Thermal forming system suitable for high-enthalpy temperature control fibers

Abstract

The invention discloses a thermal forming system suitable for high-enthalpy temperature control fibers, and the system comprises the following units: a gradient analysis unit, which collects initial temperature field data of a raw material before thermal forming by setting a temperature sensor array, and carries out temperature gradient analysis to obtain temperature gradient distribution data; and the heat conduction characteristic evaluation unit is used for evaluating the heat conduction characteristics of different areas of the fiber raw material according to the distribution data to obtain evaluation data of the heat conduction characteristics. According to the thermal forming system suitable for the high-enthalpy-value temperature control fibers, the technical means of providing accurate temperature control, heat conduction characteristic evaluation, thermal response simulation, dynamic correction and the like are achieved, an optimization algorithm is adopted to construct a thermal forming process optimization model, process parameters are dynamically adjusted according to real-time data, optimization of the thermal forming process is achieved, and the thermal forming efficiency is improved. The forming quality and the production efficiency of the high-enthalpy temperature control fiber are effectively improved, the rejection rate is reduced, and the production cost is reduced.

Description

Technical Field

[0001] This invention relates to the field of fiber thermoforming, and more specifically to a thermoforming system suitable for high enthalpy temperature-controlled fibers. Background Technology

[0002] In the thermoforming process of high-enthalpy temperature-controlled fibers, the temperature distribution, thermal conductivity, and thermal expansion behavior of the fiber raw material have a crucial impact on the final molding quality. Traditional thermoforming systems often lack precise sensing of the initial temperature field of the fiber raw material, making it difficult to accurately assess the thermal conductivity characteristics of different regions. This makes it impossible to effectively predict the thermal response and thermal expansion differences in different regions of the fiber during thermoforming, potentially leading to problems such as interference or excessive gaps between the mold and the fiber, affecting molding accuracy and product quality.

[0003] Meanwhile, traditional systems do not fully consider the impact of real-time heating power on local thermal response in the thermoforming system, and cannot dynamically correct thermal expansion prediction data in a timely manner. In terms of thermoforming process optimization, there is a lack of optimization models based on real-time data and advanced algorithms, making it difficult to quickly adjust process parameters according to actual conditions, and failing to meet the high precision and high quality requirements of high-enthalpy temperature-controlled fiber thermoforming. Therefore, developing a system capable of comprehensively and accurately controlling the thermoforming process is of significant practical importance. Summary of the Invention

[0004] The purpose of this invention is to provide precise temperature control, thermal conductivity assessment, simulated thermal response, and dynamic correction techniques to optimize the thermoforming process of high enthalpy temperature-controlled fibers, thereby improving forming quality and production efficiency. It solves the problem that existing thermoforming process optimization lacks optimization models based on real-time data and advanced algorithms, making it difficult to quickly adjust process parameters according to actual conditions and failing to meet the high precision and high quality requirements of high enthalpy temperature-controlled fiber thermoforming.

[0005] The present invention achieves the above objectives through the following technical solutions: A thermoforming system suitable for high enthalpy temperature-controlled fibers, the system comprising the following units: The gradient analysis unit is used to collect the initial temperature field data of the fiber raw material before thermoforming and perform temperature gradient analysis to obtain temperature gradient distribution data. The thermal conductivity assessment unit is used to assess the thermal conductivity characteristics of different regions of the fiber raw material using the temperature gradient distribution data and the constructed local thermal conductivity tendency prediction model to obtain thermal conductivity assessment data; wherein, the local thermal conductivity tendency prediction model is constructed based on simulating local heat flow paths under different microstructures and a CNN network. The thermal expansion prediction unit is used to obtain local thermal response simulation data of the fiber raw material using a pre-constructed thermo-coupling dynamic digital twin model of the fiber raw material and the thermal conduction characteristic evaluation data, and to obtain the prediction results of thermal expansion differences in various regions of the fiber raw material based on a multi-dimensional feature fusion prediction framework and the local thermal response simulation data. The dynamic correction unit is used to combine the real-time heating power data and local thermal response simulation data of the thermoforming system to identify the heat input influencing factors, obtain the power-related heat input influencing factors, and perform dynamic correction of the thermal expansion difference prediction results. The thermoforming optimization unit is used to optimize the dynamic correction data of thermal expansion using an optimization algorithm and send the optimization results to the thermoforming control system.

[0006] Furthermore, the thermal conductivity assessment includes the following steps: S21. Construct a virtual fiber model based on the microstructure characteristics of the fiber raw material, and map the temperature gradient distribution data to the virtual fiber model to obtain local heat flow path simulation data. S22. Input the simulated local heat flow path data into the CNN network for training, and classify the heat conduction tendency of each region of the fiber based on the trained model; combine the classification results with the pre-set heat conduction characteristic reference table to determine the heat conduction characteristic level of each region and obtain evaluation data with heat conduction characteristics.

[0007] Furthermore, obtaining the local thermal response simulation data of the fiber raw material includes the following steps: S31. Construct a dynamic digital twin model of the thermal coupling of fiber raw materials, and embed the thermal conductivity evaluation data into each local region of the model; S32. Simulate the heating state of the thermoforming system and dynamically generate a local heat flow distribution map in the dynamic digital twin model based on the heat conduction characteristics of the fiber raw material; S33. Introduce an intelligent fiber raw material behavior prediction module, and combine historical thermoforming data with the current heat flow spectrum to predict the microstructure change trend of local fiber due to heat, and adjust the local fiber raw material thermal expansion coefficient and elastic modulus in real time in the model. S34. Through iterative calculation using a digital twin model, obtain simulated data of the local thermal response in various local areas of the fiber raw material at different times.

[0008] Furthermore, the prediction of thermal expansion differences includes the following steps: S41. Build a multi-dimensional feature fusion prediction framework based on deep learning, and use local thermal response simulation data as input features; S42. Introduce a virtual thermal expansion calibration experiment module to simulate extreme thermal expansion scenarios under different feature combinations within the prediction framework and generate a virtual calibration dataset. S43. Use a virtual calibration dataset to enhance the training of the prediction framework; S44. Input the actual simulation data into the trained prediction framework to classify and predict the thermal expansion behavior of each region, and generate differential prediction data.

[0009] Furthermore, based on the predicted difference data, a preliminary assessment of the mold compatibility in the initial stage of thermoforming is performed to obtain preliminary mold compatibility assessment data, including the following steps: S51. Construct a virtual simulation scenario of thermal expansion interaction between the mold and fiber, and map the predicted data of thermal expansion difference to the contact interface between the virtual mold and the fiber raw material. S52. Introduce an intelligent conflict detection algorithm to identify potential interference areas and areas with excessive gaps between the mold and fiber due to differences in thermal expansion in a virtual simulation scenario. S53. Establish a mold adaptability evaluation index system and use machine learning models to quantitatively score key indicators of potential problem areas. S54. Based on the comprehensive scoring results of each region and the preset compatibility level classification standards, generate preliminary assessment data for mold compatibility.

[0010] Furthermore, the identification of heat input influencing factors includes the following steps: S61. Collect temperature data from various parts of the thermoforming system, and use an intelligent data fusion algorithm to characterize the temperature data to obtain a real-time heating power characterization dataset. S62. Input the real-time heating power characterization data and the local thermal response simulation data into the thermal response digital mapping model; S63. Introduce a dynamic weight allocation mechanism to assign weights to the heating power characterization data according to different heating stages and regional characteristics; S64. Through model iterative calculation and dynamic weight adjustment, key power parameters that significantly affect local thermal response simulation data are identified, and power-related thermal input influence factors are obtained.

[0011] Furthermore, the dynamic correction of thermal expansion includes the following steps: S71. Construct an intelligent correction model for the correlation between thermal expansion and heat input, and input the power-related heat input influencing factor into the model as a dynamic adjustment parameter; set up a multi-level correction strategy, and divide different correction priority areas according to the magnitude and changing trend of the influencing factor. S72. Introduce a real-time feedback learning mechanism to dynamically optimize the correction parameters of each region based on historical correction effects and actual thermoforming conditions; S73. Input the data of each region into the intelligent correction model in order of correction priority, make targeted adjustments to the thermal expansion difference prediction data of each region, and generate dynamic correction data of thermal expansion.

[0012] Furthermore, the optimization of the dynamic thermal expansion correction data specifically includes: An adaptive evolutionary optimization algorithm is introduced, and multi-level constraints are set. Through iterative calculations, the process parameters in the thermoforming process are adjusted. When the preset convergence conditions are met, the output is an optimized model of the thermoforming process containing the optimal combination of process parameters for the fiber raw materials.

[0013] The beneficial effects of this invention are as follows: 1. By setting up a temperature sensor array to collect initial temperature field data of raw materials and performing temperature gradient analysis, it is possible to comprehensively and accurately grasp the temperature distribution of fiber raw materials before thermoforming, providing a reliable basis for subsequent analysis.

[0014] 2. A virtual model is constructed based on the microstructure characteristics of the fiber, and machine learning algorithms are used to evaluate the thermal conductivity characteristics of different regions of the fiber raw material. This results in accurate evaluation data, which helps to gain a deeper understanding of the thermal conductivity of the fiber in different regions.

[0015] 3. Construct a dynamic digital twin model with thermo-mechanical coupling, combined with an intelligent fiber raw material behavior prediction module, which can accurately simulate the local thermal response of fiber raw materials during the thermoforming process and predict the thermal expansion differences in each region, thus identifying potential problems in advance.

[0016] 4. By collecting real-time heating power data of the thermoforming system, identifying heat input influencing factors, and using an intelligent correction model to dynamically correct the thermal expansion difference prediction data, the data is made more consistent with the actual thermoforming situation, thus improving the prediction accuracy.

[0017] 5. An optimization algorithm is used to construct an optimization model for the thermoforming process. The process parameters are dynamically adjusted based on real-time data to optimize the thermoforming process, effectively improve the forming quality and production efficiency of high enthalpy temperature-controlled fibers, reduce the scrap rate, and reduce production costs. Attached Figure Description

[0018] Figure 1 This is a system block diagram of the present invention; Figure 2 This is a flowchart of the thermal conductivity evaluation unit of the present invention; Figure 3 This is a flowchart of the thermal expansion prediction unit of the present invention; Figure 4 This is a flowchart of the dynamic correction unit of the present invention. Detailed Implementation

[0019] The present application will now be described in further detail with reference to the accompanying drawings. It should be noted that the following specific embodiments are only used to further illustrate the present application and should not be construed as limiting the scope of protection of the present application. Those skilled in the art can make some non-essential improvements and adjustments to the present application based on the above application content.

[0020] Please see Figure 1-4 This invention provides a technical solution: a thermoforming system suitable for high enthalpy temperature-controlled fibers, the system comprising a gradient analysis unit, a thermal conductivity evaluation unit, a thermal expansion prediction unit, a dynamic correction unit, and a thermoforming optimization unit, specifically: The gradient analysis unit is used to collect the initial temperature field data of the fiber raw material before thermoforming and perform temperature gradient analysis to obtain temperature gradient distribution data. Among them, temperature field refers to the temperature distribution at various points in a certain space; temperature gradient analysis refers to the rate or difference of temperature change with spatial location, and temperature gradient distribution data reflects the rate of temperature change at different locations of the fiber. The thermal conductivity assessment unit is used to assess the thermal conductivity of different regions of fiber raw materials using temperature gradient distribution data and a pre-constructed local thermal conductivity tendency prediction model, so as to obtain thermal conductivity assessment data. Among them, thermal conductivity refers to the thermal conductivity of the fiber raw material, which is expressed as thermal conductivity in this embodiment; The thermal expansion prediction unit is used to obtain local thermal response simulation data of fiber raw materials by using a pre-built dynamic digital twin model of fiber raw materials and thermal conduction characteristic evaluation data, and to obtain the prediction results of thermal expansion differences in different regions of fiber raw materials based on a multi-dimensional feature fusion prediction framework and local thermal response simulation data. Among them, local thermal response simulation is a numerical simulation of the response of fiber raw materials to local temperature changes during thermoforming; thermal expansion difference prediction refers to the fact that the thermal expansion of fiber raw materials usually changes with temperature. The dynamic correction unit is used to combine the real-time heating power data and local thermal response simulation data of the thermoforming system to identify the heat input influencing factors, obtain the power-related heat input influencing factors, and perform dynamic correction of the thermal expansion difference prediction results. Among them, heat input refers to the influencing factor of heating power, that is, how heating power affects the thermal response of fiber raw materials during thermoforming; dynamic correction of thermal expansion is to adjust the thermal expansion prediction so that the simulation data is closer to the thermal expansion difference in the actual thermoforming process. The thermoforming optimization unit is used to optimize the dynamic correction data of thermal expansion using optimization algorithms and send the optimization results to the thermoforming control system.

[0021] The thermal conductivity evaluation unit obtains evaluation data on thermal conductivity characteristics, including the following steps: S21. Construct a virtual fiber model based on the microstructure characteristics of the fiber raw material, and map the temperature gradient distribution data to the virtual fiber model to obtain local heat flow path simulation data. S22. Input the simulated local heat flow path data into the CNN network for training, and classify the heat conduction tendency of each region of the fiber based on the trained model; combine the classification results with the pre-set heat conduction characteristic reference table to determine the heat conduction characteristic level of each region and obtain evaluation data with heat conduction characteristics.

[0022] Assume the input to the neural network model is simulated heat flow path data. The tendency of local heat conduction Using mean squared error (MSE) as the loss function L: ; in, This is the predicted output of the neural network model. The neural network model is trained by minimizing the loss function using the backpropagation algorithm and gradient descent.

[0023] The local thermal response simulation process in the thermal expansion prediction unit is as follows: S31. Construct a dynamic digital twin model of the thermal coupling of fiber raw materials, and embed the thermal conductivity evaluation data into each local region of the model; Coefficient of thermal expansion of fiber raw materials With temperature The relationship can be approximated as: ; in, Reference temperature The coefficient of thermal expansion at that point, It is the temperature coefficient; elastic modulus With temperature The relationship can be represented as: ; in, Reference temperature The elastic modulus below, It is the temperature correlation coefficient; S32. Simulate the heating state of the thermoforming system and dynamically generate a local heat flow distribution map in the dynamic digital twin model based on the heat conduction characteristics of the fiber raw material; S33. Introduce an intelligent fiber raw material behavior prediction module, and combine historical thermoforming data with the current heat flow spectrum to predict the microstructure change trend of local fiber due to heat, and adjust the local fiber raw material thermal expansion coefficient and elastic modulus in real time in the model. S34. Through iterative calculation using a digital twin model, obtain simulated data of local thermal response in various local areas of the fiber raw material at different times; In the digital twin model, iterative calculations are performed based on the heat conduction equation and the mechanical equilibrium equation. The heat conduction equation is as follows: ; in, It is the density of the fiber raw material. It is specific heat capacity. It is time. It is a heat source item.

[0024] The mechanical equilibrium equation is: ; in, It is the stress tensor. It is a volume force.

[0025] In the thermal expansion prediction unit, the process for predicting thermal expansion differences is as follows: S41. Build a multi-dimensional feature fusion prediction framework based on deep learning, and use local thermal response simulation data as input features; S42. Introduce a virtual thermal expansion calibration experiment module to simulate extreme thermal expansion scenarios under different feature combinations within the prediction framework and generate a virtual calibration dataset. S43. Use a virtual calibration dataset to enhance the training of the prediction framework; S44. Input the actual simulation data into the trained prediction framework to classify and predict the thermal expansion behavior of each region and generate differential prediction data. Support Vector Machine (SVM) is used to classify and predict the thermal expansion behavior of each region; the decision function of SVM is: ; in, It is a Lagrange multiplier. These are sample labels. It's a kernel function. It is a bias term; by training an SVM model, classification and prediction are performed on actual simulated data to generate differential prediction data.

[0026] Extreme thermal expansion scenarios were simulated through virtual thermal expansion calibration experiments, generating a calibration dataset which was then used to enhance the training of the prediction framework. The trained framework can identify complex thermodynamic coupling relationships, predict the thermal expansion behavior of different regions, and ultimately generate thermal expansion difference prediction data.

[0027] A preliminary assessment of mold compatibility in the initial stage of thermoforming is conducted based on thermal expansion difference prediction data to obtain preliminary mold compatibility assessment data, including the following steps: S51. Construct a virtual simulation scenario of thermal expansion interaction between the mold and fiber, and map the predicted data of thermal expansion difference to the contact interface between the virtual mold and the fiber raw material. S52. Introduce an intelligent conflict detection algorithm to identify potential interference areas and areas with excessive gaps between the mold and fiber due to differences in thermal expansion in a virtual simulation scenario. Assume the difference in thermal expansion at a certain point on the interface between the mold and the fiber material is... The preset interference threshold is The gap threshold is The conflict detection rule is as follows: if If so, then this point is a potential interference region; if If so, then that point is a region with excessively large gaps.

[0028] S53. Establish a mold adaptability evaluation index system and use machine learning models to quantitatively score key indicators of potential problem areas. S54. Based on the comprehensive scoring results of each region and the preset compatibility level classification standards, generate preliminary assessment data for mold compatibility.

[0029] In the dynamic correction unit, real-time heating power data of the thermoforming system is collected through a temperature sensor array, and the local thermal response simulation data is analyzed based on the real-time heating power data to identify the heat input influence factor, thereby obtaining the power-related heat input influence factor. This includes the following steps: S61. Collect temperature data from various parts of the thermoforming system, and use an intelligent data fusion algorithm to characterize the temperature data to obtain a real-time heating power characterization dataset. S62. Input the real-time heating power characterization data and the local thermal response simulation data into the thermal response digital mapping model; Assume the temperature measured by the temperature sensor array is The weighted average method can be used to convert temperature information into real-time heating power characterization data. : ; in, It is a weighting coefficient, which can be determined based on the sensor's location and accuracy.

[0030] S63. Introduce a dynamic weight allocation mechanism to assign weights to the heating power characterization data according to different heating stages and regional characteristics; Let the different heating stages be: Different regions are Weight functions can be defined. : ; in, It is a region The basic weights, It is the heating stage. The amount of weight adjustment.

[0031] S64. Through model iterative calculation and dynamic weight adjustment, key power parameters that significantly affect local thermal response simulation data are identified, and power-related thermal input influence factors are obtained.

[0032] Dynamic correction of thermal expansion difference prediction data using influencing factors includes the following steps: S71. Construct an intelligent correction model for the correlation between thermal expansion and heat input, and input the power-related heat input influencing factor into the model as a dynamic adjustment parameter; set up a multi-level correction strategy, and divide different correction priority areas according to the magnitude and changing trend of the influencing factor. S72. Introduce a real-time feedback learning mechanism to dynamically optimize the correction parameters of each region based on historical correction effects and actual thermoforming conditions; S73. Input the data of each region into the intelligent correction model in order of correction priority, make targeted adjustments to the thermal expansion difference prediction data of each region, and generate dynamic thermal expansion correction data. In the process of dynamic correction for thermal expansion, the following thermal expansion correction formula is used to make targeted adjustments to the predicted data of thermal expansion differences in various regions: ; in: After thermal expansion dynamic correction, the first Thermal expansion of each region; For the first The amount of thermal expansion in the original thermal expansion difference prediction data of each region; For the first The coefficient of thermal expansion of fiber raw materials in each region can be pre-determined and stored in the system database based on the actual properties of the fiber raw materials. Different regions may have different coefficients of thermal expansion due to differences in the microstructure of the fiber raw materials. For the first A heat input response sensitivity factor for each region, with a value range of [0,1], is used to characterize the sensitivity of the region to changes in heat input and is determined in the following way: In the process of collecting historical thermoforming data, the first Data on thermal expansion changes in a region under different thermal input conditions were used to construct a dataset. ,in For the first The heat input power of this experiment This represents the corresponding change in thermal expansion. This represents the number of samples in the dataset. Using datasets Train a linear regression model, where ,in, For regression coefficients, The intercept; Will After normalization, the thermal input response sensitivity factor is obtained. ; in This represents the total number of regions in the system. For the first The power-related heat input influence factor of a region is related to the preset standard heat input power of that region. The difference, i.e. ,in, For the first The power-related heat input influence factor for each region is obtained through step S66.

[0033] In the thermoforming optimization unit, the dynamic correction data for thermal expansion is optimized using an optimization algorithm. The process is as follows: An adaptive evolutionary optimization algorithm is introduced, and multi-level constraints are set. Through iterative calculations, the process parameters in the thermoforming process are adjusted. When the preset convergence conditions are met, the output is an optimized model of the thermoforming process containing the optimal combination of process parameters for the fiber raw materials.

[0034] 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.

[0035] 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 thermoforming system suitable for high enthalpy temperature-controlled fibers, characterized in that, The system includes the following units: The gradient analysis unit is used to collect the initial temperature field data of the fiber raw material before thermoforming and perform temperature gradient analysis to obtain temperature gradient distribution data. The thermal conductivity assessment unit is used to assess the thermal conductivity characteristics of different regions of the fiber raw material using the temperature gradient distribution data and the constructed local thermal conductivity tendency prediction model to obtain thermal conductivity assessment data; wherein, the local thermal conductivity tendency prediction model is constructed based on simulating local heat flow paths under different microstructures and a CNN network. The thermal expansion prediction unit is used to obtain local thermal response simulation data of the fiber raw material using a pre-constructed thermo-coupling dynamic digital twin model of the fiber raw material and the thermal conduction characteristic evaluation data, and to obtain the prediction results of thermal expansion differences in various regions of the fiber raw material based on a multi-dimensional feature fusion prediction framework and the local thermal response simulation data. The dynamic correction unit is used to combine the real-time heating power data and local thermal response simulation data of the thermoforming system to identify the heat input influencing factors, obtain the power-related heat input influencing factors, and perform dynamic correction of the thermal expansion difference prediction results. The thermoforming optimization unit is used to optimize the dynamic correction data of thermal expansion using an optimization algorithm and send the optimization results to the thermoforming control system.

2. The thermoforming system for high-enthalpy temperature-controlled fibers according to claim 1, characterized in that, The thermal conductivity assessment includes the following steps: S21. Construct a virtual fiber model based on the microstructure characteristics of the fiber raw material, and map the temperature gradient distribution data to the virtual fiber model to obtain local heat flow path simulation data. S22. Input the simulated local heat flow path data into the CNN network for training, and classify the heat conduction tendency of each region of the fiber based on the trained model; combine the classification results with the pre-set heat conduction characteristic reference table to determine the heat conduction characteristic level of each region and obtain evaluation data with heat conduction characteristics.

3. The thermoforming system for high-enthalpy temperature-controlled fibers according to claim 2, characterized in that, The acquisition of the local thermal response simulation data of the fiber raw material includes the following steps: S31. Construct a dynamic digital twin model of the thermal coupling of fiber raw materials, and embed the thermal conductivity evaluation data into each local region of the model; S32. Simulate the heating state of the thermoforming system and dynamically generate a local heat flow distribution map in the dynamic digital twin model based on the heat conduction characteristics of the fiber raw material; S33. Introduce an intelligent fiber raw material behavior prediction module, and combine historical thermoforming data with the current heat flow spectrum to predict the microstructure change trend of local fiber due to heat, and adjust the local fiber raw material thermal expansion coefficient and elastic modulus in real time in the model. S34. Through iterative calculation using a digital twin model, obtain simulated data of the local thermal response in various local areas of the fiber raw material at different times.

4. The thermoforming system for high-enthalpy temperature-controlled fibers according to claim 3, characterized in that, The prediction of thermal expansion differences includes the following steps: S41. Build a multi-dimensional feature fusion prediction framework based on deep learning, and use local thermal response simulation data as input features; S42. Introduce a virtual thermal expansion calibration experiment module to simulate extreme thermal expansion scenarios under different feature combinations within the prediction framework and generate a virtual calibration dataset. S43. Use a virtual calibration dataset to enhance the training of the prediction framework; S44. Input the actual simulation data into the trained prediction framework to classify and predict the thermal expansion behavior of each region, and generate differential prediction data.

5. A thermoforming system for high-enthalpy temperature-controlled fibers according to claim 4, characterized in that, Based on the predicted difference data, a preliminary assessment of mold compatibility in the initial stage of thermoforming is performed to obtain preliminary mold compatibility assessment data, including the following steps: S51. Construct a virtual simulation scenario of thermal expansion interaction between the mold and fiber, and map the predicted data of thermal expansion difference to the contact interface between the virtual mold and the fiber raw material. S52. Introduce an intelligent conflict detection algorithm to identify potential interference areas and areas with excessive gaps between the mold and fiber due to differences in thermal expansion in a virtual simulation scenario; S53. Establish a mold adaptability evaluation index system and use machine learning models to quantitatively score key indicators of potential problem areas. S54. Based on the comprehensive scoring results of each region and the preset compatibility level classification standards, generate preliminary assessment data for mold compatibility.

6. A thermoforming system for high-enthalpy temperature-controlled fibers according to claim 5, characterized in that, The identification of heat input influencing factors includes the following steps: S61. Collect temperature data from various parts of the thermoforming system, and use an intelligent data fusion algorithm to characterize the temperature data to obtain a real-time heating power characterization dataset. S62. Input the real-time heating power characterization data and the local thermal response simulation data into the thermal response digital mapping model; S63. Introduce a dynamic weight allocation mechanism to assign weights to the heating power characterization data according to different heating stages and regional characteristics; S64. Through model iterative calculation and dynamic weight adjustment, key power parameters that significantly affect local thermal response simulation data are identified, and power-related thermal input influence factors are obtained.

7. A thermoforming system for high-enthalpy temperature-controlled fibers according to claim 6, characterized in that, The dynamic correction for thermal expansion includes the following steps: S71. Construct an intelligent correction model for the correlation between thermal expansion and heat input, and input the power-related heat input influencing factor into the model as a dynamic adjustment parameter; set up a multi-level correction strategy, and divide different correction priority areas according to the magnitude and changing trend of the influencing factor. S72. Introduce a real-time feedback learning mechanism to dynamically optimize the correction parameters of each region based on historical correction effects and actual thermoforming conditions; S73. Input the data of each region into the intelligent correction model in order of correction priority, make targeted adjustments to the thermal expansion difference prediction data of each region, and generate dynamic correction data of thermal expansion.

8. A thermoforming system for high-enthalpy temperature-controlled fibers according to claim 7, characterized in that, The optimization of the dynamic correction data for thermal expansion is specifically as follows: An adaptive evolutionary optimization algorithm is introduced, and multi-level constraints are set. Through iterative calculations, the process parameters in the thermoforming process are adjusted. When the preset convergence conditions are met, the output is an optimized model of the thermoforming process containing the optimal combination of process parameters for the fiber raw materials.

Images