Intelligent forming system and equipment based on thermal-mechanical coupling carbon fiber composite material

Abstract

The invention relates to the technical field of high-pressure resin transfer molding (HP-RTM), in particular to an intelligent forming system and equipment based on thermal-mechanical coupling carbon fiber composites.The intelligent forming method comprises the steps that real-time temperature field and strain field data are collected through a partition temperature control mold, thermal-mechanical coupling state parameters are obtained through signal filtering and abnormal value removing processing, and the thermal-mechanical coupling state parameters are obtained through a thermal-mechanical coupling module; an ultrasonic probe array is combined to detect internal defect distribution to evaluate a forming quality index, process parameters are dynamically compensated according to the quality index, and a deep learning model is constructed to optimize a forming process. According to the invention, real-time monitoring and closed-loop control of multi-physics field coupling can be realized, the defect rate is obviously reduced, the debugging period is shortened, the production efficiency is improved, and an intelligent solution is provided for carbon fiber composite material forming.

Description

Technical Field

[0001] The present invention belongs to the technical field of high-pressure resin transfer molding (HP-RTM), and specifically relates to an intelligent molding system and equipment for carbon fiber composite materials based on thermal-mechanical coupling. Background Art

[0002] Carbon fiber composites, due to their high specific strength, high specific modulus, and excellent corrosion resistance, have been widely used in aerospace, new energy vehicles, wind power, and other fields. However, their molding process is complex, especially the thermo-mechanical coupling involved in high-pressure resin transfer molding (HP-RTM), which has a decisive impact on molding quality. Traditional molding processes have significant shortcomings in resin flow control, temperature uniformity during the curing process, and multi-physics field coupling optimization, leading to high defect rates, high trial-and-error costs, and low production efficiency. For example, resin under high pressure (10-20 MPa) is prone to fiber scouring or uneven infiltration, resulting in defects such as dry spots and pores. Warping and residual stress caused by uneven temperature during the curing process further exacerbate molding difficulties. Furthermore, traditional processes rely on experience, have long debugging cycles (dozens of mold trials), and scrap rates can reach 20%, making them unable to meet the high precision and consistency requirements of lightweight manufacturing for high-end equipment.

[0003] In the prior art, a carbon fiber material molding autoclave, published in CN118721797B, incorporates both oil and air heating mechanisms, combined with a soft silicone wrapping method to maintain a constant temperature during the molding process, thereby improving workpiece quality. However, this technical solution primarily relies on a static temperature control strategy and lacks the ability to dynamically monitor and control the resin flow field and the thermochemical field of the curing reaction. Furthermore, it fails to consider the impact of mold thermoelastic deformation on the cavity geometry, potentially leading to localized uneven resin flow or excessive cure gradients, which in turn can cause defects such as dry spots and pores. Another carbon fiber product molding jig and process, published in CN114750435B, utilizes contoured blocks and positioning elements to achieve shape adaptation and position adjustment during the molding process, reducing molding limitations. However, this technology remains primarily empirically driven, lacking systematic modeling and intelligent decision-making support for thermal-mechanical coupling effects. It also fails to incorporate real-time sensor data fusion and digital twin technology, making it impossible to dynamically predict the resin flow front and cure distribution, making it difficult to respond to unexpected anomalies (such as sudden injection pressure increases or temperature fluctuations). In addition, the fixture has limited adaptability to complex structural parts and is difficult to meet the needs of lightweight manufacturing of high-end equipment.

[0004] The above problems indicate that the existing carbon fiber composite molding technology still has significant deficiencies in terms of fully coupled modeling of thermal-mechanical coupling effects, real-time monitoring and dynamic control, and intelligent process optimization. Specifically, traditional process optimization relies on finite element simulation and experimental verification, but offline simulation cannot be controlled in real time, and the simulation results are disconnected from the actual production data, making it difficult to dynamically correct process parameters; multi-physics field coupling calculations are complex, and resin flow (fluid mechanics), curing reaction (thermochemistry), and mold deformation (solid mechanics) need to be modeled separately, making collaborative optimization difficult; manual parameter adjustment has a slow response, lacks intelligent decision-making capabilities, and is difficult to deal with sudden anomalies. Therefore, there is an urgent need for an intelligent molding system and control method based on thermal-mechanical coupling, which can realize real-time simulation and closed-loop control of multi-physics field coupling through digital twin technology, reduce defect rates, shorten process debugging cycles, and improve production efficiency, thereby meeting the needs of lightweight and green manufacturing of high-end equipment.

[0005] This paper studies the thermal-mechanical coupling effect in the HP-RTM process, focusing on solving the following core problems: (1) resin flow control is difficult, and fiber preforms are easily washed out or unevenly infiltrated under high pressure; (2) the curing process is irreversible, and the uneven temperature field leads to component warping and residual stress; (3) the process relies on experience, with high trial-and-error costs and low efficiency. By introducing digital twin technology, integrating thermal-mechanical coupling simulation with real-time sensor data, the resin flow front and curing degree distribution are accurately predicted, and process parameters are dynamically adjusted based on model predictive control to achieve "one-time qualified molding." At the same time, by accumulating process data to build an AI model, the dependence on human experience is reduced, and composite material manufacturing is promoted from "experience-driven" to "data-driven", which is in line with the development trend of lightweight high-end equipment and green manufacturing. Summary of the Invention

[0006] The present invention provides an intelligent molding system and equipment for carbon fiber composite materials based on thermal-mechanical coupling. Its main purpose is to solve the problems of high defect rate, long debugging cycle and low production efficiency caused by thermal-mechanical coupling in the high-pressure resin transfer molding (HP-RTM) process. Through digital twin technology, real-time optimization and closed-loop control of multi-physical field coupling are realized, thereby improving molding quality and reducing production costs.

[0007] To achieve the above objectives, the present invention provides an intelligent molding system for carbon fiber composite materials based on thermal-mechanical coupling, comprising: A zoned temperature-controlled mold with a built-in fiber Bragg grating sensor is used to collect real-time temperature and strain field data of the target component. The real-time temperature field data includes: temperature distribution in the resin flow area, temperature distribution on the mold surface, and peak value of curing exotherm. Performing signal filtering and outlier elimination processing on the real-time temperature field and strain field data to obtain real-time thermal-mechanical coupling state parameters, wherein the real-time thermal-mechanical coupling state parameters include: resin viscosity change rate, mold thermal expansion, and curing degree gradient; Using a pre-built ultrasonic probe array to detect the internal defect distribution of the target component, calculating the dynamic deformation of the mold cavity based on the real-time thermal-mechanical coupling state parameters, and evaluating the molding quality index of the target component by combining the internal defect distribution and the dynamic deformation of the mold cavity; Determining whether the molding quality index is lower than a preset quality threshold; If the molding quality index is lower than the quality threshold, the injection pressure and the mold partition temperature are dynamically compensated according to the molding quality index to obtain optimized process parameters; If the molding quality index is not lower than the quality threshold, the current process parameters are used as optimized process parameters; Acquire a historical molding data set of a target component, and set an initial process window of the target component according to the historical molding data set, wherein the initial process window includes: an injection pressure range, a mold temperature range, and a curing time range; Constructing an initial process optimization model according to the initial process window and the pre-built deep learning model, and training the initial process optimization model using the historical molding data set to obtain a target process optimization model; According to the optimized process parameters, the target process optimization model is used to dynamically adjust the molding process of the target component.

[0008] Optionally, performing signal filtering and outlier elimination processing on the real-time temperature field and strain field data to obtain real-time thermal-mechanical coupling state parameters includes: Performing low-pass filtering on the real-time temperature field and strain field data to obtain preliminary state parameters; A signal-to-noise ratio threshold of the fiber Bragg grating sensor is obtained, and outlier elimination processing is performed on the preliminary state parameters based on the signal-to-noise ratio threshold to obtain real-time thermal-mechanical coupling state parameters, where the real-time thermal-mechanical coupling state parameters are represented by: resin viscosity change rate, mold thermal expansion, and curing degree gradient.

[0009] Optionally, calculating the dynamic deformation of the mold cavity according to the real-time thermal-mechanical coupling state parameter, and evaluating the molding quality index of the target component in combination with the internal defect distribution and the dynamic deformation of the mold cavity, includes: Calculating the dynamic deformation of the mold cavity using a mold thermoelastic deformation model according to the real-time thermal-mechanical coupling state parameters; Combining the internal defect distribution and the dynamic deformation of the mold cavity, a weighted scoring method is used to evaluate the molding quality index of the target component, wherein the weight distribution is dynamically adjusted according to the defect type and deformation size.

[0010] Optionally, dynamically compensating the injection pressure and the mold partition temperature according to the molding quality index to obtain optimized process parameters includes: Constructing a dynamic compensation strategy matrix according to the molding quality index, wherein the dynamic compensation strategy matrix includes injection pressure increments and mold partition temperature adjustment values; The current process parameters are compensated and calculated according to the dynamic compensation strategy matrix to obtain optimized process parameters, wherein the optimized process parameters include: target injection pressure, target partition temperature and target solidification time.

[0011] Optionally, setting the initial process window of the target component according to the historical molding data set includes: Obtaining process boundary conditions of the historical molding data set, wherein the historical molding data set is a combination of multiple sets of process parameters with molding quality labels, and the process boundary conditions include: maximum injection pressure, minimum mold temperature, and maximum curing time; The maximum injection pressure, the minimum mold temperature, and the maximum curing time are respectively used as the upper limit and the lower limit of the initial process window to obtain the initial process window range; According to the preset safety margin, the optimal process parameter combination is selected within the initial process window to obtain the initial process window.

[0012] Optionally, the using the historical molding data set to train the initial process optimization model to obtain a target process optimization model includes: Randomly dividing the historical forming data set into a training data set and a validation data set; Extracting training samples in sequence from the training data set; Inputting the training samples into the initial process optimization model to obtain model prediction results; Identifying the molding quality labels of the training samples, and determining whether the model prediction results are consistent with the molding quality labels of the training samples; If the model prediction result is consistent with the molding quality label of the training sample, the initial process window is used as the target process window; If the model prediction result is inconsistent with the molding quality label of the training sample, the initial process window is adjusted according to the training sample to obtain the target process window; Constructing a verification process optimization model based on the deep learning model and the target process window; Extracting validation samples in sequence from the validation data set, inputting the validation samples into a validation process optimization model, and obtaining a model validation result; Identify the molding quality label of the verification sample and determine whether the model verification result is consistent with the molding quality label of the verification sample: If the model verification result is inconsistent with the molding quality label of the verification sample, obtaining inconsistent data in the verification sample, using the inconsistent data as a training sample, using the verification process optimization model as an initial process optimization model, and returning to the step of inputting the training sample into the initial process optimization model; If the model verification result is consistent with the molding quality label of the verification sample, the verification process optimization model is used as the target process optimization model.

[0013] Optionally, adjusting the initial process window according to the training sample to obtain the target process window includes: The training sample is expressed as: Where, represents the training sample, represents the injection pressure, represents the mold temperature, and represents the curing time; The initial process window is expressed as: Wherein, represents the initial injection pressure range, represents the minimum injection pressure, represents the maximum injection pressure, represents the initial mold temperature range, represents the minimum mold temperature, represents the maximum mold temperature, represents the initial curing time range, represents the shortest curing time, and represents the longest curing time; Determining the difference type between the model prediction result and the molding quality label, wherein the difference type includes: premature curing and insufficient curing; If the difference type is premature solidification, the initial process window is delayed according to the training sample to obtain the target process window; If the difference type is insufficient curing, the initial process window is accelerated according to the training sample to obtain the target process window.

[0014] Optionally, the difference type between the prediction result of the judgment model and the molding quality label includes: Obtain the target curing degree of the molding quality label and the predicted curing degree of the model prediction result; determining whether the target curing degree is within a predicted curing degree range; If the target curing degree is not within the predicted curing degree range, the difference type is set to premature curing; If the target curing degree is within the predicted curing degree range, the difference type is set to insufficient curing.

[0015] Optionally, dynamically adjusting the molding process of the target component using a target process optimization model according to the optimized process parameters includes: Inputting the optimized process parameters into a target process optimization model to obtain a predicted molding state; The predicted molding state is matched with the target process window to obtain a molding process adjustment plan, which includes injection path optimization, zone temperature distribution optimization, and curing time extension or shortening.

[0016] To achieve the above objectives, the present invention further provides an intelligent molding system for carbon fiber composite materials based on thermal-mechanical coupling, comprising: A data acquisition module is used to collect real-time temperature and strain field data of the target component using a zoned temperature-controlled mold with a built-in fiber Bragg grating sensor. The real-time temperature field data includes: temperature distribution in the resin flow area, temperature distribution on the mold surface, and peak exothermicity during curing. The real-time temperature and strain field data are subjected to signal filtering and outlier removal processing to obtain real-time thermal-mechanical coupling state parameters. The real-time thermal-mechanical coupling state parameters include: resin viscosity change rate, mold thermal expansion, and curing degree gradient. a quality assessment module for detecting internal defect distribution of a target component using a pre-built ultrasonic probe array, calculating a dynamic deformation of the mold cavity based on the real-time thermal-mechanical coupling state parameter, and evaluating a molding quality index of the target component by combining the internal defect distribution and the dynamic deformation of the mold cavity; a process optimization module, configured to determine whether the molding quality index is lower than a preset quality threshold; if so, dynamically compensate the injection pressure and the mold zone temperature according to the molding quality index to obtain optimized process parameters; and if not, use the current process parameters as optimized process parameters, obtain a historical molding data set of the target component, and set an initial process window of the target component based on the historical molding data set, wherein the initial process window includes: an injection pressure range, a mold temperature range, and a curing time range; A dynamic adjustment module is used to construct an initial process optimization model based on the initial process window and a pre-built deep learning model, train the initial process optimization model using the historical molding data set to obtain a target process optimization model, and dynamically adjust the molding process of the target component using the target process optimization model according to the optimized process parameters.

[0017] In order to solve the above problem, the present invention further provides an electronic device, comprising: a memory storing at least one instruction; The processor executes the instructions stored in the memory to implement the above-mentioned carbon fiber composite material intelligent molding system and equipment based on thermal-mechanical coupling.

[0018] In order to solve the above problems, the present invention also provides a computer-readable storage medium, which stores at least one instruction, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned thermal-mechanical coupling carbon fiber composite material intelligent molding system and equipment.

[0019] To address the problems described in the background art, the present invention utilizes a zoned temperature-controlled mold with built-in fiber Bragg grating sensors to collect real-time temperature and strain field data from the target component, enabling intelligent, real-time monitoring of the thermo-mechanical coupling state during the molding process. Signal filtering and outlier removal are performed on the real-time temperature and strain field data to obtain real-time thermo-mechanical coupling state parameters, transforming complex multi-physics field data into intuitive state indicators. An ultrasonic probe array is used to detect the internal defect distribution of the target component, enabling defect location and quantification under non-destructive testing, providing a basis for subsequent molding quality assessment. The dynamic deformation of the mold cavity is calculated based on the real-time thermo-mechanical coupling state parameters, resulting in a prediction of mold cavity geometry changes based on a thermoelastic deformation model, facilitating subsequent process optimization. By combining the internal defect distribution with the dynamic deformation of the mold cavity, the molding quality index of the target component is evaluated, achieving a numerical assessment of molding quality. Because the molding quality index has an acceptable range, eliminating the need for compensation adjustments for all molding quality indices, determining whether the molding quality index is below a quality threshold allows screening of molding states within the threshold. If the molding quality index falls below the quality threshold, the molding state is outside the acceptable range. Therefore, dynamic compensation of the injection pressure and mold zone temperature is performed based on the molding quality index to obtain optimized process parameters and optimize the molding quality of the target component. If the molding quality index is not below the quality threshold, the molding state is within the acceptable range. By using the current process parameters as the optimized process parameters, unnecessary compensation adjustments can be skipped, accelerating the overall molding process optimization process. By obtaining the historical molding dataset of the target component and setting the initial process window for the target component based on the historical molding dataset, a basis for molding process optimization is obtained. Furthermore, an initial process optimization model is constructed based on the initial process window and a deep learning model. This initial process optimization model is trained using the historical molding dataset to obtain the target process optimization model. This step utilizes the data-driven nature of the deep learning model to construct a model that can intelligently optimize the molding process. This target process optimization model is unaffected by subjective human factors and exhibits high accuracy. Finally, by inputting the optimized process parameters into the target process optimization model, dynamic adjustment of the molding process for the target component is achieved. This process eliminates the need for extensive human intervention, reducing human resource consumption. Therefore, the present invention can reduce the human resource consumption in the process of optimizing the molding process and improve the accuracy and efficiency of the molding process. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram of a process flow of a carbon fiber composite material intelligent molding system and equipment based on thermal-mechanical coupling provided by one embodiment of the present invention; Figure 2 A functional module diagram of a carbon fiber composite material intelligent molding system based on thermal-mechanical coupling provided by one embodiment of the present invention; Figure 3 A schematic structural diagram of an electronic device for implementing the thermal-mechanical coupling-based carbon fiber composite intelligent molding system and equipment provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0021] This invention provides a carbon fiber composite intelligent molding system and equipment based on thermal-mechanical coupling. Its core is to achieve real-time optimization and closed-loop control of multi-physics field coupling through digital twin technology, thereby addressing the high defect rate, long commissioning cycle, and low production efficiency caused by thermal-mechanical coupling in the high-pressure resin transfer molding (HP-RTM) process. The technical solutions of this invention are described in detail below, with reference to the accompanying figures and their reference numerals, as well as specific embodiments.

[0022] like Figure 1 As shown, the flow chart of the intelligent forming system and equipment of carbon fiber composite materials based on thermal-mechanical coupling provided by the present invention shows the operating logic of the entire system. First, the data acquisition module uses a partitioned temperature-controlled mold with a built-in fiber grating sensor to collect real-time temperature field and strain field data of the target component. Specifically, the partitioned temperature-controlled mold consists of a plurality of independently controllable heating areas, each of which is embedded with a fiber grating sensor for real-time monitoring of the temperature distribution of the resin flow area, the temperature distribution of the mold surface and the curing exothermic peak. These data are converted into real-time thermal-mechanical coupling state parameters after signal filtering and outlier elimination, including the resin viscosity change rate, the mold thermal expansion and the curing degree gradient. Among them, the signal filtering adopts a low-pass filtering algorithm, and the formula is as follows: ; in, Represents the filter output at the current moment, Represents the input signal at the current moment, Represents the filter output at the previous moment, is the filter coefficient, typically ranging from 0.1 to 0.3. Low-pass filtering of the preliminary state parameters effectively removes high-frequency noise. Furthermore, outliers in the preliminary state parameters are removed by combining the signal-to-noise ratio threshold of the fiber Bragg grating sensor, further improving data reliability.

[0023] The quality assessment module then uses a pre-built ultrasonic probe array to detect the internal defect distribution of the target component. The ultrasonic probe array is placed around the mold cavity, emitting high-frequency ultrasonic waves and receiving reflected signals to generate a map of the target component's internal defect distribution. Based on the real-time thermal-mechanical coupling state parameters, the mold's thermoelastic deformation model is used to calculate the dynamic deformation of the mold cavity. The mathematical expression for the mold's thermoelastic deformation model is as follows: ; in, Indicates the length change of the mold cavity, represents the linear expansion coefficient of the material, represents the initial length of the mold cavity, represents the temperature change, F represents the applied force, E represents the elastic modulus of the material, and A represents the area under load. This model comprehensively considers the effects of thermal expansion and mechanical stress on the mold cavity geometry to accurately predict dynamic deformation. Based on this, a weighted scoring method is used to evaluate the molding quality index of the target component, combining the internal defect distribution with the dynamic deformation of the mold cavity. The calculation formula for the weighted scoring method is as follows: ; Among them, Q represents the molding quality index, D represents the quantitative value of the internal defect distribution, Indicates the dynamic deformation of the mold cavity, and are the corresponding weight coefficients, and satisfy The weight distribution is dynamically adjusted according to the defect type and deformation size. For example, for crack defects, Can be set to 0.7, and for pore defects, Can be set to 0.5.

[0024] Next, the process optimization module determines whether the molding quality index is below the preset quality threshold. If the molding quality index is below the quality threshold, it means that the current molding state is not within the acceptable range. Based on the molding quality index, dynamic compensation of injection pressure and mold zone temperature is required to obtain optimized process parameters. The formula for constructing the dynamic compensation strategy matrix is ​​as follows: ; ; in, Indicates the injection pressure increment, Indicates the mold partition temperature adjustment value, and are the corresponding proportional coefficients, represents the quality threshold, and Q represents the current molding quality index. The dynamic compensation strategy matrix is ​​used to compensate for the current process parameters, ultimately yielding the optimized process parameters, including target injection pressure, target zone temperature, and target curing time. If the molding quality index is not lower than the quality threshold, the current process parameters are directly used as the optimized process parameters, thus avoiding unnecessary compensation adjustments and accelerating the molding process optimization process.

[0025] To further optimize the molding process, the system acquires the target component's historical molding dataset and sets an initial process window for the target component based on this dataset. The historical dataset contains multiple sets of process parameter combinations with molding quality labels. Each set records key parameters such as injection pressure, mold temperature, and curing time, along with their corresponding molding quality results. The initial process window is set as follows: First, the process boundary conditions from the historical dataset are extracted, including the maximum injection pressure, minimum mold temperature, and maximum curing time. These are used as the upper and lower limits of the initial process window, respectively. Then, based on a preset safety margin, the optimal process parameter combination within the initial process window is selected to obtain the initial process window. For example, if the maximum injection pressure in the historical dataset is 10 MPa, the minimum mold temperature is 80°C, and the maximum curing time is 60 minutes, the initial process window can be set to an injection pressure range of 8-10 MPa, a mold temperature range of 80-120°C, and a curing time range of 40-60 minutes.

[0026] Based on the initial process window, the system uses a deep learning model to build an initial process optimization model, and trains it with historical molding data sets to obtain the target process optimization model. Figure 2 As shown in the figure, the functional module diagram of the thermal-mechanical coupled carbon fiber composite intelligent molding system clearly demonstrates the collaborative relationship between the various modules. During the training process, the historical molding dataset is randomly divided into a training dataset and a validation dataset. The training dataset is used to extract training samples and input them into the initial process optimization model to obtain model prediction results; the validation dataset is used to extract validation samples and input them into the validation process optimization model to evaluate the model's generalization ability. If the model prediction results are consistent with the molding quality labels of the training samples, the initial process window is used as the target process window; if not, the initial process window is adjusted based on the training samples. The adjustment process includes determining the type of difference between the model prediction results and the molding quality labels, such as premature curing or insufficient curing. If the difference is premature curing, the initial process window is delayed; if the difference is insufficient curing, it is accelerated. Through continuous iterative optimization, the target process optimization model is ultimately obtained.

[0027] Finally, the dynamic adjustment module dynamically adjusts the molding process of the target component based on the optimized process parameters and the target process optimization model. This involves inputting the optimized process parameters into the target process optimization model to obtain a predicted molding state; then, analyzing the predicted molding state against the target process window, determining a molding process adjustment plan. This molding process adjustment plan may involve optimizing the injection path, optimizing the temperature distribution of specific zones, and extending or shortening the curing time. For example, if the predicted molding state indicates insufficient curing in a specific area, the molding quality can be improved by increasing the mold temperature or extending the curing time in that area.

[0028] like Figure 3 As shown, the electronic device implementing the aforementioned thermal-mechanically coupled carbon fiber composite intelligent molding system and device includes a memory and a processor. The memory is used to store at least one instruction, while the processor is responsible for executing the instructions stored in the memory to implement the aforementioned method. Furthermore, the present invention also provides a computer-readable storage medium storing at least one instruction that, when executed by the processor in the electronic device, implements the aforementioned method.

[0029] In summary, this invention achieves intelligent, real-time monitoring of the thermal-mechanical coupling state during the molding process through a zoned temperature-controlled mold equipped with built-in fiber Bragg grating sensors. Combining an ultrasonic probe array with a deep learning model, this method implements closed-loop control of the entire process, from data acquisition to process optimization. By leveraging key technical approaches such as a dynamic compensation strategy matrix and a weighted scoring method, this method significantly improves molding quality and reduces production costs, providing reliable technical support for the intelligent manufacturing of carbon fiber composites.

Claims

1. An intelligent molding system for carbon fiber composite materials based on thermal-mechanical coupling, characterized in that: The system comprises: A data acquisition module is used to collect real-time temperature and strain field data of the target component using a zoned temperature-controlled mold with a built-in fiber Bragg grating sensor. The real-time temperature field data includes the temperature distribution in the resin flow area, the temperature distribution on the mold surface, and the peak value of curing exotherm. The real-time temperature and strain field data are subjected to signal filtering and outlier removal processing to obtain real-time thermal-mechanical coupling state parameters. The real-time thermal-mechanical coupling state parameters include the resin viscosity change rate, the mold thermal expansion, and the curing degree gradient. a quality assessment module for detecting internal defect distribution of a target component using a pre-built ultrasonic probe array, calculating a dynamic deformation of the mold cavity based on the real-time thermal-mechanical coupling state parameter, and evaluating a molding quality index of the target component by combining the internal defect distribution and the dynamic deformation of the mold cavity; a process optimization module, configured to determine whether the molding quality index is lower than a preset quality threshold; if so, dynamically compensate the injection pressure and the mold zone temperature according to the molding quality index to obtain optimized process parameters; and if not, use the current process parameters as optimized process parameters, obtain a historical molding data set of the target component, and set an initial process window for the target component based on the historical molding data set, the initial process window including an injection pressure range, a mold temperature range, and a curing time range; A dynamic adjustment module is used to construct an initial process optimization model based on the initial process window and a pre-built deep learning model, train the initial process optimization model using the historical molding data set to obtain a target process optimization model, and dynamically adjust the molding process of the target component using the target process optimization model according to the optimized process parameters.

2. The intelligent forming system of carbon fiber composite materials based on thermal-mechanical coupling according to claim 1, characterized in that: The real-time temperature field and strain field data are subjected to signal filtering and outlier elimination processing to obtain real-time thermal-mechanical coupling state parameters, including: Performing low-pass filtering on the real-time temperature field and strain field data to obtain preliminary state parameters; A signal-to-noise ratio threshold of the fiber Bragg grating sensor is obtained, and abnormal value elimination processing is performed on the preliminary state parameter according to the signal-to-noise ratio threshold to obtain a real-time thermal-mechanical coupling state parameter.

3. The intelligent forming system of carbon fiber composite materials based on thermal-mechanical coupling according to claim 1, characterized in that: The step of calculating the dynamic deformation of the mold cavity according to the real-time thermal-mechanical coupling state parameters and evaluating the molding quality index of the target component by combining the internal defect distribution and the dynamic deformation of the mold cavity includes: Calculating the dynamic deformation of the mold cavity using a mold thermoelastic deformation model according to the real-time thermal-mechanical coupling state parameters; Combining the internal defect distribution with the dynamic deformation of the mold cavity, a weighted scoring method is used to evaluate the molding quality index of the target component.

4. The intelligent forming system of carbon fiber composite materials based on thermal-mechanical coupling according to claim 1, characterized in that: The method of dynamically compensating the injection pressure and the mold partition temperature according to the molding quality index to obtain optimized process parameters includes: Constructing a dynamic compensation strategy matrix according to the molding quality index, wherein the dynamic compensation strategy matrix includes injection pressure increments and mold partition temperature adjustment values; The current process parameters are compensated and calculated according to the dynamic compensation strategy matrix to obtain the optimized process parameters.

5. The intelligent forming system of carbon fiber composite materials based on thermal-mechanical coupling according to claim 1, characterized in that: The step of setting the initial process window of the target component according to the historical molding data set includes: Obtaining process boundary conditions of the historical molding data set, wherein the historical molding data set is a combination of multiple sets of process parameters with molding quality labels, and the process boundary conditions include maximum injection pressure, minimum mold temperature, and maximum curing time; The maximum injection pressure, the minimum mold temperature, and the maximum curing time are respectively used as the upper limit and the lower limit of the initial process window to obtain the initial process window range; According to the preset safety margin, the optimal process parameter combination is selected within the initial process window to obtain the initial process window.

6. The carbon fiber composite material intelligent molding system based on thermal-mechanical coupling according to claim 1, characterized in that: The method of training the initial process optimization model using the historical molding data set to obtain a target process optimization model includes: Randomly dividing the historical forming data set into a training data set and a validation data set; Extracting training samples in sequence from the training data set; Inputting the training samples into the initial process optimization model to obtain model prediction results; Identifying the molding quality labels of the training samples, and determining whether the model prediction results are consistent with the molding quality labels of the training samples; If the model prediction result is inconsistent with the molding quality label of the training sample, the initial process window is adjusted according to the training sample to obtain the target process window.

7. The intelligent forming system of carbon fiber composite materials based on thermal-mechanical coupling according to claim 6, characterized in that: The step of adjusting the initial process window according to the training sample to obtain the target process window includes: Determining the difference type between the model prediction result and the molding quality label, wherein the difference type includes premature curing and insufficient curing; If the difference type is premature solidification, the initial process window is delayed according to the training sample to obtain the target process window; If the difference type is insufficient curing, the initial process window is accelerated according to the training sample to obtain the target process window.

8. The intelligent forming system of carbon fiber composite materials based on thermal-mechanical coupling according to claim 7, characterized in that: The types of differences between the prediction results of the judgment model and the molding quality labels include: Obtain the target curing degree of the molding quality label and the predicted curing degree of the model prediction result; determining whether the target curing degree is within a predicted curing degree range; If the target curing degree is not within the predicted curing degree range, the difference type is set to premature curing; If the target curing degree is within the predicted curing degree range, the difference type is set to insufficient curing.

9. The intelligent forming system of carbon fiber composite materials based on thermal-mechanical coupling according to claim 1, characterized in that: The method of dynamically adjusting the molding process of the target component using the target process optimization model according to the optimized process parameters includes: Inputting the optimized process parameters into a target process optimization model to obtain a predicted molding state; The predicted molding state is matched and analyzed with the target process window to obtain a molding process adjustment plan, which includes injection path optimization, zone temperature distribution optimization, and curing time extension or shortening.

10. An electronic device, characterized in that: The electronic device comprises: a memory storing at least one instruction; A processor executes instructions stored in the memory to implement the intelligent forming system of carbon fiber composite materials based on thermal-mechanical coupling according to any one of claims 1 to 9.

Images