealing life, and manufacturing cost are determined through the analytic hierarchy process (AHP), and a genetic algorithm or particle swarm optimization algorithm is selected based on the optimization target type using an adaptive selection module; the intelligent optimization design module also includes a key parameter identification module, specifically: based on the simulation results of the dynamic sealing performance simulation module, design parameters that significantly affect sealing performance are determined through sensitivity analysis, and the impact of parameter fluctuations on performance is predicted using Monte Carlo simulation with the help of a parameter fluctuation impact prediction module; the intelligent optimization design module also includes a rapid scheme screening module, specifically: multiple optimization schemes are simulated and verified, key parameters are adjusted through an optimal scheme detail optimization module, and the final optimization scheme is output.

[0037] In one feasible embodiment, the real-time feedback module for operating condition changes and rubber material parameters specifically monitors the dynamic changes of the multi-field coupled operating condition parameters, inputs the changes into the dynamic calculation module for rubber material aging factors and the fatigue damage accumulation coupling module, and updates the dynamic rubber material parameters in real time to ensure that the rubber material performance parameters remain synchronized with the changes in operating conditions. The dynamic adjustment module for rubber material performance degradation and simulated load specifically obtains the total degradation coefficient of the dynamic degradation module for rubber material performance. Input the loading step size adaptive module based on the properties of rubber materials, and through Adjust the loading step size to avoid mismatch between the applied load and the actual bearing capacity of the rubber material; the simulation deviation and working condition / rubber material parameter correction module specifically: receives the deviation data from the deviation source positioning module, if the deviation originates from the working condition parameters, corrects the multi-field coupled working condition parameters, and if the deviation originates from the rubber material parameters, updates the rubber material properties by back-inferring the rubber material parameters from the test data.

[0038] In one feasible embodiment, the optimization parameter and mesh density adaptive matching module specifically involves: acquiring the key design parameters of the key parameter identification module, and adjusting the density adjustment coefficient of the mesh density adaptive optimization module according to the magnitude of parameter changes. The greater the parameter change, the better. A larger value ensures that the mesh density matches the parameter optimization requirements and adapts to the mechanical properties of the rubber material. The model accuracy and optimization efficiency balancing module specifically involves: based on the mesh information of the adaptive mesh density optimization module and the algorithm type of the adaptive selection module, adjusting the number of optimization iterations through the efficiency and accuracy balancing model. The model expression is: In the formula This represents the actual number of iterations. The maximum number of iterations, This represents the actual grid density. The maximum mesh density is achieved through an optimization iteration and model reconstruction linkage module. Specifically, during the optimization iteration process, if the change in key parameters exceeds a set threshold, the intelligent identification and cutting module for key regions and the model reconstruction and optimization module are triggered to reconstruct the local finite element model.

[0039] In one feasible embodiment, the experimental deviation and design parameter reverse optimization module specifically involves: acquiring the deviation value from the deviation quantification analysis module, inputting it into the key parameter identification module, determining the design parameter causing the deviation, and adjusting the optimization weight of the parameter through the multi-objective optimization weight dynamic allocation module to perform reverse optimization; the design scheme and experimental verification priority ranking module specifically involves: based on multiple optimization schemes from the optimal scheme detail optimization module, combined with the deviation source information from the deviation weight allocation module, prioritizing the selection of deviation-sensitive schemes for experimental verification; and the iteration effect quantification evaluation module specifically involves: calculating the simulation and experimental deviation rate after each iteration, and through... The effect is quantitatively evaluated, and the iteration is terminated if the deviation rate is less than the set threshold twice in a row.

[0040] In one feasible embodiment, the assembly tolerance and working condition load co-influence module specifically involves: inputting the tolerance values ​​from the assembly tolerance dynamic allocation module and the multi-field coupled working condition parameters into the constraint and deformation co-verification module, and then using the co-influence model... The deformation of the rubber seal ring under the combined action of tolerance and working conditions is analyzed to ensure that the deformation is within the allowable range. The assembly constraint and rubber material deformation adaptation module specifically involves: obtaining the elastic modulus and Poisson's ratio from the dynamic rubber material parameters, inputting them into the constraint and deformation co-verification module, and adjusting the stiffness coefficient of the assembly constraint to adapt the constraint conditions to the deformation characteristics of the rubber material.

[0041] In one feasible embodiment, the contact pressure distribution and wear rate mapping module specifically involves: based on the contact pressure distribution data from the contact pressure and rubber material hardness linkage calculation module, using the Arcard wear model. Calculate the wear volume, where For wear volume, The wear coefficient is... To contact pressure, The sliding distance, The module for dynamic updating of wear accumulation and contact area is for rubber material hardness. Specifically, it inputs the wear volume data into the dynamic calculation module for contact area and updates the geometry and contact pressure distribution of the contact area in real time to ensure that the contact calculation matches the wear accumulation state.

[0042] The Archard model is a classic model for wear calculation, which incorporates the real-time contact pressure. With dynamic rubber material hardness This enables dynamic linkage between wear rate and rubber seal contact state.

[0043] In one feasible embodiment, the loading strategy and optimization target matching module specifically involves: obtaining the target weights of the multi-objective optimization weight dynamic allocation module; if the sealing life weight is the highest, uniform step-by-step loading is adopted; if the leakage weight is the highest, gradient step-by-step loading is adopted, so that the step-by-step loading strategy is consistent with the optimization target; the loading step size and optimization iteration efficiency linkage module specifically involves: adjusting the step size change rate of the load gradient dynamic adjustment module according to the iteration progress of the optimization algorithm; using a large step size in the early stage of iteration to accelerate convergence; and using a small step size in the later stage of iteration to improve optimization accuracy, adapting to the nonlinear optimization requirements of rubber materials.

[0044] Example 1 The technical system of this embodiment includes: a working condition and rubber material performance coupling module, a virtual assembly model construction module, a local finite element model generation module, a dynamic sealing performance simulation module, a simulation and test data calibration module, an intelligent optimization design module, and an interactive innovation module group.

[0045] The complete technical implementation process of this system is as follows: First, the working condition and rubber material performance coupling module is activated. Through the real-time acquisition and mapping module of the working condition parameters in the multi-field coupled working condition parameter modeling module, a distributed sensor array is used to collect raw working condition data such as temperature, pressure, and medium viscosity in the service environment of the rubber sealing ring. The acquisition frequency is set to 10-100Hz according to the dynamic change characteristics of the working conditions to ensure the capture of instantaneous fluctuations in the working condition parameters. After the acquired data is converted from analog to digital, the timing synchronization of multiple field parameters is achieved through the multi-field parameter collaborative loading module. The synchronization accuracy is controlled within 1ms to avoid coupling modeling errors caused by timing deviations. The multi-field parameter collaborative loading adopts a coupling coefficient allocation model. ,in The results were obtained through simulation using the controlled variable method, i.e., keeping other field parameters fixed and only changing the first field parameter. Field parameters, calculate sealing performance parameters The rate of change, such as contact pressure; Based on the intensity of the working conditions, high-temperature working conditions Time temperature parameters Use 0.8-1.0 for high-voltage operating conditions. Pressure parameters Using values ​​of 0.8-1.0, the field parameters under normal operating conditions are... All values ​​are set to 0.5-0.7, and the final output is a set of parameters for multi-field coupling conditions.

[0046] Based on the sensitivity analysis of sealing performance and multiple field parameters, the influence of a single field parameter on performance is quantified by partial derivatives, and an operating condition adaptation coefficient is introduced. Correcting theoretical sensitivity ensures that the loading sequence aligns with the actual operating conditions, among which... The value range was calibrated through a large number of working condition simulation tests, covering common service scenarios of rubber seals.

[0047] In parallel with the multi-field coupled operating condition parameter modeling, the dynamic degradation modeling module for rubber material properties is activated, based on the fundamental properties of the rubber sealing ring material, such as elastic modulus. Poisson's ratio Initial hardness The degradation law of rubber material properties with the duration of operating conditions is obtained through the dynamic calculation module of material aging factor. The material aging factor is calculated using the modified Arrhenius equation. ,in The initial aging test of rubber materials was used to determine the performance degradation rate, which involved subjecting rubber material samples to a 1000-hour room temperature aging test and measuring the percentage of performance degradation. ; The activation energy of the rubber material is obtained by differential scanning calorimetry (DSC) testing, and the test temperature range covers the service temperature range of the rubber seal. The aging rate index is set at 0.3-0.8 for rubber seals, with the specific value determined by fitting aging test data for different durations. Meanwhile, the fatigue damage accumulation coupling module employs the Miner linear accumulation criterion. ,in It is calculated using the load cycle frequency and service duration from the operating parameters. This data is obtained through fatigue testing of rubber materials. Different cyclic load levels are applied to rubber material samples, and the number of cycles at fracture is recorded as the corresponding load level. Through weighting coefficients The value is 0.4-0.6, determined based on the main failure modes of the rubber seal. When aging is the dominant failure mode... Take a value of 0.5-0.6 when fatigue is the primary cause of failure. Taking values ​​between 0.4 and 0.5, the total attenuation coefficient is obtained by superimposing these values. The final output shows the dynamic performance parameters of the rubber material, including the elastic modulus as a function of time and operating conditions. ,hardness wait.

[0048] Introducing a time factor based on the Arrhenius equation It adapts to the aging patterns of rubber sealing materials during long-term service, avoiding the limitations of the traditional Arrhenius equation which only considers the effect of temperature; the Miner criterion is directly used for damage accumulation calculation under load cycles, and the two are weighted by a coefficient. Coupling enables synergistic characterization of aging and fatigue, ensuring that the performance degradation modeling of rubber materials closely matches the actual failure mechanism.

[0049] The working condition and rubber material parameter linkage calibration module receives the test deviation data output by the subsequent simulation and test data calibration module, and uses the test data to back-calculate the rubber material parameters based on the least squares optimization model. The basic properties of the rubber material are adjusted, with constraints set on the physical value range of the rubber material parameters (e.g., elastic modulus not less than 1 MPa, Poisson's ratio between 0.3 and 0.5). The optimal rubber material parameters are then solved using a gradient descent algorithm. A module for adapting operating conditions to rubber material parameters monitors the changes in these multi-field coupled operating condition parameters in real time. ,pass , The elastic modulus adjustment coefficient is determined by fitting the test data of the rubber material, and the dynamic rubber material performance parameters are dynamically updated to ensure that the rubber material parameters match the fluctuations of the working conditions in real time.

[0050] With the goal of minimizing the sum of squared deviations between simulation and experimental performance parameters, an optimization model is constructed to solve for the optimal rubber material parameters, avoiding parameter deviations caused by single experimental data and ensuring the accuracy and robustness of the rubber material parameters.

[0051] The virtual assembly model construction module receives dynamic rubber material parameters and multi-field coupled working condition parameters output by the working condition and rubber material performance coupling module. It then activates the complex structure adaptive modeling module. Based on the rubber sealing ring structural parameters, such as inner diameter, outer diameter, cross-sectional dimensions, and groove structure, it constructs a basic geometric model using parametric modeling software, such as ANSYS DesignModeler, through a parametric geometry generation module. The model accuracy is controlled within 0.01mm. For complex structural areas such as the rubber sealing ring lip and groove corners, an adaptive mesh generation algorithm, such as the AdvancingFront algorithm, is used for geometric refinement. The refined mesh element size is no larger than 0.1mm, ensuring that the geometric model accurately represents the mechanical properties of the complex structure and adapts to the deformation requirements of the rubber material. Simultaneously, the assembly tolerance dynamic allocation module, based on the multi-field coupled working condition parameters and the tolerance and performance influence model, performs geometric refinement. Assign tolerance grades to each assembly surface, where The total tolerance allowable value for the assembly of rubber seals is determined according to the product design requirements. The tolerances of other assembly surfaces are obtained through simulation using the controlled variable method, i.e., the tolerances of the first assembly surface are kept constant, and only the tolerances of the second assembly surface are changed. Assembly surface tolerances, and the rate of change of sealing performance parameters are calculated as follows. The constraint and deformation co-verification module uses finite element static analysis, taking the elastic modulus and Poisson's ratio from the dynamic rubber material parameters as input, applying assembly constraints such as interference fit and bolt preload, and calculating the assembly deformation of the rubber seal ring. If the deformation exceeds the design allowable value (in one feasible embodiment, no more than 0.1 mm), the assembly tolerance or constraint conditions are adjusted until the deformation meets the requirements. Finally, a virtual rubber seal ring assembly model containing tolerance and constraint information is output.

[0052] The influence weight of each assembly surface was determined through sensitivity analysis. The total tolerance is allocated by weight to ensure that key assembly surfaces achieve higher tolerance accuracy, balance the assembly difficulty with the sealing performance of the rubber seal, and avoid performance redundancy or insufficiency caused by the traditional average distribution of tolerance.

[0053] The local finite element model generation module receives the virtual rubber sealing ring assembly model output by the virtual assembly model construction module, and activates the key area intelligent identification and cutting module. Based on the constraint information of the virtual assembly model, such as interference fit surfaces and bolt tightening surfaces, as well as the multi-field coupling working condition parameters, such as high-pressure action surfaces, a machine learning algorithm, such as Support Vector Machine (SVM), is used to train the key area identification model. The training samples are simulation models of rubber sealing rings under different structures and working conditions, along with corresponding key area annotation data, achieving a training accuracy of over 95%. The trained model identifies key areas such as sealing contact areas and stress concentration areas, and a cutting algorithm is used to cut the virtual assembly model, such as planar cutting and curved surface cutting, to obtain local model fragments. The cutting boundary smoothing module uses a B-spline curve fitting algorithm to smooth the cutting surface, eliminating sharp edges generated during cutting, avoiding abrupt changes in boundary stress, and adapting to the stress transfer characteristics of the rubber material. The mesh density adaptive optimization module in the model reorganization and optimization module optimizes the mesh density based on the stress gradient distribution of the key areas. An adaptive encryption algorithm is used to adjust the grid density. The grid density adjustment model is as follows: ,in The base mesh density, determined based on the model size, is 0.5 mm in one feasible embodiment. This is a density adjustment factor, ranging from 0.5 to 2.0, applicable to areas with large stress gradients. For regions with smaller stress gradients, a value of 1.5-2.0 is used. Use a value of 0.5-1.0 to ensure that the mesh in critical areas is refined and the mesh in non-critical areas is simplified. The recombined model compatibility verification module uses modal analysis to compare the first 5 natural frequencies of the recombined local finite element model with the original virtual assembly model. If the frequency deviation does not exceed 5%, it is considered compatible. Otherwise, the mesh density or cutting range is adjusted, and the final output is a local finite element model containing adaptive mesh and node information.

[0054] Based on stress gradient The degree of stress change is quantified by adjusting the coefficient. By controlling the mesh refinement level, the computational load is reduced while ensuring simulation accuracy, thus resolving the contradiction between accuracy and efficiency caused by traditional fixed mesh density and adapting to the nonlinear simulation requirements of rubber materials.

[0055] The dynamic sealing performance simulation module receives the local finite element model output by the local finite element model generation module, the dynamic rubber material parameters output by the working condition and rubber material performance coupling module, and the multi-field coupled working condition parameters. It then activates the loading step size adaptive module based on rubber material properties, and adjusts the loading step size according to the elastic modulus in the dynamic rubber material parameters. and hardness The changing trend is observed by adjusting the step size model. , The initial loading step size is set to 0.001s-0.01s, and the step size is dynamically optimized. The loading step size increases when the elastic modulus decreases and decreases when the elastic modulus increases. The load gradient dynamic adjustment module uses a linear interpolation algorithm to achieve a smooth transition in load application, avoiding simulation convergence difficulties caused by sudden load changes, and adapting to the elastic properties of the rubber material. The contact pressure and rubber material hardness linkage calculation module in the contact area dynamic calculation module is based on the hardness value in the dynamic rubber material parameters. The contact pressure is calculated using the modified Hertz contact theory. The modified contact pressure model is as follows: ,in The initial contact pressure is calculated from the interference fit to ensure that the calculated contact pressure matches the dynamic properties of the rubber material. The contact area wear prediction coupling module inputs the contact pressure distribution data into the Archard wear model. ,in The wear coefficient is determined through friction and wear tests, with values ​​taken from the rubber-metal contact area. , The sliding distance is calculated from the motion speed and time under the operating conditions, and the wear volume is calculated accordingly. The wear data is then fed back to the contact area calculation module.

[0056] Based on the Hertz contact theory, which states that contact pressure is proportional to the square root of the hardness of rubber materials, a real-time hardness is introduced. For initial contact pressure The model is modified to address the issue of traditional contact pressure calculations neglecting the dynamic changes in rubber material properties; the Archard model incorporates real-time contact pressure. With dynamic rubber material hardness This enables dynamic linkage between wear rate and rubber seal contact state.

[0057] The nonlinear rubber material constitutive adaptive correction module receives contact data such as contact pressure and strain from the contact area dynamic calculation module, along with the dynamic rubber material parameters. Through a constitutive parameter real-time matching module, it selects an appropriate nonlinear constitutive model based on the rubber material type. For rubber-type sealing rings, the Mooney and Rivlin models are used, and the constitutive model parameters are adjusted based on the dynamic rubber material parameters, such as those of the Mooney and Rivlin models. , Parameters are obtained through dynamic elastic modulus The calculation shows that the nonlinear error compensation module uses a polynomial fitting model. ,in The compensation value is determined by fitting the deviation between experimental data and constitutive model calculation data. The results are superimposed on the constitutive model calculation results to correct the calculation deviation caused by nonlinear deformation, and finally output the corrected sealing performance simulation data, such as leakage, contact pressure distribution, and wear rate.

[0058] By fitting the polynomial relationship between strain and error to experimental data, the fitting coefficients are obtained, and the calculation deviation of the nonlinear constitutive model is compensated in a targeted manner to improve the accuracy of simulation data and adapt to the nonlinear characteristics of rubber materials.

[0059] The simulation and test data calibration module activates the multi-dimensional test data synchronization module, which collects multi-dimensional test raw data such as leakage, contact pressure, and wear of the rubber seal ring during actual operation through a sensor array. Timestamp synchronization technology is used to achieve time-series synchronization of multi-sensor data, with a synchronization error not exceeding 0.5ms. The data noise filtering and standardization submodule employs a Gaussian filtering algorithm. , These are the filter coefficients, ranging from 0.5 to 1.0. The filter window size is set to 3-5 to remove data noise and convert the experimental data to a unit consistent with the simulation data, such as unifying the leakage amount to . The contact pressure is standardized to MPa, and standardized test data is output. The deviation source positioning module compares the simulation results output by the dynamic sealing performance simulation module with the standardized test data, and performs variance analysis. , For the sum of squares between groups, For the degrees of freedom between groups, For the sum of squares within the group, To determine the degrees of freedom within a group, the main sources of deviation are identified, including deviations in operating condition parameters, rubber material parameters, and constitutive model deviations. The deviation weight allocation module uses the analytic hierarchy process (AHP) to determine the influence weight of each deviation source and outputs a deviation analysis report and deviation values. The correction parameter priority ranking module ranks the correction parameters based on their influence weight, prioritizing the correction of the top three parameters with the highest influence weight. The correction effect iterative verification module inputs the corrected parameters into the operating condition and rubber material performance coupling module or the dynamic sealing performance simulation module, re-performs the simulation calculation, and compares the deviation rate of the new simulation results with the standardized test data. If the deviation rate exceeds a set threshold (5% in one feasible embodiment), the correction process is repeated until the deviation rate falls below the set threshold, at which point the parameter correction command and verification results are output.

[0060] The intelligent optimization design module receives the corrected sealing performance simulation data output by the dynamic sealing performance simulation module, and starts the multi-objective optimization weight dynamic allocation module. According to the sealing performance target requirements of the rubber sealing ring, such as minimum leakage, longest sealing life, and lowest manufacturing cost, a judgment matrix is ​​constructed through the analytic hierarchy process (AHP) to calculate the weight coefficient of each target. The sum of the weight coefficients is 1. If the sealing life is the core target, its weight coefficient is 0.4-0.6, the leakage weight coefficient is 0.3-0.4, and the manufacturing cost weight coefficient is 0.1-0.2. The optimization algorithm adaptive selection module selects the optimization algorithm according to the optimization target type and parameter dimension. The non-dominated sorting genetic algorithm NSGA-Ⅲ is used for multi-objective and high-dimensional parameter optimization, and the particle swarm optimization algorithm PSO is used for single-objective and low-dimensional parameter optimization. The key parameter identification module, based on the sealing performance simulation data, calculates the sensitivity coefficients of each design parameter (structural parameter, rubber material parameter, assembly parameter) to sealing performance using the Morris screening method based on global sensitivity analysis. Parameters with an absolute value of sensitivity coefficient greater than 0.3 are identified as key parameters. The parameter fluctuation impact prediction module uses Monte Carlo simulation to apply fluctuations of ±5% to ±10% to the key parameters, simulating the impact of parameter fluctuations on sealing performance, and outputs a list of key parameters and fluctuation impact curves. The rapid scheme screening module performs simulation verification on multiple optimization schemes, using the Pareto optimal solution screening method to eliminate inferior schemes and retain the schemes corresponding to non-dominated solutions. The optimal scheme detail optimization module fine-tunes the key parameters of the retained schemes, adjusting the step size by 1% to 3% of the parameter values, and determines the optimal design scheme through simulation verification. The combination of structural parameters, rubber material parameters, and assembly parameters is used to finally output the optimal design scheme and verification report.

[0061] Each interactive innovation module works collaboratively in the above process: the working condition and rubber material and simulation adaptive linkage module's working condition change and rubber material parameter real-time feedback module monitors the dynamic changes of the multi-field coupled working condition parameters, inputs the changes into the rubber material aging factor dynamic calculation module and fatigue damage accumulation coupling module, and updates the dynamic rubber material parameters in real time; the rubber material performance degradation and simulation load dynamic adjustment module obtains the total degradation coefficient. Input the loading step size adaptive module based on the properties of rubber materials, and through Adjust the loading step size; the simulation deviation and working condition / rubber material parameter correction module receives the deviation data from the deviation source positioning module and outputs parameter correction instructions to the working condition and rubber material performance coupling module according to the deviation source.

[0062] The optimization parameters and mesh density adaptive matching module in the finite element model and intelligent optimization collaborative module obtain the key design parameters of the key parameter identification module, and adjusts the density adjustment coefficient of the mesh density adaptive optimization module according to the parameter change magnitude. When the parameter change is greater than 10% The value is increased by 0.5; the model accuracy and optimization efficiency balancing module, based on the grid density information and the optimization algorithm type, through... Adjust and optimize the number of iterations. To determine the maximum number of iterations, take a value between 100 and 200. The maximum mesh density is set, and the higher the mesh density, the more iterations are required. During the optimization iteration process, if the change in key parameters exceeds 15%, the intelligent identification and cutting module for key areas and the model reconstruction optimization module are triggered to reconstruct the local finite element model.

[0063] The simulation, experiment, and design module's experimental deviation and design parameter reverse optimization module obtains the deviation value, inputs it into the key parameter identification module, and adjusts the optimization weights of the key parameters; the design scheme and experimental verification priority ranking module ranks the optimization schemes according to their sensitivity to deviation, prioritizing the verification of schemes with high sensitivity; the iteration effect quantitative evaluation module... Quantitatively evaluate the effectiveness of each iteration.

[0064] The assembly tolerance and working condition load synergistic influence module in the assembly model and working condition coupling adaptation submodule inputs the assembly tolerance value and multi-field coupled working condition parameters into the constraint and deformation synergistic verification module to analyze the deformation of the rubber seal ring under synergistic action; the assembly constraint and rubber material deformation adaptation module obtains the dynamic rubber material parameters and adjusts the stiffness coefficient of the assembly constraint.

[0065] The contact pressure distribution and wear rate mapping module in the contact calculation and wear prediction linkage module realizes the conversion of contact pressure to wear rate through the Archard model; the wear accumulation and contact area dynamic update module inputs the wear volume data into the contact area dynamic calculation module to update the contact area geometry and pressure distribution in real time.

[0066] The loading strategy and optimization target matching module in the step-by-step loading and optimization target collaboration module adjust the loading method according to the optimization target weight; the loading step size and optimization iteration efficiency linkage module adjusts the step size change rate according to the optimization iteration progress, with the step size change rate set at 0.2-0.3 in the early stage of iteration and 0.05-0.1 in the later stage of iteration.

[0067] Example 2 The technical features that distinguish this embodiment from Embodiment 1 are as follows: it includes a coupling module for working conditions and rubber material properties, a virtual assembly model construction module, a local finite element model generation module, a dynamic sealing performance simulation module, a simulation and test data calibration module, an intelligent optimization design module, an adaptive linkage module for working conditions, rubber materials and simulation, a linkage module for contact calculation and wear prediction, and a coupling and adaptation sub-module for assembly model and working conditions.

[0068] The technical implementation process of this system is as follows: Operating conditions and rubber material performance coupling module: High-temperature and corrosion-resistant sensor arrays are used to collect raw operating conditions such as temperature, pressure and medium concentration in the pipeline. Signal isolation technology is used to avoid interference from corrosive media. After filtering and amplification, the timing synchronization of multiple field parameters is achieved.

[0069] Multi-parameter synergistic loading highlights the dominant role of temperature and pressure. The material aging factor is calculated using the modified Arrhenius equation, and fatigue damage accumulation adopts the Miner linear accumulation criterion. When the total attenuation coefficient is superimposed, the dominant failure role of high-temperature aging is highlighted, and dynamic rubber material performance parameters are output.

[0070] The working condition and rubber material parameter linkage calibration module uses test deviation data to back-calculate and correct rubber material parameters. By adapting the working condition fluctuations to the rubber material parameters, it ensures that the parameters match the working condition fluctuations in real time.

[0071] Virtual assembly model construction module: For the V-shaped cross-section groove structure of rubber sealing rings in chemical pipelines, a basic geometric model is constructed through a parametric geometry generation module, and an adaptive mesh generation algorithm is used to refine the geometry of the V-shaped lip.

[0072] The assembly tolerance dynamic allocation module allocates the tolerance level of each assembly surface based on the tolerance and performance influence model. The constraint and deformation co-verification module applies the interference fit required for high-pressure sealing, calculates the assembly deformation by inputting dynamic rubber material parameters, ensures that the deformation meets the design allowable value, and outputs a virtual rubber sealing ring assembly model containing tolerance and constraint information.

[0073] Local finite element model generation module: Based on the interference fit surface and high pressure surface of the virtual assembly model, the module uses a trained machine learning model to identify the sealing contact area and stress concentration area, uses a surface cutting algorithm to cut out local model segments, and uses a B-spline curve fitting algorithm to smooth the cut surface.

[0074] The adaptive mesh density optimization module adjusts the mesh density according to the stress gradient distribution in the key area, and the reconstructed model compatibility verification module compares the natural frequencies of the reconstructed model and the original model to ensure that their mechanical properties are consistent, and outputs a local finite element model.

[0075] Dynamic sealing performance simulation module: Based on the trend of elastic modulus change in dynamic rubber material parameters, the loading step size is adjusted to avoid insufficient loading step size caused by the decrease in rubber material stiffness; The load gradient dynamic adjustment module uses a linear interpolation algorithm to achieve stable pressure loading.

[0076] The contact pressure and rubber material hardness linkage calculation module corrects the contact pressure based on the dynamic hardness value, and the contact area wear prediction coupling module uses the Archard wear model to calculate the wear volume and outputs the wear volume change curve over time.

[0077] The constitutive adaptive correction module for nonlinear rubber materials selects the Mooney-Rivlin constitutive model, calculates constitutive parameters based on dynamic elastic modulus, corrects nonlinear deformation deviations through polynomial fitting model, and outputs simulation data of corrected sealing performance.

[0078] Simulation and test data calibration module: High-temperature resistant sensors are used to collect multi-dimensional test data such as leakage, contact pressure, and wear. Data synchronization is achieved through timestamp synchronization technology, and Gaussian filtering algorithm is used to remove sensor noise under high-temperature environment and standardize the data.

[0079] The deviation source localization module determines the main sources of deviation through variance analysis, and the correction parameter priority sorting module prioritizes the correction of key deviation parameters, iteratively verifying until the deviation rate meets the threshold requirement.

[0080] Intelligent optimization design module: Set the sealing life, leakage amount and manufacturing cost as optimization objectives, determine the weight coefficients through the analytic hierarchy process, and use an algorithm adapted to multi-objective optimization for optimization.

[0081] The key parameter identification module uses sensitivity analysis to determine the lip thickness, interference fit amount, and rubber material hardness as key parameters, while the parameter fluctuation impact prediction module simulates the impact of key parameter fluctuations on performance.

[0082] The solution rapid screening module selects and retains advantageous solutions through Pareto optimal solution screening, while the optimal solution detail optimization module adjusts key parameters and outputs the final optimized solution.

[0083] The various interactive innovation modules work together. The working condition and rubber material and simulation adaptive linkage module update material parameters and adjust loading step size in real time. The contact calculation and wear prediction linkage module realizes dynamic linkage between contact pressure and wear rate. The assembly model and working condition coupling adaptation sub-module ensures the stability of deformation under the collaborative action.

[0084] Example 3 The technical features that distinguish this embodiment from Embodiment 1 are as follows: it includes a coupling module for working conditions and rubber material properties, a virtual assembly model construction module, a local finite element model generation module, a dynamic sealing performance simulation module, a simulation and test data calibration module, an intelligent optimization design module, a finite element model and intelligent optimization collaboration module, a simulation and test and design module, and a step-by-step loading and optimization target collaboration module.

[0085] The technical implementation process of this system is as follows: Working condition and rubber material performance coupling module: High-response speed sensor is used to collect raw data of working conditions of hydraulic system such as working pressure, reciprocating speed, oil temperature, etc. Signal amplification technology is used to improve the identification of weak signals and realize the timing synchronization of multiple field parameters.

[0086] Multi-parameter synergistic loading highlights the dominant role of pressure and reciprocating velocity. The material aging factor is calculated using the modified Arrhenius equation, and fatigue damage accumulation adopts the Miner linear accumulation criterion. When the total attenuation coefficient is superimposed, the dominant failure role of fatigue damage is highlighted, and dynamic rubber material performance parameters are output.

[0087] The working condition and rubber material parameter linkage calibration module uses test deviation data to back-calculate and correct rubber material parameters, and dynamically updates rubber material performance parameters to address the frequent pressure fluctuations under high-frequency reciprocating conditions.

[0088] Virtual assembly model construction module: For the Y-shaped cross-sectional structure of the rubber seal ring in the hydraulic system, a basic geometric model is constructed through the parametric geometry generation module, and the Y-shaped lip is geometrically refined using an adaptive mesh generation algorithm.

[0089] The assembly tolerance dynamic allocation module allocates the tolerance level of each assembly surface based on the tolerance and performance influence model. The constraint and deformation co-verification module applies the interference fit amount, inputs dynamic rubber material parameters to calculate the assembly deformation amount, ensures that the deformation amount meets the design allowable value, and outputs a virtual rubber sealing ring assembly model containing tolerance and constraint information.

[0090] Local finite element model generation module: Based on the interference fit surface and reciprocating contact surface of the virtual assembly model, the module uses a trained machine learning model to identify the sealing contact area and stress concentration area, uses a plane cutting algorithm to cut out local model segments, and uses a B-spline curve fitting algorithm to smooth the cut surface.

[0091] The adaptive mesh density optimization module adjusts the mesh density according to the stress gradient distribution in the key area, and the reconstructed model compatibility verification module compares the natural frequencies of the reconstructed model and the original model to ensure that their mechanical properties are consistent, and outputs a local finite element model.

[0092] Dynamic sealing performance simulation module: Based on the trend of elastic modulus change in dynamic rubber material parameters, the loading step size is adjusted to adapt to the rapid load changes under high frequency reciprocating motion; The load gradient dynamic adjustment module uses a linear interpolation algorithm to achieve stable pressure loading and ensure that the load application is synchronized with the reciprocating motion.

[0093] The contact pressure and rubber material hardness linkage calculation module corrects the contact pressure based on the dynamic hardness value, and the contact area wear prediction coupling module uses the Archard wear model to calculate the wear volume and outputs the wear volume change curve over time.

[0094] The constitutive adaptive correction module for nonlinear rubber materials selects the Mooney-Rivlin constitutive model, calculates constitutive parameters based on dynamic elastic modulus, corrects nonlinear deformation deviations through polynomial fitting model, and outputs simulation data of corrected sealing performance.

[0095] Simulation and test data calibration module: High-response sensors are used to collect multi-dimensional test data such as leakage, contact pressure, and wear. Data synchronization is achieved through timestamp synchronization technology, and Gaussian filtering algorithm is used to remove sensor noise caused by high-frequency vibration and standardize the data.

[0096] The deviation source localization module determines the main sources of deviation through variance analysis, and the correction parameter priority sorting module prioritizes the correction of key deviation parameters, iteratively verifying until the deviation rate meets the threshold requirement.

[0097] Intelligent optimization design module: Set the sealing life, leakage amount and manufacturing cost as optimization objectives, determine the weight coefficients through the analytic hierarchy process, and use an algorithm adapted to multi-objective optimization for optimization.

[0098] The key parameter identification module identifies lip thickness, interference fit amount, and rubber material fatigue life as key parameters through sensitivity analysis, while the parameter fluctuation impact prediction module simulates the impact of key parameter fluctuations on performance.

[0099] The solution rapid screening module selects and retains advantageous solutions through Pareto optimal solution screening, while the optimal solution detail optimization module adjusts key parameters and outputs the final optimized solution.

[0100] The various interactive innovation modules work together. The finite element model and intelligent optimization collaborative module adjusts the mesh density and iteration number according to parameter changes. The simulation, experiment and design module optimizes the design parameters in reverse based on deviation data and prioritizes the verification of sensitive schemes. The step-by-step loading and optimization target collaborative module adjusts the loading method and step size change rate according to the optimization target and iteration progress.

[0101] This application also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, which, when executed by a computer, cause the computer to perform a system or system as described in the foregoing embodiments.

[0102] Those skilled in the art will understand that all or part of the processes in the systems described in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the embodiments of the above systems. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0103] It should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A multi-field coupling intelligent simulation optimization system for a rubber seal ring, characterized in that, include: Working condition and rubber material performance coupling module: Collects and transforms raw working condition data through multi-field coupled working condition parameter modeling, calculates and outputs basic working condition and material parameters; Virtual assembly model construction module: Based on basic working conditions and material parameters, it constructs a basic geometric model through parametric geometry generation and complex structure refinement, dynamically allocates assembly tolerances and verifies deformation by combining multi-field coupled working condition parameters, and outputs a virtual assembly model containing tolerance and constraint information. Local finite element model generation module: Based on the constraint information and multi-field coupled working condition parameters of the virtual assembly model, it intelligently identifies key areas of sealing contact and stress concentration and smoothly cuts the boundaries, adaptively adjusts the mesh density according to the stress gradient, verifies the mechanical consistency of the model, and outputs a local finite element model. Dynamic sealing performance simulation module: Through local finite element model and dynamic working conditions and material parameters, it adaptively optimizes the step size and dynamically adjusts the load gradient to achieve a smooth transition of load application; Simulation and experimental data calibration module: Collects multi-dimensional experimental data and performs noise reduction and standardization processing; compares simulation data and experimental data to locate the source of deviation and quantifies the degree of influence; sorts parameters by weight, corrects them, iteratively verifies them, and provides feedback on the corrected parameters; Intelligent optimization design module: Receives calibrated sealing performance simulation data, determines weighting coefficients and selects an appropriate optimization algorithm, identifies key design parameters and predicts their fluctuation effects, selects several optimization schemes and adjusts key parameters, and finally outputs the optimal design scheme.

2. The rubber seal ring multi-field coupling intelligent simulation optimization system according to claim 1, characterized in that, The working condition and rubber material performance coupling module includes a multi-field coupled working condition parameter modeling unit, which collects raw data of temperature, pressure, and medium type working conditions, converts physical working condition parameters into simulation input parameters, realizes the time-series synchronization and coupled application of multiple field parameters, and allocates loading priority based on the weight of the influence of each field parameter on sealing performance.

3. The rubber seal ring multi-field coupling intelligent simulation optimization system according to claim 1, characterized in that, The working condition and rubber material performance coupling module includes a rubber material performance dynamic decay modeling unit. Based on the basic properties of rubber materials, the material aging factor dynamic calculation module obtains the decay law of rubber material performance with the duration of working conditions, and combines it with the fatigue damage accumulation coupling module to realize the collaborative modeling of aging and fatigue.

4. The rubber seal ring multi-field coupling intelligent simulation optimization system according to claim 1, characterized in that, The virtual assembly model construction module includes a complex structure adaptive modeling unit. The unit constructs a basic geometric model through a parametric geometry generation module and uses an adaptive mesh generation algorithm to refine the complex structural areas of the rubber sealing ring groove and lip, ensuring the consistency between the geometric model and the actual structure.

5. The rubber seal ring multi-field coupling intelligent simulation optimization system according to claim 1, characterized in that, The local finite element model generation module includes a key area intelligent identification and cutting unit and a mesh density adaptive optimization unit. The key area intelligent identification and cutting unit uses machine learning algorithms to identify key areas, including rubber sealing contact and stress concentration, and performs mesh smoothing on the cutting surface. The mesh density adaptive optimization unit adjusts the mesh density according to the stress gradient distribution of the key areas to verify the consistency of mechanical properties between the reconstructed model and the original assembly model.

6. The rubber seal ring multi-field coupling intelligent simulation optimization system according to claim 1, characterized in that, The dynamic sealing performance simulation module comprises a loading step size adaptive unit, receives dynamic rubber material parameters, dynamically optimizes the step size according to the change trend of the rubber material elastic modulus and hardness, and realizes smooth transition of the load application by means of a load gradient dynamic adjustment module.

7. The rubber seal ring multi-field coupling intelligent simulation optimization system according to claim 1, characterized in that, The dynamic sealing performance simulation module comprises a contact pressure linkage calculation unit, corrects a contact pressure calculation model based on the hardness value in the dynamic rubber material parameters, and converts the contact pressure distribution into a wear rate through a contact area wear prediction coupling module.

8. The rubber seal ring multi-field coupling intelligent simulation optimization system according to claim 1, characterized in that, The simulation and test data calibration module comprises a multi-dimensional test data synchronization unit and a deviation source positioning unit, the multi-dimensional test data synchronization unit collects multi-dimensional test original data, including leakage, contact pressure and wear, removes data noise and converts the test data into consistent dimensions with the simulation data; the deviation source positioning unit compares the simulation results with the standardized test data, determines the main source of deviation and quantifies the influence degree of each source.

9. The rubber seal ring multi-field coupling intelligent simulation optimization system according to claim 1, characterized in that, The intelligent optimization design module comprises a multi-objective optimization weight dynamic distribution unit, determines the weight coefficient of the target according to the sealing performance target requirements of the rubber sealing ring, including leakage, sealing life and manufacturing cost, and selects the corresponding optimization algorithm according to the optimization target type.

10. The rubber seal ring multi-field coupling intelligent simulation optimization system according to claim 1, characterized in that, The intelligent optimization design module comprises a key parameter identification unit, which determines the design parameters that significantly affect the sealing performance based on the sealing performance simulation results through sensitivity analysis, and predicts the influence of parameter fluctuation on performance by means of a parameter fluctuation influence prediction module.

Images