Method for optimizing air tightness of soft pressurizing cabin

Abstract

The invention provides an air tightness optimization method for a soft pressurization cabin, and the method comprises the steps: presetting a dynamic sensor array at a specific position where a structure is liable to fail according to a failure risk assessment table, collecting stress concentration data caused by non-uniform pressure distribution in real time, and generating a stress distribution dynamic graph containing a time sequence; the dynamic adjusting device is driven to operate through the homogenized pressure distribution adjusting scheme, pressure field data in the cabin body is updated in real time, whether material fatigue is within the fracture risk range or not is judged, and a fatigue state monitoring report is generated; obtaining a fracture risk index in the fatigue state monitoring report, carrying out iterative adjustment on the fiber weaving density and the elastic modulus of the key area by adopting a material design optimization algorithm, and determining a final structure layout parameter for improving the performance; and extracting a limiting condition of dynamic adjustment difficulty from the final structure layout parameters, simulating a cabin operation state in an extreme environment through a digital twin technology, calculating a boundary value of performance limitation, and obtaining a verification result of performance improvement.

Description

Technical Field

[0001] The present invention relates to the technical fields of material science and structural mechanics, and in particular to a method for optimizing the air tightness of a soft pressurized cabin. Background Art

[0002] The application of materials science and structural mechanics in extreme environments is one of the pillars of modern scientific and technological development. Its importance is reflected in the breakthroughs it has made in deep space exploration, deep-sea operations, and polar life support systems. These scenarios place stringent demands on equipment lightweighting, high pressure bearing capacity, and environmental adaptability, which are directly related to the success of the mission and the safety of personnel. However, current solutions still have significant limitations. Traditional soft pressurized cabins often rely on a single elastomer and woven fiber layer, resulting in insufficient airtightness, limited pressure bearing capacity, and high weight. At the same time, uneven pressure distribution and lack of dynamic adjustment capabilities further weaken their reliability under extreme conditions. These defects make it difficult for existing technologies to meet the increasingly complex application needs, and innovative breakthroughs are urgently needed.

[0003] While existing technologies have achieved basic functions to a certain extent, their limitations expose core challenges that cannot be ignored. In particular, three technical factors—airtightness, pressure resistance, and uniform pressure distribution—are key constraints on the performance of soft pressurized cabins. Inadequate airtightness leads to high leakage rates, limiting the cabin's long-term use in vacuum or high-pressure environments; low pressure resistance makes the structure susceptible to failure under extreme pressures; and uneven pressure distribution triggers localized stress concentrations, accelerating material fatigue and cracking. These unresolved technical factors not only reduce the cabin's service life but also increase safety risks. This is especially true in scenarios where the pressure inside and outside the cabin fluctuates frequently, where the lack of dynamic adaptability exacerbates the problem.

[0004] Therefore, the key challenge in the technological innovation of soft pressurized cabins is how to significantly improve airtightness and pressure resistance by optimizing material design and structural layout while maintaining lightweight, while also achieving uniform pressure distribution and dynamic adjustment capabilities. Solving this problem will directly determine whether they can operate stably in extreme environments such as deep space and the deep sea, providing reliable protection for life support systems. Summary of the Invention

[0005] The present invention provides a method for optimizing the airtightness of a soft pressurized cabin, which mainly includes:

[0006] Obtain the current material parameters and structural layout data of the soft pressurized cabin, simulate the high leakage rate caused by insufficient airtightness in extreme environments through finite element analysis, calculate the gas permeability and stress distribution of each part, and obtain the distribution map of key areas with high leakage rate;

[0007] Based on the distribution map of key areas with high leakage rates, a multi-layer composite material superposition algorithm is used to process material parameters, determine the optimal thickness ratio and bonding strength of the elastomer and woven fiber layers, and generate an optimized material combination solution;

[0008] Potential defects with low compressive strength are extracted from the optimized material combination scheme. Molecular dynamics simulation is used to analyze the changes in the intermolecular forces of the material under high pressure, and the specific locations where the structure is prone to failure are determined to obtain a failure risk assessment table.

[0009] Based on the failure risk assessment table, dynamic sensor arrays are preset at specific locations of the structure prone to failure to collect stress concentration data caused by uneven pressure distribution in real time and generate a dynamic stress distribution diagram including a time series.

[0010] If the stress distribution dynamic diagram shows that the local stress concentration exceeds the preset threshold, the cabin airflow distribution is adjusted through the adaptive pressure regulation algorithm, and the pressure compensation value of each area is calculated to obtain a uniform pressure distribution adjustment plan;

[0011] The dynamic adjustment device is driven by a uniform pressure distribution adjustment scheme to update the pressure field data inside the cabin in real time, determine whether the material fatigue is within the rupture risk range, and generate a fatigue status monitoring report.

[0012] Obtaining rupture risk indicators from fatigue condition monitoring reports, the material design optimization algorithm is used to iteratively adjust the fiber weave density and elastic modulus in key areas to determine the final structural layout parameters for improved performance.

[0013] Extracting constraints that make dynamic adjustment difficult from the final structural layout parameters, simulating cabin operation in extreme environments through digital twin technology, calculating performance-limiting boundary values, and verifying performance improvements.

[0014] Based on the verification results of performance improvement, combined with the multi-layer composite material superposition algorithm and the adaptive pressure regulation algorithm, a complete technical optimization plan for the soft pressurized cabin is generated, and an implementation plan including material formulation and structural adjustment is output.

[0015] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0016] The present invention discloses a method for optimizing the airtightness of a soft pressurized cabin. The method simulates leakage problems in extreme environments through finite element analysis, identifies key leakage areas, and optimizes material parameters using a multi-layer composite material superposition algorithm. Combined with molecular dynamics simulation, the present invention evaluates the risk of structural failure and sets a dynamic sensor array at locations prone to failure to monitor stress distribution in real time. When it is detected that the local stress concentration exceeds the threshold, an adaptive pressure regulation algorithm is used to balance the pressure distribution in the cabin. The present invention also adjusts the fiber weaving density and elastic modulus through a material design optimization algorithm, and uses digital twin technology to verify performance improvement. Ultimately, the present invention generates a complete technical optimization solution including material formulation and structural adjustment, which effectively improves the airtightness and structural stability of the soft pressurized cabin in extreme environments, extends its service life, and improves safety performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 The figure is a flow chart of a method for optimizing the air tightness of a soft pressurized cabin according to the present invention.

[0018] Figure 2 Schematic diagram of a method for optimizing the air tightness of a soft pressurized cabin according to the present invention.

[0019] Figure 3 This is another schematic diagram of a method for optimizing the air tightness of a soft pressurized cabin according to the present invention. DETAILED DESCRIPTION

[0020] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] like Figure 1-3 In this embodiment, a method for optimizing the airtightness of a soft pressurized cabin may specifically include:

[0022] S101. Obtain the current material parameters and structural layout data of the soft pressurized cabin, simulate the high leakage rate caused by insufficient airtightness in extreme environments through finite element analysis, calculate the gas permeability and stress distribution of each part, and obtain a distribution map of key areas with high leakage rates.

[0023] The material parameters and structural layout data of the soft pressurized cabin are obtained, and the corresponding values are extracted from a preset database to obtain the initial model parameters. The initial model parameters are simulated and calculated through finite element analysis, and a scenario with insufficient airtightness is generated under extreme conditions to obtain the stress distribution and gas permeability data of each part. The gas permeability data is sorted and analyzed to determine the parts where the permeability exceeds the preset threshold, and a set of high permeability areas is obtained. The stress values corresponding to the set of high permeability areas are extracted from the stress distribution data, and the stress concentration areas are determined through comparative analysis to obtain preliminary key areas. The preliminary key areas are grouped using a clustering algorithm to obtain spatially adjacent areas with similar permeabilities to obtain the optimized key area distribution. The optimized key area distribution is combined with the structural layout data through grid mapping technology to generate a key area distribution map. If there are isolated points in the key area distribution map, the abnormal points are eliminated through neighborhood analysis to obtain the final distribution map.

[0024] Specifically, first, the current material parameters of the soft pressurized cabin are obtained through the sensor network, including an elastic modulus of 1-10MPa, a Poisson's ratio of 0.5, and structural layout data such as a wall thickness of 3mm and an internal pressure of 1MPa. Finite element analysis software is used to establish a three-dimensional model of the pressurized cabin, using tetrahedral meshing with a mesh size of 1mm to ensure model accuracy. In extreme environments, to simulate insufficient airtightness, the external pressure is set to 15MPa and the temperature range is -50°C to 70°C. By calculating the gas permeability of each part, Darcy's law is used, and the permeability coefficient is 5×10^-12m 2 Based on the stress distribution and using the Von Mises stress criterion, the maximum stress reached 120 MPa at the cabin joints. Analysis results showed that the critical areas with high leakage rates were concentrated in the cabin joints and welds, with permeability rates reaching as high as 8 L / min, far exceeding the 2 L / min in other areas. Using visualization technology, a distribution map of these critical areas with high leakage rates was generated, providing data support for subsequent design optimization.

[0025] S102. For the distribution map of key areas with high leakage rates, a multi-layer composite material superposition algorithm is used to process material parameters, determine the optimal thickness ratio and bonding strength of the elastomer and the woven fiber layer, and generate an optimized material combination solution.

[0026] The material parameters of the key areas are processed using a multi-layer composite algorithm to determine the initial values of the thickness ratio and bonding strength. Permeability data is extracted from the key areas, and the support vector machine algorithm is used to determine the degree of influence of the thickness ratio on the permeability to obtain the classification results. The number of layers of woven fibers is adjusted based on the classification results, and an updated model of the stress distribution is generated using meshing technology. Based on the stress distribution in the updated model, the deformation data of the elastomer is obtained to determine the correction range of the bonding strength. If the correction range exceeds the preset threshold, the combination of thickness ratio and bonding strength is optimized using a linear regression algorithm to obtain an adjusted parameter set. The adjusted parameter set is used to update the multi-layer composite structure and generate a distribution map of the optimization scheme. The optimization scheme distribution map is processed using neighborhood analysis technology, and isolated areas are eliminated to obtain the final material combination scheme.

[0027] Specifically, for the distribution map of key areas with high leakage rates, a three-dimensional model was first established using finite element analysis software, and the boundary conditions of the leakage area were set to a pressure difference of 5MPa. ANSYS Fluent was used for fluid dynamics simulation to obtain the flow velocity distribution cloud map and identify high leakage areas with flow velocities exceeding 2m / s. Based on the simulation results, a genetic algorithm was used to optimize the material parameters, setting the population size to 50, the number of iterations to 100, and the optimization goal to set the leakage rate below 0.1L / min. The algorithm crossover probability was set to 8, the mutation probability to 1, and the fitness function was used to calculate the optimal thickness ratio of the elastomer to the braided fiber layer to be 1:3. In the material bonding strength optimization stage, molecular dynamics simulation LAMMPS software was used, the COMPASS force field was set, the simulated temperature was 300K, the pressure was 1atm, and different bonding interface energies were calculated. When the interface energy reached 50mJ / m 2 Finally, a multi-physics coupling analysis was performed using ABAQUS, and the optimized material parameters were imported into the model, including an elastomer layer with an elastic modulus of 1-10 MPa and a Poisson's ratio of 3, and a carbon fiber braided layer with a tensile strength of 800 MPa. Stress-strain analysis was performed to verify that the maximum deformation was less than 1 mm under a working pressure of 8 MPa, meeting the design requirements. The entire process automatically processed data streams through Python scripts, calling various software APIs to implement parameter transfer, and ultimately generated a solution report containing 5 preferred material combinations. Each combination was marked with specific thickness ratios, bonding process parameters, and expected performance indicators.

[0028] S103. Extract potential defect points with low compressive strength from the optimized material combination scheme, analyze the changes in the intermolecular forces of the material under high pressure through molecular dynamics simulation, determine the specific locations where the structure is prone to failure, and obtain a failure risk assessment table.

[0029] Molecular dynamics simulations are used to obtain data on the force variation of material combinations under high pressure to determine the distribution characteristics of defect points. The fluctuation range associated with compressive strength is extracted from the force variation data to determine the correlation range of defect points in structural failure. A Monte Carlo algorithm is used to process the distribution characteristics within the fluctuation range to obtain a probability distribution of defect point evolution. High-risk areas of the material combination are divided according to the probability distribution to obtain a priority ranking of structural failure. If the priority ranking exceeds the preset threshold, the local accuracy of the simulation analysis is adjusted using meshing technology to determine the correction range of the force variation. The parameter set of the molecular dynamics simulation is updated based on the correction range to obtain an optimized position judgment result. The position judgment result is processed using neighborhood analysis technology to eliminate low-probability areas and generate the final risk assessment data.

[0030] Specifically, potential defects of low compressive strength were extracted from the optimized material combination scheme. First, the molecular dynamics simulation software LAMMPS was used to analyze the changes in the intermolecular forces of the material under high pressure. The simulation conditions were set to a temperature of 0.50K and a pressure of 10MPa. The ReaxFF force field was used to describe the intermolecular interactions. The simulation time step was 1fs and the total simulation time was 100ps. By calculating the changes in the intermolecular bond length, bond angle and non-bonded force, the area where the intermolecular force was significantly weakened under pressure loading was identified, which was mainly concentrated at the interface between the elastomer and the woven fiber layer, and the interface energy was reduced to 30mJ / m 2 The following shows that this area is prone to failure under high pressure. Further through stress distribution analysis, the Voronoi algorithm is used to partition the internal stress field of the material and identify stress concentration areas, where the maximum stress value reaches 600MPa, exceeding the yield strength of the material. Based on the above analysis results, combined with the failure mode and effect analysis (FMEA) method, a quantitative assessment of potential defects is performed, setting the failure severity to 8, the probability of occurrence to 6, the detection difficulty to 7, and the calculated risk priority number (RPN) to 336. A failure risk assessment table is generated, which details the location, failure mode and risk level of each defect point, providing data support for subsequent material improvements. The entire process uses Python scripts to realize data automation processing, calling LAMMPS and MATLAB APIs for simulation and calculation to ensure the accuracy and consistency of the analysis results.

[0031] S104. According to the failure risk assessment table, a dynamic sensor array is preset at specific locations where the structure is prone to failure, and stress concentration data caused by uneven pressure distribution is collected in real time to generate a stress distribution dynamic graph including a time series.

[0032] Dynamic sensors collect pressure distribution data to obtain a sequence of changes in stress concentration areas. Time series features are extracted from the change sequence to determine the dynamic evolution of the distribution. Preset arrays are used to analyze the time series data to identify locations at high risk of structural failure. Dynamic sensor acquisition density is adjusted for high-risk locations to generate updated local pressure distribution data. A support vector machine is used to process this updated data to determine the boundaries of stress concentration. Distribution features are prioritized based on the boundaries to identify key areas for real-time analysis. Neighborhood analysis techniques are used to process data from key areas to generate dynamic distribution results that include evolutionary trends.

[0033] Specifically, when presetting the dynamic sensor array at specific locations where the structure is prone to failure, the key monitoring points are first determined according to the failure risk assessment table. For example, sensors are arranged at the mid-span position and near the supports of the bridge, and the sensor spacing is set to 5 meters to ensure coverage of key areas. The sensor uses high-precision strain gauges with a sampling frequency of 100 Hz, which can capture tiny stress changes in real time. During the data acquisition process, the sensor data is sent to the central processing unit through a wireless transmission module, and the Kalman filter algorithm is used to pre-process the data to eliminate noise interference and ensure data accuracy. When generating a dynamic stress distribution diagram, the collected stress data is modeled using finite element analysis software, and combined with time series analysis methods, a stress distribution diagram containing a time dimension is generated.

[0034] For example, by analyzing the stress changes on bridges under vehicle loads, it was found that the stress peak at the midspan reached 50 MPa when a vehicle passed through, while the stress distribution near the supports was more uniform, with a peak of only 20 MPa. Machine learning algorithms, such as support vector machines, were further used to analyze historical data, predict areas of potential stress concentration in the future, and implement reinforcement measures in advance. This approach enables real-time monitoring and early warning of structural stress distribution, effectively reducing the risk of structural failure.

[0035] S105. If the stress distribution dynamic graph shows that the local stress concentration exceeds a preset threshold, the airflow distribution in the cabin is adjusted using an adaptive pressure regulation algorithm, and the pressure compensation value of each area is calculated to obtain a uniform pressure distribution adjustment solution.

[0036] If the dynamic graph detects that local stress exceeds a preset threshold, an adaptive algorithm is used to analyze the changing trend of airflow distribution and calculate the initial value of pressure compensation. Based on the initial value, the configuration parameters of the airflow distribution are adjusted to obtain updated pressure distribution data for each area. The updated data is processed using a support vector machine to determine the boundary range for uniform distribution. The boundary range is used to prioritize regional calculations, resulting in a sequence of key areas for real-time adjustment. The sequence of key areas is processed using neighborhood analysis technology to obtain a dynamic adjustment plan for airflow distribution. If the pressure compensation for a certain area in the dynamic adjustment plan exceeds the preset range, the configuration parameters for that area are recalculated to obtain an optimized uniform distribution result. Based on the optimized results, the execution instructions for real-time adjustment are updated to generate the final airflow distribution plan.

[0037] Specifically, in the stress distribution dynamic diagram, when it is detected that the local stress concentration exceeds a preset threshold.

[0038] For example, if the stress value in a certain area reaches 150 MPa (while the threshold is 120 MPa), the system automatically activates the adaptive pressure adjustment algorithm. This algorithm first calculates the current stress distribution through finite element analysis (FEA) to identify the specific location and extent of the stress concentration areas. The algorithm then calculates the required pressure compensation value for each area based on the degree of stress concentration and the area.

[0039] For example, for stress concentration area A, the algorithm calculates that pressure compensation should be increased by 5kPa, while for area B, it should be reduced by 3kPa. The system then adjusts the airflow distribution within the cabin and optimizes the airflow path using CFD simulation to ensure accurate pressure compensation for each area. Ultimately, the system generates a uniform pressure distribution adjustment plan, achieving a more balanced stress distribution throughout the cabin.

[0040] For example, the overall stress value is controlled between 100 MPa and 110 MPa, thereby effectively avoiding the potential risks caused by local stress concentration.

[0041] S106. The dynamic adjustment device is driven to operate through the uniform pressure distribution adjustment scheme, the pressure field data inside the cabin is updated in real time, whether the material fatigue is within the rupture risk range is determined, and a fatigue status monitoring report is generated.

[0042] The device is driven to operate by adjusting the solution, obtaining real-time updated data on the pressure field and confirming the integrity of data collection. Based on the real-time updated data, a random forest algorithm is used to process the changing trends of the pressure field and determine the distribution characteristics of material fatigue. If the distribution characteristics of material fatigue exceed the rupture risk range, corresponding control instructions are generated through dynamic adjustment to obtain the adjustment parameters for the device operation. The device operating status is updated based on the adjustment parameters, and a new round of pressure field data is obtained to determine the degree of relief of the fatigue state. The relief degree data is processed using neighborhood analysis technology to obtain the optimization direction of the pressure distribution. The execution order of dynamic adjustment is adjusted according to the optimization direction, and real-time feedback data of the device operation is obtained to determine whether the material fatigue is tending to stabilize. If the material fatigue is tending to stabilize, the monitoring results are updated through data acquisition to determine the degree of homogenization of the pressure field.

[0043] Specifically, through a uniform pressure distribution adjustment scheme, the dynamic adjustment device can monitor the pressure field data inside the cabin in real time.

[0044] For example, using a finite element analysis algorithm, the cabin is divided into 1,000 cells. The pressure value of each cell is collected by sensors and input into the calculation model. The model uses an iterative method, updating the pressure distribution with each iteration until the pressure difference between each cell is less than 1 Pascal, ensuring a uniform pressure field. During the real-time update of the pressure field data, the system uses a Kalman filter algorithm to process the sensor data, reducing noise interference and improving data accuracy.

[0045] For example, the error in filtered pressure data is controlled within ±0.5 Pascals. Based on the updated pressure field data, the system uses a fatigue life prediction model to determine the material's fatigue state. This model uses Miner's linear cumulative damage theory, combined with the material's SN curve, to calculate the fatigue damage value for each element.

[0046] For example, when the fatigue damage value of a unit reaches 8, the system determines that the unit is at risk of rupture. Finally, the system generates a fatigue status monitoring report that includes the fatigue damage value of each unit, the rupture risk level, and recommended maintenance measures.

[0047] For example, the report indicated that the fatigue damage value of five units exceeded 8, recommending immediate material replacement or reinforcement. Through this process, the system achieves real-time monitoring and early warning of the cabin pressure field and material fatigue status, ensuring safe equipment operation.

[0048] S107. Obtain the rupture risk index from the fatigue status monitoring report, use the material design optimization algorithm to iteratively adjust the fiber weaving density and elastic modulus in the key areas, and determine the final structural layout parameters to improve performance.

[0049] The rupture risk data in the monitoring report is obtained, and the rupture risk indicators are processed through data cleaning technology to obtain standardized risk distribution characteristics. Based on the standardized risk distribution characteristics, the cluster analysis method is used to divide the key areas and determine the fatigue state differences of each area. Based on the fatigue state differences, the initial values of the fiber weaving density and elastic modulus are extracted from the preset material database to obtain a preliminary material design scheme. The preliminary material design scheme is processed through the optimization algorithm, and the fiber weaving density and elastic modulus are iteratively adjusted to determine the optimization parameters of the key areas. If the optimization parameters exceed the preset threshold, the structural layout is adjusted through parameter smoothing technology to obtain smoothed layout data. Based on the smoothed layout data, real-time feedback fatigue state data is obtained to judge the performance stability of the key areas. The performance stability data is processed through neighborhood analysis technology to determine the final structural layout parameters.

[0050] Specifically, to extract rupture risk indicators from fatigue condition monitoring reports, the composite structure's stress-strain field is first simulated using finite element analysis software (such as ANSYS). Loading conditions are set to a cyclic alternating stress amplitude of ±200 MPa, a frequency of 10 Hz, and a number of cycles of 10^6. The stress spectrum is statistically analyzed using the rainflow counting method, and the damage degree D is calculated in conjunction with Miner's linear cumulative damage theory. Areas with D ≥ 8 are marked as high-risk. For high-risk areas, a mapping model is established between fiber density ρ and elastic modulus E, with initial parameters set to ρ = 0.8 g / cm³ and E = 120 GPa. A genetic algorithm is used for multi-objective optimization, with a population size of 100, a crossover probability of 85, and a mutation probability of 0.1. The objective function is to minimize the maximum principal stress σ_max and maximize the fatigue life N_f. Constraints include ρ ∈ [5, 2] g / cm³ and E ∈ [100, 150] GPa. Parametric modeling is performed using ABAQUS at each iteration, automatically adjusting element properties and recalculating the stress field. The optimization process terminated when the fitness function's rate of change remained below 5% for five consecutive generations. The optimal solution was output as ρ = 0.5 g / cm³ and E = 138 GPa. This reduced σ_max by 27% and increased N_f to 8 × 10^6 cycles. Finally, a Python script was used to import the optimized parameters into CATIA to generate a 3D layup model, completing the structural layout update.

[0051] S108. Extract the constraints that make dynamic adjustment difficult from the final structural layout parameters, simulate the cabin operation status under extreme environments through digital twin technology, calculate the boundary values of performance limitations, and obtain verification results of performance improvement.

[0052] The final structural layout parameters are processed through parameter extraction technology to obtain the constraint data for dynamic adjustment. Based on the constraint data, digital twin technology is used to simulate the cabin operation status under extreme environments to obtain the operation status distribution. Through the operation status distribution, the performance limitation range of the cabin operation under extreme environments is calculated, and the boundary value set is determined. For the boundary value set, verification data associated with the operation status is obtained to determine the distribution characteristics of the performance limitation. If the distribution characteristics exceed the preset threshold, the boundary value set is adjusted through smoothing technology to obtain the adjusted verification data. Based on the adjusted verification data, the K-means clustering algorithm is used to divide the performance-limited area range and determine the optimized operation status parameters. The optimized operation status parameters are processed through neighborhood analysis technology to obtain a dynamic adjustment plan that matches the structural layout.

[0053] Specifically, based on the dynamic adjustment constraints in the final structural layout parameters, digital twin technology was used to construct a multi-physics coupling model of the cabin, with environmental parameters set as a temperature gradient of -50°C to 200°C, a pressure fluctuation of 1 to 5 MPa, and a random vibration spectral density of 0.1 g² / Hz. A real-time data interaction channel was established through Simcenter 3D, the finite element mesh size was controlled within 5 mm, and an explicit dynamics algorithm was used to solve the transient response, with a time step set to 1 microsecond. For performance boundary calculations, the critical criteria were defined as local strain exceeding 8% or modal frequency offset greater than 15%. The Kriging surrogate model was used to establish the input and output response surface, with 200 sampling points, a Gaussian radial basis kernel function, and a correlation coefficient threshold set to 95. When five consecutive over-limit alarms were detected in the door hinge area within three seconds, an adaptive adjustment strategy was triggered. A particle swarm optimization algorithm was used to adjust the stiffness distribution of the support structure. The population was initialized with an elastic modulus range of 80 to 200 GPa, an inertia weight linearly decreasing from 9 to 4, and a learning factor of c1 = c2 = 8. After 50 iterations, the optimal stiffness configuration was output as E1 = 175 GPa (upper edge) and E2 = 92 GPa (lower edge). The optimization results were mapped to the digital twin in real time using ANSYS Twin Builder. Monitoring data showed that the maximum deformation under extreme load was reduced from 13 mm to 1 mm, and the resonant frequency shift was controlled within 2%.

[0054] S109. Based on the verification results of performance improvement, combined with the multi-layer composite material superposition algorithm and the adaptive pressure regulation algorithm, a complete technical optimization plan for the soft pressurized cabin is generated, and an implementation plan including material formulation and structural adjustment is output.

[0055] Performance distribution characteristics are obtained from validation data. The composite material data is processed using a multi-layer composite material overlay algorithm to obtain material formulation parameters. Based on the material formulation parameters, the formulation adjustment range is determined, and adjustment data associated with the pressure distribution is obtained. The pressure distribution data is processed using an adaptive pressure adjustment algorithm to obtain a set of parameters for structural adjustment. Data processing techniques are used to analyze the parameter set to determine whether the performance distribution meets a preset threshold. If the threshold is exceeded, the parameter set is adjusted using smoothing techniques to obtain updated structural adjustment data. Based on the updated structural adjustment data, a formulation adjustment solution that matches the composite material is obtained to determine the optimized material formulation. The optimized material formulation is processed using neighborhood analysis techniques to obtain a structural adjustment solution consistent with the pressure adjustment. Based on the structural adjustment solution, data processing techniques are used to generate a complete optimization solution output.

[0056] Specifically, in the optimization design of the soft pressurized cabin, a multi-layer composite material stacking algorithm was used. The number of material layers was defined as 8, each with a thickness of 5 mm. The material properties included carbon fiber reinforced epoxy resin (elastic modulus 120 GPa, Poisson's ratio 3) and aramid fiber reinforced polyurethane (elastic modulus 80 GPa, Poisson's ratio 0.5). The laminate model was established using the finite element analysis software Abaqus, with a grid size of 3 mm. The interlaminar stress distribution was solved using an implicit dynamics algorithm with a time step of 5 microseconds. In conjunction with an adaptive pressure regulation algorithm, the pressure regulation range was defined as 5 to 3 MPa. A fuzzy control strategy was adopted, with the input variables being the cabin pressure deviation and the deviation change rate, and the output variable being the pressure regulating valve opening. The fuzzy rule base contained 25 rules, and the membership function adopted a triangular distribution. The domain of the pressure deviation was -2 to 2 MPa, and the domain of the deviation change rate was -1 to 1 MPa / s. A control model was established using MATLAB / Simul ink, with a sampling frequency of 100 Hz. A genetic algorithm was used to optimize fuzzy rule weights, with a population size of 100, a crossover probability of 8, and a mutation probability of 1. After 100 iterations, the optimal weight configuration was output. The optimization results were imported into COMSOL Multiphysics for multi-physics coupled simulation. Monitoring data showed that cabin deformation under pressure fluctuations decreased from 5 mm to 8 mm, and interlaminar stress distribution uniformity improved by 15%.

[0057] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any appropriate manner without contradiction. In order to avoid unnecessary repetition, the present invention will not further describe various possible combinations. In addition, the various different embodiments of the present invention can also be arbitrarily combined, as long as they do not violate the concept of the present invention, they should also be regarded as the content disclosed by the present invention.

Claims

1. A method for optimizing the airtightness of a soft pressurized cabin, characterized in that: The method comprises: Obtain the current material parameters and structural layout data of the soft pressurized cabin, simulate the high leakage rate caused by insufficient airtightness in extreme environments through finite element analysis, calculate the gas permeability and stress distribution of each part, and obtain the distribution map of key areas with high leakage rate; Based on the distribution map of key areas with high leakage rates, a multi-layer composite material superposition algorithm is used to process material parameters, determine the optimal thickness ratio and bonding strength of the elastomer and woven fiber layers, and generate an optimized material combination solution; Potential defects with low compressive strength are extracted from the optimized material combination scheme. Molecular dynamics simulation is used to analyze the changes in the intermolecular forces of the material under high pressure, and the specific locations where the structure is prone to failure are determined to obtain a failure risk assessment table. Based on the failure risk assessment table, dynamic sensor arrays are preset at specific locations of the structure prone to failure to collect stress concentration data caused by uneven pressure distribution in real time and generate a dynamic stress distribution diagram including a time series. If the stress distribution dynamic diagram shows that the local stress concentration exceeds the preset threshold, the cabin airflow distribution is adjusted through the adaptive pressure regulation algorithm, and the pressure compensation value of each area is calculated to obtain a uniform pressure distribution adjustment plan; The dynamic adjustment device is driven by a uniform pressure distribution adjustment scheme to update the pressure field data inside the cabin in real time, determine whether the material fatigue is within the rupture risk range, and generate a fatigue status monitoring report. Obtaining rupture risk indicators from fatigue condition monitoring reports, the material design optimization algorithm is used to iteratively adjust the fiber weave density and elastic modulus in key areas to determine the final structural layout parameters for improved performance. Extracting constraints that make dynamic adjustment difficult from the final structural layout parameters, simulating cabin operation in extreme environments through digital twin technology, calculating performance-limiting boundary values, and verifying performance improvements. Based on the verification results of performance improvement, combined with the multi-layer composite material superposition algorithm and the adaptive pressure regulation algorithm, a complete technical optimization plan for the soft pressurized cabin is generated, and an implementation plan including material formulation and structural adjustment is output.

2. The method according to claim 1, characterized in that The current material parameters and structural layout data of the soft pressurized cabin are obtained, and the high leakage rate caused by insufficient airtightness in extreme environments is simulated through finite element analysis. The gas permeability and stress distribution of each part are calculated to obtain the distribution map of key areas with high leakage rate, including: Obtain the material parameters and structural layout data of the soft pressurized cabin, extract the corresponding values through the preset database, and obtain the initial model parameters; Finite element analysis was used to simulate and calculate the initial model parameters, generate scenarios with insufficient airtightness under extreme environments, and obtain stress distribution and gas permeability data for each part; Sorting and analyzing the gas permeability data to determine the locations where the permeability exceeds a preset threshold, and obtaining a set of high permeability areas; Extract the stress values corresponding to the high permeability area set from the stress distribution data, determine the stress concentration area through comparative analysis, and obtain the preliminary key area; A clustering algorithm is used to group the preliminary key areas, obtain spatially adjacent areas with similar permeability, and obtain the optimized key area distribution; The optimized key area distribution is combined with the structural layout data through grid mapping technology to generate a key area distribution map; If there are isolated points in the key area distribution map, the abnormal points are eliminated through neighborhood analysis to obtain the final distribution map.

3. The method according to claim 1, characterized in that The above-mentioned distribution map of key areas with high leakage rates uses a multi-layer composite material superposition algorithm to process material parameters, determine the optimal thickness ratio and bonding strength of the elastomer and the braided fiber layer, and generate an optimized material combination solution, including: The material parameters of the key areas are processed by a multi-layer composite algorithm to determine the initial values of thickness ratio and bonding strength; Extract permeability data from key areas, use support vector machine algorithm to determine the impact of thickness ratio on permeability, and obtain classification results; The number of layers of braided fibers is adjusted based on the classification results, and an updated model of stress distribution is generated using meshing technology; Based on the stress distribution in the updated model, deformation data of the elastic body is obtained to determine the correction range of the bonding strength; If the correction range exceeds the preset threshold, the combination of thickness ratio and bonding strength is optimized by a linear regression algorithm to obtain an adjusted parameter set; Update the multi-layer composite structure using the adjusted parameter set and generate a distribution map of the optimized solution; The optimization scheme distribution map is processed by neighborhood analysis technology, isolated areas are eliminated, and the final material combination scheme is obtained.

4. The method according to claim 1, wherein The method extracts potential defects with low compressive strength from the optimized material combination scheme, analyzes the changes in the intermolecular forces of the material under high pressure through molecular dynamics simulation, determines the specific locations where the structure is prone to failure, and obtains a failure risk assessment table, including: Through molecular dynamics simulation, we can obtain the force variation data of the material combination under high pressure and determine the distribution characteristics of the defect points. Extract the fluctuation range related to compressive strength from the force change data and determine the correlation range of defect points in structural failure; The Monte Carlo algorithm is used to process the distribution characteristics within the fluctuation range to obtain the probability distribution of defect point evolution; Divide the high-risk areas of material combinations according to probability distribution and obtain the priority ranking of structural failure; If the priority ranking exceeds the preset threshold, the local accuracy of the simulation analysis is adjusted through meshing technology to determine the correction range of the force change; The parameter set of the molecular dynamics simulation is updated according to the correction range to obtain the optimized position judgment result; The location judgment results are processed through neighborhood analysis technology, low-probability areas are eliminated, and the final risk assessment data is generated.

5. The method according to claim 1, wherein According to the failure risk assessment table, a dynamic sensor array is preset at specific locations of the structure prone to failure to collect stress concentration data caused by uneven pressure distribution in real time and generate a stress distribution dynamic graph containing a time series, including: Collect pressure distribution data through dynamic sensors to obtain the change sequence of stress concentration areas; Extract time series features from the change sequence and determine the evolution law of distribution dynamics; Use preset arrays to analyze time series data to identify high-risk locations for structural failure; Adjust the acquisition density of dynamic sensors for high-risk locations to obtain updated data on local pressure distribution; The updated data is processed by support vector machine to obtain the boundary range of stress concentration; Prioritize distribution features based on boundary ranges and identify key areas for real-time analysis; Neighborhood analysis technology is used to process data in key areas and generate dynamic distribution results including evolution trends.

6. The method according to claim 1, characterized in that If the stress distribution dynamic graph shows that the local stress concentration exceeds a preset threshold, the cabin airflow distribution is adjusted using an adaptive pressure regulation algorithm, and the pressure compensation value of each area is calculated to obtain a uniform pressure distribution adjustment plan, including: If the dynamic graph detects that the local stress exceeds the preset threshold, the adaptive algorithm analyzes the changing trend of the airflow distribution and calculates the initial value of the pressure compensation; Adjust the configuration parameters of airflow distribution according to the initial values and obtain updated data on the pressure distribution in each area; Process the updated data through support vector machine to determine the boundary range of uniform distribution; Use boundary ranges to divide regional calculation priorities and obtain a sequence of key areas that can be adjusted in real time; By processing the key area sequence through neighborhood analysis technology, a dynamic adjustment plan for airflow distribution is obtained; If the pressure compensation of a certain area in the dynamic adjustment scheme exceeds the preset range, the configuration parameters of the area are recalculated to obtain the optimized uniform distribution result; The execution instructions for real-time adjustment are updated according to the optimized results to generate the final airflow distribution plan.

7. The method according to claim 1, characterized in that The uniform pressure distribution adjustment scheme drives the dynamic adjustment device to operate, updates the pressure field data inside the cabin in real time, determines whether the material fatigue is within the rupture risk range, and generates a fatigue status monitoring report, including: By adjusting the scheme to drive the device to operate, obtain real-time updated data of the pressure field and confirm the integrity of data collection; Based on real-time updated data, the random forest algorithm is used to process the changing trend of the pressure field and determine the distribution characteristics of material fatigue; If the distribution characteristics of material fatigue exceed the rupture risk range, corresponding control instructions are generated through dynamic adjustment to obtain adjustment parameters for device operation; Update the device operating status based on the adjustment parameters, obtain a new round of pressure field data, and determine the degree of fatigue relief; By processing the relief degree data through neighborhood analysis technology, the optimization direction of pressure distribution is obtained; Adjust the execution order of dynamic adjustment according to the optimization direction, obtain real-time feedback data of device operation, and determine whether material fatigue is stabilizing; If the material fatigue tends to be stable, the monitoring results are updated through data acquisition to determine the degree of homogenization of the pressure field.

8. The method according to claim 1, characterized in that The method of obtaining the rupture risk index from the fatigue condition monitoring report and iteratively adjusting the fiber braiding density and elastic modulus in key areas using a material design optimization algorithm to determine the final structural layout parameters for improving performance includes: Obtain rupture risk data from monitoring reports, process rupture risk indicators using data cleaning technology, and obtain standardized risk distribution characteristics; Based on the standardized risk distribution characteristics, cluster analysis method is used to divide key areas and determine the fatigue status differences in each area; Based on the difference in fatigue state, the initial values of fiber weaving density and elastic modulus are extracted from the preset material database to obtain a preliminary material design scheme; Processing preliminary material design solutions through optimization algorithms, iteratively adjusting fiber weave density and elastic modulus to determine optimized parameters in key areas; If the optimization parameter exceeds the preset threshold, the structural layout is adjusted through parameter smoothing technology to obtain smoothed layout data; Based on the smoothed layout data, real-time fatigue status data is obtained to determine the performance stability of key areas; The performance stability data is processed through neighborhood analysis technology to determine the final structural layout parameters.

9. The method according to claim 1, characterized in that The method extracts the constraints that make dynamic adjustment difficult from the final structural layout parameters, simulates the cabin's operating state in extreme environments through digital twin technology, calculates the performance-limited boundary values, and obtains verification results of performance improvement, including: Process the final structural layout parameters through parameter extraction technology to obtain dynamically adjusted constraint condition data; Based on the constraint data, digital twin technology is used to simulate the cabin's operating status under extreme environments and obtain the operating status distribution; Through the distribution of operating states, the performance limitation range of the cabin under extreme conditions is calculated and the boundary value set is determined; For the boundary value set, obtain verification data associated with the operating state and determine the distribution characteristics of performance limitations; If the distribution characteristics exceed the preset threshold, the boundary value set is adjusted through smoothing technology to obtain the adjusted verification data; Based on the adjusted validation data, the K-means clustering algorithm is used to divide the performance-limited area range and determine the optimized operating status parameters; The optimized operating status parameters are processed through neighborhood analysis technology to obtain a dynamic adjustment plan that matches the structural layout.

10. The method according to claim 1, characterized in that Based on the performance improvement verification results, combined with the multi-layer composite material stacking algorithm and the adaptive pressure regulation algorithm, a complete technical optimization plan for the soft pressurized cabin is generated. The output includes an implementation plan that includes material formulation and structural adjustment, including: The performance distribution characteristics are obtained by verifying the data, and the composite material data is processed using a multi-layer composite material superposition algorithm to obtain the material formulation parameters; Based on the material formula parameters, determine the formula adjustment range and obtain the adjustment data associated with the pressure distribution; The pressure distribution data is processed by an adaptive pressure regulation algorithm to obtain a set of parameters for structural adjustment; Using data processing technology to analyze the parameter set, determine whether the performance distribution meets the preset threshold. If it exceeds the threshold, the parameter set is adjusted through smoothing technology to obtain updated structural adjustment data; Based on the updated structural adjustment data, obtain the formula adjustment plan that matches the composite material and determine the optimized material formula; The optimized material formula is processed by neighborhood analysis technology to obtain a structural adjustment plan consistent with pressure regulation; Based on the structural adjustment plan, data processing technology is used to generate a complete optimization plan output.

Images