Blended fiber weaving system for phase change temperature control fibers
By constructing a fiber compatibility evaluation model and various optimization algorithms, the problem of lack of prediction and optimization in the hybrid fiber weaving process was solved, achieving efficient and stable fiber mixing and weaving structure optimization, and improving the consistency of fabric performance and environmental adaptability.
Patent Information
- Application Number
- CN202511747367.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-26
- Publication Date
- 2026-02-17
AI Technical Summary
The existing hybrid fiber weaving process lacks systematic early prediction and optimization methods, resulting in long process development cycles, high costs, difficulty in ensuring the stability and consistency of finished product performance, and insufficient consideration of the impact of production environment fluctuations.
By constructing a fiber compatibility assessment model, finite element simulation, genetic algorithm, neural network and particle swarm optimization algorithm, combined with mechanical performance testing and environmental factor simulation, the fiber mixing ratio and weaving structure parameters are optimized to achieve accurate prediction and stability control.
It significantly reduces the cost of experimental trial and error, ensures the uniformity and interfacial stability of mixed fiber weaving, and improves the functional stability of fabrics in actual production and use environments.
Smart Images
Figure CN121543347A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the field of fiber weaving, more particularly to a mixed fiber weaving system for phase change temperature control fibers. BACKGROUND
[0002] The rapid development of intelligent textiles puts forward higher requirements for fabric functions, and phase change temperature control fibers have attracted widespread attention due to their unique temperature regulation capabilities. In practical applications, phase change fibers are often mixed with other fibers to improve the overall performance of the fabric. Currently, the development of mixed fiber weaving processes mainly relies on experimental experience, and the fiber combination and weaving parameters are selected through trial and error method. The existing technical solutions mainly focus on performance testing of fiber materials or post-evaluation of finished fabrics, and lack systematic pre-prediction and optimization means.
[0003] In the existing research methods, the determination of the fiber mixing ratio is often based on simple mechanical performance tests or empirical formulas, without fully considering the complex interactions of various physical properties between fibers. The selection of weaving structures is also limited to the direct application of traditional patterns, lacking structure adaptability analysis for specific mixed materials. In addition, the influence of production environment fluctuations on process stability is often simplified as fixed parameters for processing, which is difficult to reflect the dynamic changes of actual production conditions. These factors result in long process development cycle, high cost, and difficulty in ensuring the stability and consistency of the performance of finished products. SUMMARY
[0004] The purpose of the present application is to provide a mixed fiber weaving system for phase change temperature control fibers to overcome the shortcomings of relying on experience and trial and error in the development of existing mixed fiber weaving processes, and lack of coordinated optimization and accurate prediction of fiber compatibility, mixing ratio, weaving structure and environmental factors.
[0005] The present application achieves the above-mentioned purposes through the following technical solutions: The present application proposes a mixed fiber weaving system for phase change temperature control fibers, which comprises: A first acquisition module for acquiring a physical property data set of target mixed fibers with phase change temperature control fibers, and performing compatibility analysis on the physical property data set; A first determination module for determining the fiber mixing ratio based on the compatibility analysis data; A second acquisition module for performing mechanical performance tests on a mixed fiber pattern configured based on the fiber mixing ratio to obtain performance test data; A second determination module for determining the preliminary weaving structure parameters based on the mechanical performance test data by establishing a mapping relationship between the weaving structure parameters and the mechanical performance and simulating and screening; The weaving optimization module is configured to optimize the preliminary screening weaving structure parameters based on simulation results of influences of environmental temperature and humidity data on phase change performance, and output final weaving structure parameters to a weaving equipment control system.
[0006] Further, the physical property data set includes fiber diameter, fiber length, fiber surface roughness, and phase change temperature range data of the phase change temperature control fiber.
[0007] Further, the compatibility analysis on the physical property data set includes the following steps: A fiber compatibility evaluation model is constructed, and input parameters of the model are obtained from the physical property data set, and at least include fiber diameter difference, fiber length matching degree, fiber surface roughness fitting degree, and phase change temperature range overlap degree between phase change temperature control fibers. A fuzzy comprehensive evaluation method is used to assign corresponding weight coefficients to each input parameter. Each input parameter after standardization is substituted into the evaluation model for fuzzy operation to obtain a membership degree representing the compatibility degree between any two fibers. According to the maximum membership degree principle, the compatibility grade between fibers is determined, and fiber compatibility data for guiding the optimization of mixing ratio are generated.
[0008] Further, the first determination module includes: A finite element simulation unit is configured to receive the fiber compatibility data, perform finite element analysis on a mixing ratio combination of n fibers , ,… , wherein , and calculate performance prediction values P under each ratio. An optimization calculation unit is configured to introduce physical constraint conditions in the optimization process , and the constraint conditions at least include a mixing uniformity constraint caused by fiber diameter difference and a fiber friction constraint affected by surface roughness ; and a genetic algorithm is used to perform iterative optimization with a fitness function , as follows ; wherein , is a weight, is the number of constraint conditions; when the fitness function F converges to a maximum value, the corresponding fiber mixing ratio combination is output as an optimization result.
[0009] Further, the performance test data is obtained by the following steps: According to the fiber mixing ratio, a sample of mixed fibers is configured; The sample is subjected to tensile testing and bending testing respectively to obtain tensile strength and bending modulus; The mechanical testing is repeated multiple times, and the tensile strength and bending modulus obtained in each test are respectively taken as arithmetic mean values as the mechanical property test data.
[0010] Further, the second determination module comprises: A regression modeling unit is configured to establish a regression model of the woven structure parameters and the mechanical property indexes according to the mechanical property test data; the regression model takes yarn density and interlacing angle as independent variables, and takes tensile strength and bending modulus as dependent variables, and the relationship is expressed as: ; ; Wherein, , , , , , , , are regression coefficients; A parameter screening unit is configured to use a multiple linear regression method to fit the regression coefficients by a least square method, and based on the fitted model, to simulate the performance of the woven structure under different combinations of yarn density and interlacing angle , and to screen out a combination of parameters meeting the preset mechanical property requirements as the preliminary screened woven structure parameters.
[0011] Further, in the weaving optimization module, the influence of environmental temperature and humidity data on the phase change performance is simulated, including the following steps: Obtain temperature data and humidity data of the weaving environment; Establish a neural network model taking the temperature and humidity as input and the phase change temperature and phase change enthalpy of the phase change temperature control fiber as output, and train the model; Input the real-time obtained temperature and humidity data of the weaving environment into the trained neural network model to simulate the phase change performance change data; Analyze the fluctuation law of the phase change performance under different environmental conditions to generate environmental correlation phase change performance influence data.
[0012] Further, the neural network model is a multi-layer perceptron comprising an input layer, at least one hidden layer and an output layer; wherein the number of input layer neurons is 2, corresponding to the ambient temperature and humidity respectively, and the number of output layer neurons is 2, corresponding to the phase transition temperature and the phase transition enthalpy respectively.
[0013] Further, the optimization of the preliminary screening of the weaving structure parameters comprises the following steps: Based on the environmental correlation phase change performance influence data, a weaving structure parameter correction model is constructed; Using a particle swarm optimization algorithm, the preliminary screening of the weaving structure parameters is used as the position information of the initial particle swarm; The performance stability index of the mixed fiber woven product in the simulated environment is used as the fitness function, the weaving structure parameters are iteratively adjusted in the simulated weaving environment, and the fitness value is calculated; When the fitness value meets the preset convergence condition, the current optimal weaving structure parameter combination is output as the final weaving structure parameter.
[0014] Further, the performance stability index Defined by the standard deviation of the mechanical property test data, the calculation formula is: ; Wherein, is the number of tests, is the mechanical property value of a single test, is the average value of the mechanical property of the test.
[0015] The beneficial effects of the present application are: 1、The present application firstly establishes a fiber compatibility fuzzy evaluation model integrating multiple physical properties, providing a basis for fiber mixing, ensuring uniformity and interface stability. Secondly, combining finite element simulation and intelligent algorithm for mixed proportion optimization, it can accurately predict the performance of different formulations in a virtual environment, significantly reducing experimental trial and error costs. Thirdly, by establishing a quantitative regression model of weaving structure parameters and mechanical properties, the matching and rapid screening of weaving structure and material properties are realized.
[0016] 2、The present application introduces an environmental factor dynamic prediction mechanism, which uses a neural network to simulate the influence of temperature and humidity changes on phase change performance, and uses a particle swarm optimization algorithm to optimize the process parameters in real time, ensuring the high stability of the fabric in the actual production and use environment. BRIEF DESCRIPTION OF DRAWINGS
[0017] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the present application and together with the description serve to explain the present application. In the drawings: Figure 1 A system block diagram of a system for weaving a mixed fiber system with phase change temperature control fiber in the present application; Figure 2 A flowchart of a first determination module processing compatibility data in the present application; Figure 3 A flowchart of a weaving optimization module processing combined environmental data and preliminary parameters in the present application. DETAILED DESCRIPTION
[0018] The technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.
[0019] Embodiment 1 Please refer to Figure 1 In one embodiment of the present application, a mixed fiber weaving system with phase change temperature control fiber is provided, which includes a first acquisition module, a first determination module, a second acquisition module, a second determination module, and a weaving optimization module. Each of the above modules participates in the processing flow from fiber characteristic analysis to final weaving parameter output.
[0020] The first acquisition module is responsible for acquiring the physical characteristic data set of the target mixed fiber. The data set specifically includes basic physical parameters such as fiber diameter, fiber length, and fiber surface roughness, as well as phase change temperature range data specific to phase change temperature control fiber.
[0021] The core function of the first acquisition module is to perform compatibility analysis on the data set. The specific implementation process is as follows: first, a fiber compatibility evaluation model is constructed, and the input parameters of the model are obtained from the physical property data set, mainly including fiber diameter difference, fiber length matching degree, fiber surface roughness matching degree, and phase change temperature range overlap degree between different phase change temperature control fibers. Next, the fuzzy comprehensive evaluation method is used to assign corresponding weight coefficients to the above input parameters to reflect the importance of different parameters on compatibility. Then, the standardized input parameters are substituted into the evaluation model for fuzzy operation, and finally a membership degree representing the compatibility degree between any two fibers is output. According to the maximum membership degree principle, the compatibility grade between fibers can be determined, and structured fiber compatibility data can be generated, providing a direct basis for subsequent mixed ratio optimization.
[0022] The first determination module receives the inter-fiber compatibility data from the previous module and performs mixed simulation calculation based on it, and the core output is the optimized fiber mixing ratio. Through simulation analysis, this module determines the mixing scheme that can maximize the synergistic effect between fibers.
[0023] The second acquisition module actually configures a mixed fiber sample according to the fiber mixing ratio output by the first determination module, and performs standard mechanical property tests such as tensile test and bending test to obtain reliable tensile strength, bending modulus and other performance test data.
[0024] The function of the second determination module is to establish a quantitative mapping relationship between the weaving structure parameters (such as yarn density and interlacing angle) and the mechanical performance indicators using the mechanical performance test data provided by the second acquisition module. Through this mapping relationship, a set of preliminary weaving structure parameters that can meet the basic mechanical performance requirements is determined from numerous parameter combinations.
[0025] The weaving optimization module is responsible for environmental adaptability optimization of the preliminary selected weaving structure parameters. This module will introduce real-time or simulated temperature and humidity data of the weaving environment to evaluate its impact on the performance of phase change temperature control fibers, and based on this impact, the preliminary parameters will be corrected and optimized. Finally, the optimized final weaving structure parameters with environmental adaptability are output to the control system of the weaving equipment to directly guide production.
[0026] Furthermore, a compatibility analysis is performed on the physical property dataset, including the following steps: A fiber compatibility evaluation model is constructed. The input parameters of the model are obtained by parsing the physical property dataset, including at least fiber diameter differences, fiber length matching, fiber surface roughness compatibility, and overlap of phase change temperature ranges between phase change temperature-controlled fibers; A fuzzy comprehensive evaluation method is used to assign corresponding weight coefficients to each input parameter; The standardized input parameters are substituted into the evaluation model for fuzzy computation to obtain the membership degree characterizing the compatibility between any two fibers; Based on the maximum membership degree principle, the compatibility level between fibers is determined, and fiber compatibility data is generated to guide the optimization of the mixing ratio.
[0027] Please see Figure 2 Furthermore, the first determination module is used to perform mixing simulations based on fiber compatibility data to determine the optimal fiber mixing ratio. This module specifically includes two core parts: a finite element simulation unit and an optimization calculation unit.
[0028] The finite element simulation unit is used to receive fiber compatibility data. This unit models and analyzes a hybrid system composed of n fiber materials, where the proportion of each fiber in the hybrid system is expressed as... , ,… ,in, By establishing a finite element model of the fiber hybrid system, this unit can simulate and calculate the performance prediction value P under different mixing ratio combinations. This prediction value comprehensively reflects the mechanical and thermal properties of the hybrid fibers.
[0029] The optimized computational unit introduces key physical constraints based on finite element simulation. These constraints are expressed as mathematical inequalities. The form is represented as , where j is the constraint number; the constraint includes at least the mixing uniformity constraint caused by the difference in fiber diameter. This constraint ensures that fibers of different diameters can be uniformly distributed, and includes constraints on inter-fiber friction caused by surface roughness. This constraint ensures appropriate bonding strength between fibers; and a genetic algorithm is used with a fitness function. Perform iterative optimization, as shown in the following formula. ; in, These are the weighting coefficients for the performance prediction values. These are the weighting coefficients for each constraint. The number of constraints; the weighting coefficients of the performance prediction values. and the weighting coefficients of each constraint condition The settings are determined based on historical data calibration. During the optimization process, the genetic algorithm continuously updates the mixing ratio combination through operations such as selection, crossover, and mutation. When the fitness function F converges to its maximum value, the corresponding fiber mixing ratio combination is the optimal solution, which serves as the final output of the module.
[0030] In this embodiment, the second acquisition module acquires performance test data, including the following steps: Based on the fiber mixing ratio, prepare a sample of mixed fibers; perform tensile and bending tests on the sample to obtain tensile strength and bending modulus; repeat the mechanical test multiple times, and take the arithmetic mean of the tensile strength and bending modulus obtained from each test as the mechanical property test data.
[0031] The mechanical tests include tensile and bending tests. Tensile testing uses a universal testing machine, and the specimen is axially stretched according to standard tensile testing methods (such as GB / T 1040.3) until it fractures. Load and displacement data are continuously recorded during the test, and the tensile strength of the specimen can be calculated. Bending testing uses a standard bending testing device (such as a three-point bending fixture), and the bending performance of the specimen is tested according to relevant testing standards (such as GB / T 9341). The flexural modulus of the specimen is calculated by recording the load-deflection curve; this index is used to evaluate the material's stiffness against bending deformation.
[0032] In this embodiment, the second determining module is used to establish a quantitative relationship between the braiding structure parameters and the mechanical properties based on the mechanical property test data, and to screen out preliminary braiding structure parameters. This module specifically includes a regression modeling unit and a parameter screening unit.
[0033] The core task of the regression modeling unit is to establish a mathematical relationship model between weaving structure parameters and mechanical performance indicators. This unit uses mechanical performance test data (i.e., tensile strength) provided by the second acquisition module. and flexural modulus The measured average value was used as the basis for modeling. The constructed regression model explicitly uses two key weaving structure parameters as independent variables: yarn density. and interlacing angle The model will consider tensile strength. and flexural modulus These are expressed as linear functions of the two independent variables, respectively, and the interaction between them is considered. The specific form of the model is: ; ; in, , , , , , , , These are the regression coefficients that need to be determined by fitting experimental data.
[0034] The parameter selection unit utilizes the established regression model for parameter optimization and selection. This unit first employs the multiple linear regression method, based on the aforementioned model, and then uses the least squares method to optimize the parameters obtained from historical or experimental data. , , , The dataset is fitted to calculate the specific values of all regression coefficients, thus completing the model calibration.
[0035] Subsequently, based on this well-fitted model that reflects the quantitative relationship between structural parameters and performance, the unit operates at a set yarn density. and interlacing angle Within the feasible range, systematically simulate a large number of different parameter combinations ( , For each simulated parameter combination, a regression model is used to predict its corresponding tensile strength and flexural modulus. Finally, those parameter combinations that simultaneously meet the preset performance requirements (judged by a threshold) are selected as preliminary screening parameters for the braided structure and output to the subsequent braiding optimization module.
[0036] Please see Figure 3 In this embodiment, the core function of the weaving optimization module is to simulate the impact of ambient temperature and humidity data on the properties of phase change temperature-controlled fibers. The specific implementation process is as follows: This module first acquires real-time temperature and relative humidity data of the weaving environment through a network of environmental sensors deployed around the weaving equipment. This data serves as the basic input for simulation analysis.
[0037] Subsequently, the module establishes a multilayer perceptron neural network model to characterize the complex nonlinear relationship between environmental conditions and phase change performance. This network structure includes an input layer, at least one hidden layer, and an output layer. The input layer has two fixed neurons, used to receive normalized environmental temperature and humidity values, respectively. The output layer also has two fixed neurons, corresponding to the two key performance outputs of the phase change temperature-controlled fiber: phase change temperature and phase change enthalpy. The number of hidden layers and the number of neurons in each layer can be configured based on the amount of historical data and the complexity of the relationship; for example, a single hidden layer with 8-16 neurons can be used to balance model fitting ability and computational efficiency.
[0038] The training of this neural network model relies on a pre-built historical dataset. This dataset contains a large number of phase transition temperatures and enthalpies of phase transition temperature-controlled fibers, actually measured by experimental equipment under different combinations of temperature and humidity. During training, the backpropagation algorithm is used to optimize the weights and bias parameters within the network to minimize the error (such as mean square error) between the model's predicted values and the actual experimental values.
[0039] Once the model is trained, it is immediately put into application. The system inputs real-time collected environmental temperature and humidity data into the trained neural network model. The model calculates through forward propagation and outputs the predicted phase change temperature and phase change enthalpy of the phase change temperature-controlled fiber under the current environmental conditions. These data are collectively referred to as "phase change performance change data".
[0040] Finally, by analyzing the phase change performance data obtained under different temperature and humidity inputs, the module identifies the patterns of how environmental fluctuations (such as increased temperature and humidity) lead to changes in phase change performance (such as phase change temperature shifts and phase change enthalpy changes), and generates structured "environment-related phase change performance impact data." This data quantitatively describes the degree of influence of environmental factors on the thermal functional properties of materials.
[0041] In this embodiment, the weaving optimization module performs environmental adaptability optimization on the initially screened weaving structure parameters. The specific implementation process is as follows: This module first constructs a weaving structure parameter correction model based on the "environment-related phase change performance impact data" generated in the preceding steps. This model is essentially a response function, whose inputs are environmental temperature and humidity data and the weaving structure parameters to be optimized (mainly yarn density). and interlacing angle The output is the predicted product performance value. This model is constructed by integrating phase change performance change data with existing mechanical property regression models, thereby reflecting how environmental fluctuations affect the performance of the final product by influencing phase change behavior.
[0042] Secondly, the module employs a particle swarm optimization algorithm for parameter optimization. During algorithm initialization, the preliminary screening of the weaving structure parameters output by the second determining module (i.e., one or more sets of parameters that meet the basic mechanical requirements) is used. and The value is set as the initial position of each particle in the particle swarm. The position of each particle represents an alternative combination of weaving structure parameters.
[0043] The goal of the optimization process is to improve the performance stability of the product under varying environments. To this end, the algorithm uses a fitness function as the evaluation criterion. This fitness function is specifically defined as the performance stability index S of the blended fiber woven product under simulated environments. This index is calculated by simulating the mechanical properties of the product under N different environmental conditions (set according to the expected range of environmental fluctuations). For each simulation, a mechanical property value is predicted using the aforementioned modified model. (e.g., tensile strength or flexural modulus), then calculate the standard deviation S of these N predicted values: ; in, For the number of tests, These are the mechanical property values from a single test. for The average mechanical properties from all tests. The fitness value is taken as the negative of the stability index S (i.e., -S), because the optimization objective is to minimize the standard deviation S, thereby maximizing performance stability.
[0044] During the iterative optimization process, the particle swarm continuously updates its velocity and position (i.e., adjusts the weaving structure parameters) based on the individual's historical best position and the swarm's historical best position. After each update, the fitness value is recalculated based on the new parameter combination and simulated environmental fluctuations. When the change in fitness value is less than a preset threshold or the maximum number of iterations is reached, the algorithm terminates and outputs the optimal position found in the current swarm, which is the final weaving structure parameter combination that ensures the most stable performance of the product under the expected environmental fluctuations, and sends it to the weaving equipment control system.
[0045] Based on the above embodiments, the working principle of the present invention is as follows: The system first acquires physical property data of the fibers through a first acquisition module and uses fuzzy comprehensive evaluation to analyze the compatibility between fibers, generating compatibility level data. Based on this data, a first determination module uses finite element simulation combined with a genetic algorithm to optimize and calculate the fiber mixing ratio, considering physical constraints such as mixing uniformity and inter-fiber friction. A second acquisition module prepares samples according to this ratio and obtains the average values of tensile strength and flexural modulus through standardized mechanical testing. The second determination module uses this data to establish a regression model of yarn density, interlacing angle, and mechanical properties, and uses simulation to screen preliminary weaving structure parameters. Finally, a weaving optimization module incorporates environmental temperature and humidity data, predicts phase change performance changes through a neural network, and uses a particle swarm optimization algorithm with performance stability as the optimization objective to optimize the preliminary parameters for environmental adaptability, outputting the final weaving structure parameters to the control system.
[0046] Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0047] The above embodiments provide a detailed description of the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.
Claims
1. A hybrid fiber weaving system for phase change temperature-controlled fibers, characterized in that, The system includes: The first acquisition module is used to acquire a dataset of physical properties of the target hybrid fiber with phase change temperature control fiber, and to perform compatibility analysis on the physical property dataset. The first determining module is used to perform mixing simulation based on compatibility analysis data in order to determine the fiber mixing ratio; The second acquisition module is used to perform mechanical property tests on the mixed fiber pattern configured based on the fiber mixing ratio to obtain performance test data; The second determining module is used to determine the preliminary weaving structure parameters by establishing a mapping relationship between the weaving structure parameters and the mechanical properties and by simulating screening based on the mechanical performance test data. The weaving optimization module is used to optimize the preliminary selected weaving structure parameters based on the simulation results of the influence of environmental temperature and humidity data on phase change performance, and output the final weaving structure parameters to the weaving equipment control system.
2. The hybrid fiber weaving system for phase change temperature-controlled fibers according to claim 1, characterized in that, The physical property dataset includes data on fiber diameter, fiber length, fiber surface roughness, and the phase change temperature range of the phase change temperature-controlled fiber.
3. A hybrid fiber weaving system for phase change temperature-controlled fibers according to claim 2, characterized in that, The compatibility analysis of the physical property dataset includes the following steps: A fiber compatibility evaluation model is constructed. The input parameters of the model are obtained by parsing the physical property dataset and include at least fiber diameter difference, fiber length matching degree, fiber surface roughness compatibility degree, and overlap of phase change temperature range between phase change temperature-controlled fibers. The fuzzy comprehensive evaluation method is used to assign corresponding weight coefficients to each of the input parameters. Substitute the standardized input parameters into the evaluation model for fuzzy computation to obtain the membership degree characterizing the compatibility between any two fibers; Based on the principle of maximum membership, the compatibility level between fibers is determined, and fiber compatibility data is generated to guide the optimization of the mixing ratio.
4. A hybrid fiber weaving system for phase change temperature-controlled fibers according to claim 3, characterized in that, The first determining module includes: The finite element simulation unit is used to receive the inter-fiber compatibility data and to simulate the mixing ratios of n types of fibers. , ,… ,in, Finite element analysis was performed to calculate the predicted performance value P at each scale. Optimization computational units are used to introduce physical constraints during the optimization process. The constraints include at least a mixing uniformity constraint caused by differences in fiber diameter. and interfiber frictional constraints influenced by surface roughness And a genetic algorithm is used, with a fitness function Perform iterative optimization, as shown in the following formula. ； in, , As weight, The number of constraints is denoted by ; when the fitness function F converges to its maximum value, the corresponding fiber mixing ratio combination is output as the optimization result.
5. A hybrid fiber weaving system for phase change temperature-controlled fibers according to claim 1, characterized in that, The process of obtaining performance test data includes the following steps: Prepare a sample of the mixed fibers according to the fiber mixing ratio; The specimens were subjected to tensile and bending tests to obtain tensile strength and flexural modulus. Repeat the mechanical test multiple times, and take the arithmetic mean of the tensile strength and flexural modulus obtained from each test as the mechanical property test data.
6. A hybrid fiber weaving system for phase change temperature-controlled fibers according to claim 5, characterized in that, The second determining module includes: The regression modeling unit is used to establish a regression model between the weaving structure parameters and mechanical performance indicators based on the mechanical performance test data; the regression model uses yarn density as a reference. and interlacing angle As the independent variable, tensile strength and flexural modulus As the dependent variable, their relationship can be expressed as: ； ； in, , , , , , , , These are the regression coefficients; The parameter selection unit is used to fit the regression coefficients using the least squares method through multiple linear regression, and based on the fitted model, simulate different yarn densities. and interlacing angle The performance of the braided structure under the parameter combination is selected, and the parameter combination that meets the preset mechanical performance requirements is selected as the preliminary braided structure parameter.
7. A hybrid fiber weaving system for phase change temperature-controlled fibers according to claim 1, characterized in that, The weaving optimization module simulates the impact of environmental temperature and humidity data on phase change performance, including the following steps: Acquire temperature and humidity data of the weaving environment; A neural network model is established with the temperature and humidity as inputs and the phase transition temperature and phase transition enthalpy of the phase transition temperature-controlled fiber as outputs, and the model is trained. The real-time acquired temperature and humidity data of the weaving environment are input into the trained neural network model to simulate the phase change performance data. Analyze the fluctuation patterns of phase change performance under different environmental conditions and generate environmentally related phase change performance impact data.
8. A hybrid fiber weaving system for phase change temperature-controlled fibers according to claim 7, characterized in that, The neural network model is a multilayer perceptron comprising an input layer, at least one hidden layer, and an output layer; wherein the number of neurons in the input layer is 2, corresponding to the ambient temperature and humidity respectively, and the number of neurons in the output layer is 2, corresponding to the phase transition temperature and the phase transition enthalpy respectively.
9. A hybrid fiber weaving system for phase change temperature-controlled fibers according to claim 8, characterized in that, The optimization of the preliminary selected weave structure parameters includes the following steps: Based on the environmental-related phase change performance impact data, a correction model for braided structure parameters is constructed. The particle swarm optimization algorithm is used to select the weaving structure parameters as the position information of the initial particle swarm. Using the performance stability index of hybrid fiber woven products in a simulated environment as the fitness function, the woven structure parameters are iteratively adjusted and the fitness value is calculated in the simulated woven environment. When the fitness value meets the preset convergence condition, the current optimal combination of braiding structure parameters is output as the final braiding structure parameters.
10. A hybrid fiber weaving system for phase change temperature-controlled fibers according to claim 9, characterized in that, The performance stability index Defined by the standard deviation of mechanical property test data, the calculation formula is as follows: ； in, For the number of tests, These are the mechanical property values from a single test. for The average mechanical properties of each test.