Dynamic optimization method and device for automatic fiber placement path of composite material and medium

Abstract

The invention discloses a dynamic optimization method and device for an automatic fiber placement path of a composite material and a medium, and belongs to the technical field of automatic fiber placement of composite materials. The method comprises the steps that a three-dimensional model of a component to be laid is obtained, and curved surface curvature distribution characteristics and fiber laying angle constraints are obtained based on the three-dimensional model; processing the curved surface curvature distribution characteristics based on a path planning algorithm to generate an initial fiber placement path; on the basis of the tension mapping table and the temperature compensation coefficient, the fiber placement head is driven to execute reverse pre-tension control; acquiring actual fiber trend data according to a preset sampling period based on a polarization laser polarization instrument, and extracting a fiber angle deviation of the actual fiber trend data; processing the fiber angle deviation and the resin viscoelasticity data based on a Bayesian optimization algorithm so as to dynamically correct the laying path and generate an updating instruction; and adjusting the spatial pose and tension of the fiber placement head according to the updating instruction. Based on the method, dynamic multi-target fiber placement path optimization and real-time feedback control are realized.

Description

Technical Field

[0001] The present application relates to the technical field of automatic fiber placement of composite materials, and in particular to a method, equipment and medium for dynamic optimization of the automatic fiber placement path of composite materials. Background Art

[0002] As a key technology in advanced manufacturing, automated fiber placement technology for composite materials has been widely used in aerospace and automotive engineering. In existing technologies, fiber placement path planning primarily relies on the component's CAD model, generates an initial path based on a geometric algorithm, and employs an open-loop control strategy for tension control, making it difficult to achieve high-precision placement in dynamic environments. Furthermore, traditional path correction methods often employ rule-based local adjustments and lack the ability to comprehensively process multi-source heterogeneous data. This results in limited control of fiber angle deviations during the placement of complex curved components, and makes it difficult to adapt to the effects of resin viscoelasticity changes and fiber impregnation state fluctuations on placement quality.

[0003] Traditional fiber laying methods do not fully consider the real-time coupling of environmental data (such as temperature and humidity) and material data (such as resin viscoelasticity and fiber impregnation status), resulting in the inability to adjust laying parameters in a timely manner under dynamic working conditions, affecting the quality of the layup and molding efficiency. Existing path planning algorithms mostly focus on a single goal (such as the shortest path), and it is difficult to achieve multi-objective collaborative optimization between fiber continuity, layability, impregnation quality and laying efficiency, resulting in frequent manual intervention to balance various indicators in actual applications. Traditional tension control strategies mostly use fixed parameters or simple feedback mechanisms, and have not established a multi-dimensional mapping relationship between tension, speed, temperature and viscoelastic parameters. It is difficult to adjust the control parameters in real time according to the laying status, resulting in tension fluctuations affecting the uniformity of the layup.

[0004] Therefore, how to achieve dynamic multi-objective wire laying path optimization and real-time feedback control has become a technical problem that needs to be solved urgently. Summary of the Invention

[0005] The embodiments of the present application provide a method, device and medium for dynamic optimization of the automatic wire laying path of composite materials, which are used to solve the following technical problem: how to achieve dynamic multi-objective wire laying path optimization and real-time feedback control.

[0006] In a first aspect, an embodiment of the present application provides a method for dynamic optimization of an automatic fiber placement path for composite materials, which is applied to a fiber placement robot, wherein the fiber placement robot includes a fiber placement head and a polarization laser interferometer, and is characterized in that the method includes: obtaining a three-dimensional model of a component to be placed, and obtaining surface curvature distribution characteristics and fiber placement angle constraints based on the three-dimensional model; wherein the fiber placement angle constraints are dynamically corrected according to environmental data and material data of the component to be placed, the environmental data including temperature data and humidity data, and the material data including resin viscoelasticity data and fiber infiltration state data; processing the surface curvature distribution characteristics based on a preset path planning algorithm to generate An initial fiber placement path is formed; based on a preset tension mapping table and a temperature compensation coefficient, the fiber placement head is driven to perform reverse pre-tension control; wherein, the reverse pre-tension value is positively correlated with the square of the real-time placement speed of the fiber placement head; actual fiber orientation data is acquired according to a preset sampling period based on the polarization laser polarimeter, and the fiber angle deviation of the actual fiber orientation data is extracted; based on a preset Bayesian optimization algorithm, the fiber angle deviation and the resin viscoelasticity data are processed to dynamically correct the placement path and generate an update instruction; wherein, the update instruction includes a three-dimensional position compensation vector and a tension compensation coefficient; and the spatial position and tension of the fiber placement head are adjusted according to the update instruction.

[0007] In one implementation of the present application, a three-dimensional model of a component to be laid is obtained, and surface curvature distribution characteristics and fiber placement angle constraints are obtained based on the three-dimensional model, specifically including: scanning the component to be laid based on a preset CT machine to obtain CT scanning data; processing the CT scanning data and the CAD model of the component to be laid based on a multi-source heterogeneous data fusion algorithm to construct a three-dimensional model; extracting Gaussian curvature, mean curvature and principal curvature direction on the three-dimensional model based on a preset local surface fitting algorithm to determine surface curvature distribution characteristics; correcting the allowable range of the fiber placement angle based on the temperature data and humidity data in the environmental data to determine the fiber placement angle constraint; wherein the allowable range is nonlinearly correlated with the extreme value area in the curvature characteristic map.

[0008] In one implementation of the present application, the surface curvature distribution characteristics are processed based on a preset path planning algorithm to generate an initial fiber placement path, specifically including: performing path exploration in the surface curvature distribution characteristics based on a preset random sampling algorithm to generate candidate paths that meet fiber continuity and placeability constraints; constructing a cost function based on the resin viscoelastic parameters in the material data; wherein the cost function includes a path length optimization target, a curvature change rate optimization target, and an infiltration quality optimization target; adjusting the weight coefficients of multiple optimization targets in the cost function according to feedback from the infiltration state data; and determining the initial fiber placement path based on the size of the weight coefficient.

[0009] In one implementation of the present application, based on a preset tension mapping table and a temperature compensation coefficient, the laying head is driven to perform reverse pre-tension control, specifically including: constructing a four-dimensional mapping table; wherein the four-dimensional mapping table includes tension, speed, temperature and viscoelasticity; importing the real-time laying speed of the laying head and the temperature data in the environmental data into a preset neural network model to predict the temperature compensation coefficient; determining the reverse pre-tension value based on the four-dimensional mapping table and the temperature compensation coefficient; and driving the laying head based on the reverse pre-tension value.

[0010] In one implementation of the present application, actual fiber orientation data is obtained according to a preset sampling period based on the polarized laser polarimeter, and the fiber angle deviation of the actual fiber orientation data is extracted, specifically including: solving the azimuth and pitch angles of the fiber orientation based on a preset polarized light interference fringe analysis algorithm; performing joint spatiotemporal denoising processing on the azimuth and pitch angle data based on a preset extended Kalman filter algorithm to determine the fiber angle deviation; wherein the extended Kalman filter algorithm includes state prediction, covariance update, and measurement update.

[0011] In one implementation of the present application, the fiber angle deviation and the resin viscoelastic data are processed based on a preset Bayesian optimization algorithm to dynamically correct the placement path and generate update instructions, specifically including: constructing a three-objective optimization function; wherein the three-objective optimization function includes minimizing the fiber angle deviation, optimizing the resin viscoelastic data, and maximizing the placement efficiency; modeling the three-objective optimization function based on a preset Gaussian process model, and introducing Pareto front analysis to generate a Bayesian optimization algorithm; wherein the Pareto front analysis is used to find the optimal solution set in multi-objective optimization problems; generating the three-dimensional position compensation vector and tension compensation coefficient based on the Bayesian optimization algorithm; wherein the compensation vector includes a position correction amount, an attitude adjustment amount, and a speed compensation amount; and determining the update instruction based on the three-dimensional position compensation vector and the tension compensation coefficient.

[0012] In one implementation of the present application, the spatial position and tension of the wire laying head are adjusted according to the update instruction, specifically including: converting the three-dimensional position compensation vector into a joint space trajectory based on a preset robot inverse kinematics model, and optimizing the joint motion trajectory based on a preset weighted least squares method; wherein the weighted least squares method is used to solve the optimal joint motion trajectory under multiple constraints; and adjusting the tension output based on the tension compensation coefficient.

[0013] In one implementation of the present application, the method further includes: constructing a process database; wherein the process knowledge base includes historical process parameters, material performance data, and environmental data; the historical process parameters include tension values, laying speeds, and temperature compensation coefficients under different material systems; based on the material system and geometric characteristics of the components to be laid, comparing the process knowledge base to determine the retrieval results, and sorting the retrieval results based on a preset similarity algorithm; and generating a pre-laying strategy based on the sorting results.

[0014] In a second aspect, an embodiment of the present application further provides a dynamic optimization device for an automatic fiber placement path of a composite material, the device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: obtain a three-dimensional model of a component to be laid, and obtain surface curvature distribution characteristics and fiber placement angle constraints based on the three-dimensional model; wherein the fiber placement angle constraints are dynamically corrected according to environmental data and material data of the component to be laid, the environmental data including temperature data and humidity data, and the material data including resin viscoelasticity data and fiber impregnation state data ; Based on a preset path planning algorithm, the surface curvature distribution characteristics are processed to generate an initial fiber placement path; based on a preset tension mapping table and temperature compensation coefficient, the fiber placement head is driven to perform reverse pre-tension control; wherein, the reverse pre-tension value is positively correlated with the square of the real-time placement speed of the fiber placement head; based on the polarized laser polarimeter, the actual fiber orientation data is obtained according to a preset sampling period, and the fiber angle deviation of the actual fiber orientation data is extracted; based on a preset Bayesian optimization algorithm, the fiber angle deviation and the resin viscoelasticity data are processed to dynamically correct the placement path and generate an update instruction; wherein, the update instruction includes a three-dimensional position compensation vector and a tension compensation coefficient; the spatial position and tension of the fiber placement head are adjusted according to the update instruction.

[0015] In a third aspect, the embodiment of the present application further provides a non-volatile computer storage medium for dynamic optimization of the automatic fiber placement path of composite materials, which stores computer executable instructions, characterized in that the computer executable instructions are configured to: obtain a three-dimensional model of a component to be laid, and obtain surface curvature distribution characteristics and fiber placement angle constraints based on the three-dimensional model; wherein the fiber placement angle constraints are dynamically corrected according to environmental data and material data of the component to be laid, the environmental data including temperature data and humidity data, and the material data including resin viscoelasticity data and fiber infiltration state data; process the surface curvature distribution characteristics based on a preset path planning algorithm to generate An initial fiber placement path is formed; based on a preset tension mapping table and a temperature compensation coefficient, the fiber placement head is driven to perform reverse pre-tension control; wherein, the reverse pre-tension value is positively correlated with the square of the real-time placement speed of the fiber placement head; actual fiber orientation data is acquired according to a preset sampling period based on the polarization laser polarimeter, and the fiber angle deviation of the actual fiber orientation data is extracted; based on a preset Bayesian optimization algorithm, the fiber angle deviation and the resin viscoelasticity data are processed to dynamically correct the placement path and generate an update instruction; wherein, the update instruction includes a three-dimensional position compensation vector and a tension compensation coefficient; and the spatial position and tension of the fiber placement head are adjusted according to the update instruction.

[0016] The embodiments of the present application provide a method, device and medium for dynamic optimization of the automatic fiber placement path of composite materials, which realizes dynamic correction of the fiber placement angle by integrating multi-source heterogeneous data, and significantly improves the placement accuracy and efficiency of complex curved surface components. The method uses a path planning algorithm to generate the initial fiber placement path, and combines it with a reverse pre-tension control strategy to effectively compensate for the influence of temperature fluctuations on tension. The fiber orientation data is collected in real time using a polarized laser interferometer, and the placement path is dynamically corrected in combination with a Bayesian optimization algorithm to generate an update instruction containing a three-dimensional position compensation vector and a tension compensation coefficient, thereby achieving precise posture and tension adjustment of the fiber placement head. In addition, by constructing a process database and combining historical process parameters with material performance data, customized pre-placement strategies are provided for components with different material systems and geometric characteristics, further enhancing the adaptability and intelligence level of the system. In summary, the present application solves the problems of poor dynamic environment adaptability and insufficient multi-objective optimization capabilities of traditional fiber placement methods, and improves placement quality and molding efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 A flow chart of a dynamic optimization method for automatic fiber placement path of composite materials provided in an embodiment of the present application;

[0019] Figure 2 A schematic diagram of the internal structure of a composite material automatic wire placement path dynamic optimization device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0021] The embodiments of the present application provide a method, device and medium for dynamic optimization of the automatic wire laying path of composite materials, which are used to solve the following technical problem: how to achieve dynamic multi-objective wire laying path optimization and real-time feedback control.

[0022] The technical solutions proposed in the embodiments of the present application are described in detail below based on the accompanying drawings.

[0023] Figure 1 This is a flow chart of dynamic optimization of composite material automatic fiber placement path provided by the embodiment of the present application. Figure 1 As shown, the embodiment of the present application provides a dynamic optimization method for an automatic fiber placement path of a composite material, which specifically includes the following steps:

[0024] Step 1: Obtain a three-dimensional model of the component to be laid, and based on the three-dimensional model, obtain surface curvature distribution characteristics and fiber placement angle constraints; wherein the fiber placement angle constraints are dynamically corrected according to environmental data and material data of the component to be laid, the environmental data including temperature data and humidity data, and the material data including resin viscoelasticity data and fiber impregnation state data.

[0025] An accurate three-dimensional model of the component to be laid is obtained through digital means, and on this basis, its surface curvature distribution characteristics are analyzed. At the same time, the angle constraints of fiber placement are dynamically determined according to environmental conditions and material properties.

[0026] First, a computer-aided design (CAD) model of the component to be laid is obtained using 3D scanning technology or directly from the design department. This model should contain complete geometric information of the component and serve as the basis for subsequent analysis.

[0027] Based on the three-dimensional model, mathematical methods are used to calculate the curvature distribution of the surface, including Gaussian curvature and mean curvature. These curvature characteristics reflect the degree of bending and directionality of the component surface.

[0028] Dynamically adjust the allowable fiber placement angle range based on the component's environmental data (e.g., temperature, humidity) and material data (e.g., resin viscoelasticity, fiber impregnation). Changes in these data can affect the fiber-matrix bond and, consequently, the overall performance of the component.

[0029] Step 11: Scan the component to be placed based on a preset CT machine to obtain CT scan data.

[0030] An industrial CT scanner is used to perform a full-scale scan of the components to be laid, obtaining detailed image data of their internal structure. CT scanning technology can provide non-destructive internal structural information, which is particularly important for components with complex structures.

[0031] Step 12: Process the CT scan data and the CAD model of the component to be laid based on a multi-source heterogeneous data fusion algorithm to construct a three-dimensional model.

[0032] The CT scan data is fused with the original CAD model data, and the differences between the two are automatically matched and calibrated using an algorithm to construct a more accurate three-dimensional model that includes internal structure information.

[0033] Step 13: extracting Gaussian curvature, mean curvature and principal curvature directions on the three-dimensional model based on a preset local surface fitting algorithm to determine surface curvature distribution characteristics.

[0034] Key points or areas are selected on the 3D model, and the local surface fitting algorithm is applied to calculate the curvature characteristics of these points or areas, including Gaussian curvature, mean curvature and principal curvature direction.

[0035] Step 14: Correcting the allowable range of the fiber placement angle based on the temperature data and the humidity data in the environmental data to determine the fiber placement angle constraint; wherein the allowable range is nonlinearly associated with the extreme value region in the curvature characteristic map.

[0036] Monitor and record the temperature and humidity of the placement environment in real time, and adjust the allowable range of fiber placement angles based on this data. Changes in temperature and humidity can affect the resin's curing speed and fiber wettability, which in turn affects placement quality.

[0037] In a specific example, the design department first obtains a CAD model of the composite component to be laid. The actual component is then scanned and verified using 3D scanning technology to ensure the model's accuracy. An industrial CT scanner is used to perform a full-scale scan of the component to obtain internal structural data. A multi-source heterogeneous data fusion algorithm is then applied to fuse the CT scan data with the CAD model data to construct a precise 3D model containing internal structural information. Key points or regions are selected on the fused 3D model, and a local surface fitting algorithm is applied to calculate the Gaussian curvature, mean curvature, and principal curvature directions, generating a surface curvature distribution characteristic map. The placement environment's temperature and humidity data are monitored and recorded in real time, and material data such as resin viscoelasticity and fiber impregnation status are analyzed to provide a basis for adjusting the fiber placement angle. Based on the environmental and material data, the allowable range of the fiber placement angle is dynamically adjusted. Specifically, the extreme value regions in the curvature characteristic map are considered to adjust the placement angle to accommodate the complex shape of the component surface.

[0038] Step 2: Process the surface curvature distribution characteristics based on a preset path planning algorithm to generate an initial wire laying path.

[0039] Through the path planning algorithm, combined with the surface curvature distribution characteristics extracted previously, the initial path for automatic fiber placement of composite materials is generated.

[0040] An intelligent path planning algorithm is used that automatically calculates the optimal path from the starting point to the end point, taking into account changes in surface curvature. This algorithm is typically based on graph search, heuristic search, or genetic algorithms, and can find a satisfactory path in complex curved environments.

[0041] Using the previously extracted surface curvature distribution features as input, the path planning algorithm adjusts the path calculation method based on these features to ensure that the path can adapt to changes in the surface and avoid fiber breakage or wrinkling during the laying process.

[0042] After processing by the path planning algorithm, one or more initial fiber placement paths are generated. These paths are the basis for subsequent optimization and need to meet basic fiber continuity and placeability requirements.

[0043] Step 21: Path exploration is performed in the surface curvature distribution feature based on a preset random sampling algorithm to generate candidate paths that meet the fiber continuity and placeability constraints.

[0044] A random sampling technique, such as Rapid Randomized Exploration Trees (RRT) or Probabilistic Roadmaps (PRM), is used to explore paths within the curvature distribution of the surface. This algorithm can quickly find feasible path solutions in high-dimensional spaces.

[0045] During path exploration, the algorithm considers fiber continuity and placeability constraints to ensure the generated path meets the requirements of the actual fiber placement process. For example, the path must be smooth and continuous without sharp turns or breaks. Through random sampling, a set of candidate paths that meet fiber continuity and placeability constraints are generated. These paths serve as the basis for subsequent optimization.

[0046] Step 22: Construct a cost function based on the resin viscoelastic parameters in the material data. The cost function includes optimization objectives for path length, curvature change rate, and wetting quality. Resin viscoelastic parameters, such as viscosity and relaxation time, are obtained from the material data. These parameters reflect the resin's fluidity and curing characteristics during the fiber placement process.

[0047] Based on the viscoelastic parameters of the resin, a cost function is constructed to evaluate the quality of candidate paths. The cost function usually includes multiple optimization objectives, such as path length, curvature change rate, and wetting quality.

[0048] Path length optimization goal: Aims to reduce the fiber laying length, reduce material consumption and manufacturing costs.

[0049] Curvature change rate optimization goal: aims to make the curvature change of the path smoother and reduce the stress and deformation of the fiber during the laying process.

[0050] Wetting quality optimization goal: Aims to improve the wetting effect of fibers in the resin and ensure the performance and quality of the composite material.

[0051] Step 23: Adjust the weight coefficients of multiple optimization objectives in the cost function according to the feedback of the infiltration state data.

[0052] Real-time monitoring of the wetting state during the fiber placement process, such as the contact angle between the fiber and the resin and the wetting speed, reflects the fiber’s wetting effect in the resin and the curing process.

[0053] Based on feedback from wetting status data, the weight coefficients of multiple optimization objectives in the cost function are dynamically adjusted. For example, if wetting is poor, the weight of the wetting quality optimization objective is increased, directing the algorithm's focus to fiber wetting. By adjusting the weight coefficients, a balance is achieved between multiple optimization objectives. This helps improve fiber placement quality and efficiency while satisfying fiber continuity and placeability constraints.

[0054] Step 24: Determine the initial wire laying path based on the weight coefficient.

[0055] The adjusted weight coefficients are applied to the cost function to evaluate and rank the candidate paths. The size of the weight coefficient determines the importance of each optimization objective in path selection.

[0056] Based on the evaluation results, the optimal candidate path is selected as the initial fiber placement path. This path satisfies fiber continuity and placeability constraints while also taking into account multiple factors such as resin viscoelasticity, curvature change rate, and impregnation quality, forming the foundation for subsequent fiber placement processes.

[0057] In a specific example, 3D scanning technology and surface fitting algorithms are first used to extract the surface curvature distribution characteristics of the component to be placed, including Gaussian curvature and mean curvature. Based on a pre-set path planning algorithm and random sampling algorithm, path exploration is performed within the surface curvature distribution characteristics to generate a set of candidate paths that meet fiber continuity and placeability constraints. Based on the resin viscoelastic parameters in the material data, a cost function is constructed that incorporates multiple optimization objectives: path length, curvature change rate, and impregnation quality. Real-time monitoring of the impregnation state data during the fiber placement process is performed, and the weight coefficients of the multiple optimization objectives in the cost function are dynamically adjusted based on the feedback to achieve a balance between the optimization objectives. The adjusted weight coefficients are applied to the cost function to evaluate and rank the candidate paths, and the optimal candidate path is selected as the initial fiber placement path. Based on this initial fiber placement path, further path optimization is performed, considering additional constraints and optimization objectives. Finally, the optimized fiber placement path is input into the automatic fiber placement equipment for execution.

[0058] Step 3: Based on a preset tension mapping table and a temperature compensation coefficient, the placement head is driven to perform reverse pre-tension control; wherein the reverse pre-tension value is positively correlated with the square of the real-time placement speed of the placement head.

[0059] By precisely controlling the tension of the placement head, the stability and quality of the composite material during placement are ensured. Reverse pre-tension control is an advanced tension control strategy that takes into account the real-time placement speed of the placement head and the impact of ambient temperature on material properties.

[0060] The tension mapping table is a pre-defined table that contains the corresponding pre-tension values under different layup speeds, temperatures, and material viscoelastic conditions. This table is based on extensive experimental data and experience and provides the basis for reverse pre-tension control.

[0061] Because changes in ambient temperature can affect the viscoelasticity and placement performance of the material, the pretension value needs to be adjusted using a temperature compensation coefficient. This coefficient is calculated based on real-time temperature data and material performance parameters.

[0062] The reverse pretension value is positively correlated with the square of the placement speed: This is based on experimental observations: the faster the placement speed, the greater the pretension required to maintain material stability. This positive correlation ensures that the appropriate pretension can be applied at different placement speeds.

[0063] Step 31: construct a four-dimensional mapping table; wherein the four-dimensional mapping table includes tension, speed, temperature, and viscoelasticity.

[0064] The four-dimensional mapping table is a table containing four dimensions: tension, velocity, temperature, and viscoelasticity. Each dimension corresponds to a parameter, and these parameters together determine the magnitude of the pretension.

[0065] First, through experiments and data analysis, the relationships between tension, speed, temperature, and viscoelasticity under different conditions were determined. Then, these relationships were organized into a table to form a four-dimensional mapping table.

[0066] Step 32: Import the real-time placement speed of the fiber placement head and the temperature data in the environmental data into a preset neural network model to predict the temperature compensation coefficient.

[0067] The neural network model is a pre-trained model that can predict the corresponding temperature compensation coefficient based on the input placement speed and temperature data.

[0068] The real-time placement speed of the wire placement head and the temperature data in the environmental data are imported into the neural network model. The model will predict the temperature compensation coefficient based on these data, providing a basis for subsequent pre-tension control.

[0069] Step 33: Determine the reverse pretension value based on the four-dimensional mapping table and the temperature invariant coefficient.

[0070] According to the relationship between tension and speed in the four-dimensional mapping table and the predicted temperature compensation coefficient, the reverse pre-tension value under the current conditions is determined.

[0071] Step 34: driving the wire placement head based on the reverse pre-tension value.

[0072] The determined reverse pre-tension value is input into the control system of the wire laying head, driving the wire laying head to lay the wire according to the preset tension.

[0073] In a specific case summary, taking the dynamic optimization of composite material automatic fiber placement path as an example, the specific implementation steps are as follows:

[0074] Construct a four-dimensional mapping table, including the four dimensions of tension, velocity, temperature, and viscoelasticity.

[0075] Train a neural network model to predict the temperature compensation coefficient.

[0076] Collect the real-time placement speed of the wire placement head.

[0077] Collect temperature data from environmental data.

[0078] The real-time placement speed and temperature data are imported into the neural network model to predict the temperature compensation coefficient.

[0079] According to the four-dimensional mapping table and the predicted temperature compensation coefficient, the reverse pretension value under the current conditions is determined.

[0080] The reverse pre-tension value is input into the control system of the wire laying head, driving the wire laying head to lay the wire according to the preset tension.

[0081] During the placement process, the tension and speed changes of the wire placement head, as well as the changes in ambient temperature, are monitored in real time.

[0082] According to the changes, the parameters of the four-dimensional mapping table and the neural network model are adjusted in time to optimize the reverse pretension control effect.

[0083] Step 4: acquiring actual fiber orientation data based on the polarization laser polarimeter according to a preset sampling period, and extracting the fiber angle deviation of the actual fiber orientation data.

[0084] The polarization laser polarimeter is used to obtain the fiber orientation data of the composite material laying process in real time and accurately, and further extract the fiber angle deviation, providing key information for subsequent dynamic path optimization.

[0085] A polarization laser polarimeter is a precision instrument that uses the properties of polarized light to measure the orientation of fibers on an object's surface. It emits polarized laser light and receives reflected light signals, analyzing the changes in these signals to infer the fiber's orientation.

[0086] To ensure that the acquired fiber orientation data has sufficient temporal resolution, a reasonable sampling period needs to be set. This period should be determined based on the fiber placement speed, fiber material properties, and required control accuracy.

[0087] The data collected by the polarization laser polarimeter according to the preset sampling period includes the fiber's orientation information at each moment. This data is the basis for subsequent analysis of fiber angle deviation.

[0088] By processing actual fiber orientation data, the fiber's angular deviation from the ideal orientation is extracted. This deviation is an important indicator for evaluating fiber placement quality and the basis for dynamic path optimization.

[0089] Step 41: Calculate the azimuth and pitch angles of the fiber orientation based on a preset polarized light interference fringe analysis algorithm.

[0090] The polarized light interference fringe analysis algorithm is used to analyze the optical signal collected by a polarized laser polarimeter to determine the azimuth and elevation angles of the fiber's orientation. Based on the principle of polarized light interference, the algorithm infers the fiber's orientation by analyzing the shape and positional characteristics of the interference fringes.

[0091] The angle between the projection of a fiber on a horizontal plane and a reference direction. It is an important parameter for describing the horizontal orientation of the fiber. The angle between the fiber and the horizontal plane. It is an important parameter for describing the degree of vertical inclination of the fiber.

[0092] The light signal collected by the polarization laser polarimeter is input into the polarization light interference fringe analysis algorithm. The algorithm will calculate the azimuth and pitch angles of the fiber based on the preset model and solution method.

[0093] Step 42: Performing spatiotemporal joint noise reduction processing on the azimuth and pitch angle data based on a preset extended Kalman filter algorithm to determine the fiber angle deviation; wherein the extended Kalman filter algorithm includes state prediction, covariance update, and measurement update.

[0094] The Extended Kalman Filter (EKF) algorithm is an algorithm for state estimation of nonlinear systems. It suppresses noise and enhances signals by modeling the system in state space and using observation data to estimate and update the system state.

[0095] In the extended Kalman filter algorithm, the system's dynamic model is used to predict the state at the next moment. This prediction is calculated based on the current state and system input.

[0096] To reflect the uncertainty of the predicted state, the state covariance matrix needs to be updated. This matrix describes the error range of the state estimate and is an important basis for subsequent measurement updates.

[0097] When new observations arrive, the Extended Kalman Filter uses them to modify the predicted state, obtaining a more accurate state estimate. Simultaneously, the state covariance matrix is updated to reflect the corrected uncertainty.

[0098] The Extended Kalman Filter (EKF) algorithm considers both temporal and spatial information when denoising azimuth and elevation data. By combining historical and current observations, the algorithm effectively suppresses noise, improving data accuracy and reliability.

[0099] After noise reduction processing using the extended Kalman filter algorithm, more accurate azimuth and pitch angle data are obtained. By comparing these data with the ideal direction, the fiber angular deviation is determined.

[0100] In a specific case summary,

[0101] Configure the polarization laser polarimeter and set a reasonable sampling period. Prepare the polarization light interference fringe analysis algorithm and the extended Kalman filter algorithm. Start the polarization laser polarimeter and collect the actual fiber orientation data according to the preset sampling period. Input the collected light signal into the polarization light interference fringe analysis algorithm to calculate the azimuth and pitch angles of the fiber. Input the calculated azimuth and pitch angle data into the extended Kalman filter algorithm for joint time-space domain noise reduction. Determine the fiber angle deviation based on the azimuth and pitch angle data after noise reduction. Adjust the motion trajectory and speed of the fiber placement head based on the fiber angle deviation to optimize the fiber placement path. Monitor the fiber orientation data in real time and continuously adjust the optimization strategy to ensure the quality of fiber placement.

[0102] Step 5: Process the fiber angle deviation and the resin viscoelasticity data based on a preset Bayesian optimization algorithm to dynamically correct the placement path and generate an update instruction; wherein the update instruction includes a three-dimensional position compensation vector and a tension compensation coefficient.

[0103] Through the Bayesian optimization algorithm, the fiber angle deviation, resin viscoelastic data and placement efficiency are comprehensively considered to dynamically correct the placement path of the composite material and generate corresponding update instructions to ensure the accuracy and efficiency of the fiber placement process.

[0104] The Bayesian optimization algorithm is a global optimization algorithm particularly suitable for expensive and uncertain function optimization problems. In the composite fiber placement process, due to the complexity of fiber angle deviation and resin viscoelasticity, the Bayesian optimization algorithm can effectively find the optimal placement path.

[0105] As mentioned above, it is obtained by real-time measurement using a polarization laser polarimeter device, reflecting the deviation between the actual orientation of the fiber and the ideal orientation.

[0106] Resin viscoelasticity data, which measures the viscosity and elastic behavior of a resin at specific temperatures and pressures, significantly impacts the quality and performance of composite materials. Update instructions, generated based on the results of a Bayesian optimization algorithm, adjust the placement head's trajectory, tension, and speed parameters to optimize the placement path.

[0107] The three-dimensional position compensation vector is a vector that includes position correction, attitude adjustment and speed compensation, and is used to accurately control the movement of the fiber placement head.

[0108] The tension compensation coefficient is used to adjust the fiber tension during the laying process to ensure the flatness and tight fit of the fiber.

[0109] Step 51: construct a three-objective optimization function; wherein the three-objective optimization function includes minimizing fiber angle deviation, optimizing resin viscoelastic data, and maximizing placement efficiency.

[0110] The three-objective optimization function comprehensively considers minimizing fiber angle deviation, optimizing resin viscoelasticity, and maximizing placement efficiency. This function forms the basis of the Bayesian optimization algorithm, guiding it to find the optimal solution within the search space.

[0111] Minimizing fiber angle deviation: The goal is to make the actual orientation of the fibers as close as possible to the ideal orientation to reduce errors between plies and improve the performance of the composite material.

[0112] Optimization of resin viscoelastic data: The goal is to maintain the best viscosity and elastic behavior of the resin during the placement process to ensure the molding quality and performance of the composite material.

[0113] Maximizing placement efficiency: The goal is to increase the efficiency of the wire placement process and reduce production time and costs.

[0114] Step 52: Model the three-objective optimization function based on a preset Gaussian process model, and introduce Pareto frontier analysis to generate a Bayesian optimization algorithm; wherein the Pareto frontier analysis is used to find the optimal solution set in the multi-objective optimization problem.

[0115] The Gaussian process model is a non-parametric probabilistic model that can be used to model and predict complex functions. In Bayesian optimization, the Gaussian process model is used to model three-objective optimization functions and predict the function's value under different parameters.

[0116] In multi-objective optimization problems, due to potential conflicts between objectives, it is impossible to find a single solution that satisfies all objectives simultaneously. Pareto front analysis is a method used to find optimal solutions to multi-objective optimization problems. It analyzes the trade-offs between different objectives to find a set of optimal solutions that are non-dominated.

[0117] Based on the Gaussian process model and Pareto front analysis, a Bayesian optimization algorithm is generated. This algorithm can effectively find the optimal solution that satisfies the three-objective optimization function in the search space.

[0118] Step 53: Generate the three-dimensional position compensation vector and tension compensation coefficient based on the Bayesian optimization algorithm; wherein the compensation vector includes a position correction amount, a posture adjustment amount, and a speed compensation amount.

[0119] The Bayesian optimization algorithm generates a three-dimensional position compensation vector based on the current position, attitude, and speed of the fiber placement head, as well as fiber angle deviation and resin viscoelasticity data. This vector, which includes position corrections, attitude adjustments, and speed compensation, is used to precisely control the movement of the fiber placement head.

[0120] The Bayesian optimization algorithm also generates a tension compensation coefficient based on the fiber tension and placement requirements. This coefficient is used to adjust the fiber tension during placement to ensure fiber flatness and tight fit.

[0121] Step 54: Determine an update instruction based on the three-dimensional position compensation vector and the tension compensation coefficient.

[0122] Based on the three-dimensional position compensation vector and tension compensation coefficient generated by the Bayesian optimization algorithm, an update instruction is determined. This instruction contains the specific parameters and values that need to be adjusted by the fiber placement head to dynamically correct the placement path.

[0123] Applying update commands to the fiber placement control system adjusts the placement head's trajectory, tension, and speed parameters to optimize the placement path. By continuously applying update commands, the optimal placement path is gradually approached, improving the composite material's molding quality and performance.

[0124] In a specific example:

[0125] Configure a polarized laser polarimeter and resin viscoelasticity measurement equipment to ensure real-time acquisition of fiber angle deviation and resin viscoelasticity data. Construct a three-objective optimization function, including minimizing fiber angle deviation, optimizing resin viscoelasticity data, and maximizing placement efficiency. Model the three-objective optimization function based on the Gaussian process model, and introduce Pareto front analysis to generate a Bayesian optimization algorithm. Collect fiber angle deviation and resin viscoelasticity data in real time. Input the collected data into the Bayesian optimization algorithm for processing and analysis. Based on the Bayesian optimization algorithm, generate a three-dimensional position compensation vector and tension compensation coefficient. Determine the update instruction based on the generated three-dimensional position compensation vector and tension compensation coefficient. Apply the update instruction to the fiber placement control system to adjust the motion trajectory, tension, and speed parameters of the fiber placement head. Monitor the fiber placement process in real time, and continuously adjust and optimize the update instruction based on feedback data.

[0126] Step 6: Adjust the spatial position and tension of the fiber placement head according to the update instruction.

[0127] According to the update instructions generated by the Bayesian optimization algorithm, the spatial position (i.e., location and orientation) and tension of the fiber placement head are precisely adjusted to ensure the accuracy and stability of the composite fiber placement process.

[0128] The update instructions are generated by processing the fiber angle deviation and resin viscoelasticity data through the Bayesian optimization algorithm, and include the three-dimensional position compensation vector for adjusting the spatial posture of the fiber placement head and the tension compensation coefficient for adjusting the tension.

[0129] Spatial position refers to the position and direction of the fiber placement head in three-dimensional space. It is a key parameter in the composite fiber placement process and directly affects the quality and performance of the layer.

[0130] Tension is the pulling force on the fiber during the laying process, which has an important impact on the flatness and tight fit of the fiber.

[0131] Step 61: Convert the three-dimensional position compensation vector into a joint space trajectory based on a preset robot inverse kinematics model, and optimize the joint motion trajectory based on a preset weighted least squares method; wherein the weighted least squares method is used to solve the optimal joint motion trajectory under multiple constraints.

[0132] The robot's inverse kinematics model is a mathematical model used to convert the motion of an end effector (such as a wire placement head) in Cartesian space (i.e., three-dimensional space) into motion in the robot's joint space. Through the inverse kinematics model, the three-dimensional position compensation vector is converted into the required rotation angle or displacement of each robot joint.

[0133] In specific implementation, first, based on the current position and target position of the wire laying head (determined by the three-dimensional position compensation vector), the inverse kinematics model is used to calculate the target angle or displacement that each joint of the robot needs to achieve.

[0134] Joint space trajectories refer to the movement of each robot's joints over time. By optimizing joint space trajectories, the robot's motion is smooth and accurate, avoiding jitter or shock.

[0135] The weighted least squares method is a mathematical optimization method used to find the optimal solution under multiple constraints. In robot trajectory optimization, the weighted least squares method considers multiple constraints such as joint velocity, acceleration, and torque to find the optimal joint trajectory.

[0136] In practice, the objective function of the weighted least squares method is first constructed based on the robot's dynamic model and kinematic constraints. Then, a numerical optimization algorithm (such as gradient descent or Newton's method) is used to find the optimal solution to the objective function, i.e., the optimal joint motion trajectory.

[0137] Step 62: Adjust the tension output based on the tension compensation coefficient.

[0138] The tension compensation coefficient is generated by the Bayesian optimization algorithm as described above and is used to adjust the fiber tension coefficient during the fiber placement process.

[0139] Adjust the tension output According to the tension compensation coefficient, adjust the tension control system in the fiber laying machine to change the tension on the fiber.

[0140] In practice, the target tension value is first calculated based on the tension compensation coefficient. Then, a tension control system (such as a tension sensor or tension controller) monitors and adjusts the fiber tension in real time to maintain it near the target tension value. This ensures that the fibers remain flat and tightly fitted during placement, improving the quality and performance of the composite material.

[0141] In a specific example, the dynamic optimization of the automated fiber placement path for composite materials is implemented as follows: A polarized laser polarimeter and resin viscoelasticity measurement equipment are configured to ensure real-time acquisition of fiber angle deviation and resin viscoelasticity data. A three-objective optimization function is constructed, including minimizing fiber angle deviation, optimizing resin viscoelasticity data, and maximizing placement efficiency. This three-objective optimization function is modeled based on a Gaussian process model, and Pareto front analysis is introduced to generate a Bayesian optimization algorithm. A robot inverse kinematics model and weighted least squares optimization method are established. Fiber angle deviation and resin viscoelasticity data are collected in real time. The collected data is input into the Bayesian optimization algorithm for processing and analysis, generating update instructions (including a three-dimensional position compensation vector and a tension compensation coefficient). Based on the robot inverse kinematics model, the three-dimensional position compensation vector is converted into a joint spatial trajectory. The joint motion trajectory is optimized using weighted least squares to ensure smooth and accurate robot movement. The spatial position of the fiber placement head is adjusted based on the optimized joint motion trajectory. The target tension value is calculated based on the tension compensation coefficient. The tension control system monitors and adjusts the fiber tension in real time to maintain it near the target tension value. During the placement process, fiber angle deviation, resin viscoelasticity data, and the spatial position and tension of the placement head are monitored in real time. Based on this monitoring data, instructions are continuously adjusted, optimized, and updated to ensure the accuracy and stability of the placement process.

[0142] This application also includes the following methods:

[0143] A1. Construct a process database; wherein the process knowledge base includes historical process parameters, material performance data, and environmental data; the historical process parameters include tension values, placement speeds, and temperature compensation coefficients under different material systems.

[0144] The process database is an integrated information system used to store and manage various data related to the composite fiber placement process. It includes historical process parameters, material performance data, and environmental data, providing comprehensive data support for process optimization.

[0145] Historical process parameters refer to the parameters used during past fiber placement processes for different material systems and component geometries. These parameters, including but not limited to tension, placement speed, and temperature compensation coefficient, serve as a crucial reference for process optimization.

[0146] Tension refers to the amount of pulling force applied to the fiber during the laying process. Different material systems have different tension requirements. Proper tension setting ensures fiber flatness and a tight fit.

[0147] The placement speed refers to the speed at which the wire placement head moves across the component surface. The selection of placement speed requires a comprehensive consideration of material properties, equipment capabilities, and production efficiency.

[0148] Temperature compensation coefficient: Because changes in ambient temperature may affect material properties and fiber placement results, temperature compensation needs to be adjusted based on actual conditions. The temperature compensation coefficient is a parameter used to adjust the temperature setting during the fiber placement process.

[0149] Material performance data, including the mechanical, thermal, and chemical stability of composite materials, are crucial for selecting process parameters and developing fiber placement strategies.

[0150] Refers to the environmental conditions during the fiber placement process, such as temperature, humidity, and air pressure. Environmental data has a certain impact on the fiber placement results and therefore needs to be considered in the process database.

[0151] During specific implementation, by collecting and analyzing past wire laying cases, relevant process parameters, material performance data and environmental data are extracted, and then they are organized and stored according to a certain data structure and format to form a process database.

[0152] A2. Based on the material system and geometric features of the component to be laid, the process knowledge base is compared to determine the search results, and the search results are sorted based on a preset similarity algorithm.

[0153] The material system and geometric characteristics of the component to be laid refer to the material type, number of layers, layup sequence, and shape and size of the component to be laid. These characteristics are key to selecting process parameters and formulating wire placement strategies.

[0154] Compare the material system and geometric characteristics of the components to be laid with historical cases in the process database to find similar cases as references.

[0155] A collection of similar historical cases obtained by comparing the process knowledge base. These cases contain similar material systems, geometric features, and corresponding process parameters as the component to be laid.

[0156] It is an algorithm used to evaluate the degree of similarity between two objects. In this step, the similarity algorithm is used to sort the search results, placing the most similar cases at the top for subsequent selection and optimization of process parameters.

[0157] In practice, the process database is first searched for similar historical cases based on the material system and geometric characteristics of the component to be laid. The search results are then evaluated and ranked using a pre-defined similarity algorithm. This algorithm considers similarities in material system, geometric characteristics, and process parameters, and ranks the search results by calculating a similarity score.

[0158] A3. Generate a pre-layout strategy based on the sorting results.

[0159] The sorting result refers to the case set obtained by sorting the search results using a similarity algorithm, which contains the historical cases that are most similar to the component to be laid.

[0160] The pre-placement strategy refers to the process parameters and placement strategy selected based on the sorting results, which guide the actual placement process. The pre-placement strategy includes specific parameters such as tension setting, placement speed, temperature compensation coefficient, as well as the placement path and layer sequence.

[0161] In implementation, the most similar cases in the sorted results are first analyzed to extract the process parameters and placement strategies used. Then, based on the specific conditions and actual requirements of the component to be placed, these extracted process parameters and placement strategies are adjusted and optimized to generate a pre-placement strategy suitable for the component to be placed. Finally, this pre-placement strategy is input into the placement equipment to guide the actual placement process.

[0162] The above is an embodiment of the method proposed in this application. Based on the same inventive concept, this application also provides a composite material automatic wire laying path dynamic optimization device, the structure of which is as follows: Figure 2 shown.

[0163] Figure 2 This is a schematic diagram of the internal structure of a composite material automatic fiber placement path dynamic optimization device provided in an embodiment of the present application. Figure 2 As shown, the equipment includes:

[0164] at least one processor 201;

[0165] and, a memory 202 communicatively coupled to the at least one processor;

[0166] The memory 202 stores instructions that can be executed by at least one processor, and the instructions are executed by the at least one processor 201 to enable the at least one processor 201 to:

[0167] A three-dimensional model of a component to be laid is obtained, and based on the three-dimensional model, surface curvature distribution characteristics and fiber placement angle constraints are obtained; wherein the fiber placement angle constraints are dynamically corrected according to environmental data and material data of the component to be laid, wherein the environmental data includes temperature data and humidity data, and the material data includes resin viscoelasticity data and fiber infiltration state data; the surface curvature distribution characteristics are processed based on a preset path planning algorithm to generate an initial fiber placement path; based on a preset tension mapping table and a temperature compensation coefficient, the fiber placement head is driven to perform reverse pre-tension control; wherein the reverse pre-tension value is positively correlated with the square of the real-time placement speed of the fiber placement head; actual fiber orientation data is obtained according to a preset sampling period based on the polarization laser polarimeter, and fiber angle deviations of the actual fiber orientation data are extracted; the fiber angle deviations and the resin viscoelasticity data are processed based on a preset Bayesian optimization algorithm to dynamically correct the placement path and generate update instructions; wherein the update instructions include a three-dimensional position compensation vector and a tension compensation coefficient; the spatial position and tension of the fiber placement head are adjusted according to the update instructions.

[0168] Some embodiments of the present application provide corresponding Figure 1 A non-volatile computer storage medium for dynamic optimization of composite material automatic wire placement path, storing computer executable instructions, wherein the computer executable instructions are set to:

[0169] A three-dimensional model of a component to be laid is obtained, and based on the three-dimensional model, surface curvature distribution characteristics and fiber placement angle constraints are obtained; wherein the fiber placement angle constraints are dynamically corrected according to environmental data and material data of the component to be laid, wherein the environmental data includes temperature data and humidity data, and the material data includes resin viscoelasticity data and fiber infiltration state data; the surface curvature distribution characteristics are processed based on a preset path planning algorithm to generate an initial fiber placement path; based on a preset tension mapping table and a temperature compensation coefficient, the fiber placement head is driven to perform reverse pre-tension control; wherein the reverse pre-tension value is positively correlated with the square of the real-time placement speed of the fiber placement head; actual fiber orientation data is obtained according to a preset sampling period based on the polarization laser polarimeter, and fiber angle deviations of the actual fiber orientation data are extracted; the fiber angle deviations and the resin viscoelasticity data are processed based on a preset Bayesian optimization algorithm to dynamically correct the placement path and generate update instructions; wherein the update instructions include a three-dimensional position compensation vector and a tension compensation coefficient; the spatial position and tension of the fiber placement head are adjusted according to the update instructions.

[0170] The various embodiments in this application are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other. Each embodiment focuses on the differences between the other embodiments. In particular, the IoT device and media embodiments are described briefly because they are generally similar to the method embodiments. For relevant portions, refer to the description of the method embodiments.

[0171] The system and medium provided in the embodiments of the present application correspond one-to-one to the method. Therefore, the system and medium also have similar beneficial technical effects to their corresponding methods. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.

[0172] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage) that contain computer-usable program code.

[0173] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0174] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0175] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0176] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0177] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory forms such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0178] Computer-readable media includes permanent and non-permanent, removable and non-removable media implemented by any method or technology for information storage. Information is computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change RAM (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0179] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0180] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application has various modifications and variations. Any modification, replacement, or improvement made within the spirit and principles of the present application should be included within the scope of the claims of the present application.

Claims

1. A dynamic optimization method for an automatic composite material placement path, applied to a placement robot, wherein the placement robot comprises a placement head and a polarization laser interferometer, characterized in that: The method comprises: Obtaining a three-dimensional model of the component to be laid, and obtaining surface curvature distribution characteristics and fiber placement angle constraints based on the three-dimensional model; wherein the fiber placement angle constraints are dynamically modified based on environmental data and material data of the component to be laid, the environmental data including temperature data and humidity data, and the material data including resin viscoelasticity data and fiber impregnation state data; Processing the surface curvature distribution characteristics based on a preset path planning algorithm to generate an initial wire laying path; Based on a preset tension mapping table and a temperature compensation coefficient, the placement head is driven to perform reverse pre-tension control; wherein the reverse pre-tension value is positively correlated with the square of the real-time placement speed of the placement head; Acquiring actual fiber orientation data based on the polarization laser polarimeter according to a preset sampling period, and extracting fiber angle deviations from the actual fiber orientation data; Processing the fiber angle deviation and the resin viscoelasticity data based on a preset Bayesian optimization algorithm to dynamically correct the placement path and generate an update instruction; wherein the update instruction includes a three-dimensional position compensation vector and a tension compensation coefficient; The spatial position and tension of the fiber placement head are adjusted according to the update instruction.

2. The method for dynamic optimization of composite material automatic fiber placement path according to claim 1, characterized in that: Obtaining a three-dimensional model of the component to be laid, and obtaining surface curvature distribution characteristics and fiber placement angle constraints based on the three-dimensional model, specifically including: Scanning the component to be placed based on a preset CT machine to obtain CT scanning data; Processing the CT scan data and the CAD model of the component to be laid based on a multi-source heterogeneous data fusion algorithm to construct a three-dimensional model; Extracting Gaussian curvature, mean curvature and principal curvature directions on the three-dimensional model based on a preset local surface fitting algorithm to determine surface curvature distribution characteristics; The allowable range of the fiber placement angle is corrected based on the temperature data and the humidity data in the environmental data to determine the fiber placement angle constraint; wherein the allowable range is nonlinearly associated with the extreme value region in the curvature characteristic map.

3. The method for dynamic optimization of composite material automatic fiber placement path according to claim 1, characterized in that: The surface curvature distribution characteristics are processed based on a preset path planning algorithm to generate an initial wire laying path, specifically including: Path exploration is performed in the surface curvature distribution features based on a preset random sampling algorithm to generate candidate paths that meet fiber continuity and placeability constraints; Constructing a cost function based on the resin viscoelastic parameters in the material data; wherein the cost function includes a path length optimization target, a curvature change rate optimization target, and an infiltration quality optimization target; Adjusting weight coefficients of multiple optimization objectives in the cost function according to feedback of the infiltration state data; The initial wire laying path is determined based on the size of the weight coefficient.

4. The method for dynamic optimization of composite material automatic fiber placement path according to claim 1, characterized in that: Based on a preset tension mapping table and a temperature compensation coefficient, the placement head is driven to perform reverse pre-tension control, specifically including: Constructing a four-dimensional mapping table; wherein the four-dimensional mapping table includes tension, speed, temperature and viscoelasticity; Importing the real-time placement speed of the fiber placement head and the temperature data in the environmental data into a preset neural network model to predict the temperature compensation coefficient; Determining the reverse pretension value based on the four-dimensional mapping table and the temperature invariant coefficient; The placement head is driven based on the reverse pre-tension value.

5. The method for dynamic optimization of composite material automatic fiber placement path according to claim 1, characterized in that: Acquiring actual fiber orientation data based on the polarization laser polarimeter according to a preset sampling period, and extracting the fiber angle deviation of the actual fiber orientation data, specifically includes: Calculate the azimuth and pitch angles of the fiber orientation based on the preset polarized light interference fringe analysis algorithm; The azimuth and pitch angle data are subjected to joint spatiotemporal noise reduction processing based on a preset extended Kalman filter algorithm to determine the fiber angle deviation; wherein the extended Kalman filter algorithm includes state prediction, covariance update, and measurement update.

6. The method for dynamic optimization of composite material automatic fiber placement path according to claim 1, characterized in that: The fiber angle deviation and the resin viscoelasticity data are processed based on a preset Bayesian optimization algorithm to dynamically correct the placement path and generate an update instruction, specifically including: Constructing a three-objective optimization function; wherein the three-objective optimization function includes minimizing fiber angle deviation, optimizing resin viscoelastic data, and maximizing placement efficiency; The three-objective optimization function is modeled based on a preset Gaussian process model, and Pareto frontier analysis is introduced to generate a Bayesian optimization algorithm; wherein the Pareto frontier analysis is used to find the optimal solution set in the multi-objective optimization problem; Generating the three-dimensional position compensation vector and tension compensation coefficient based on the Bayesian optimization algorithm; wherein the compensation vector includes a position correction amount, a posture adjustment amount, and a speed compensation amount; An update instruction is determined based on the three-dimensional position compensation vector and the tension compensation coefficient.

7. The method for dynamic optimization of composite material automatic fiber placement path according to claim 1, characterized in that: Adjusting the spatial position and tension of the fiber placement head according to the update instruction specifically includes: The three-dimensional position compensation vector is converted into a joint space trajectory based on a preset robot inverse kinematics model, and the joint motion trajectory is optimized based on a preset weighted least squares method; wherein the weighted least squares method is used to solve the optimal joint motion trajectory under multiple constraints; The tension output is adjusted based on the tension compensation factor.

8. The method for dynamic optimization of composite material automatic fiber placement path according to claim 1, characterized in that: The method further comprises: Constructing a process database; wherein the process knowledge base includes historical process parameters, material performance data, and environmental data; the historical process parameters include tension values, placement speeds, and temperature compensation coefficients under different material systems; Based on the material system and geometric characteristics of the component to be laid, the process knowledge base is compared to determine the search results, and the search results are sorted based on a preset similarity algorithm; Generate a pre-layout strategy based on the sorting results.

9. A dynamic optimization device for automatic fiber placement path of composite materials, characterized in that: The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: Obtaining a three-dimensional model of the component to be laid, and obtaining surface curvature distribution characteristics and fiber placement angle constraints based on the three-dimensional model; wherein the fiber placement angle constraints are dynamically modified based on environmental data and material data of the component to be laid, the environmental data including temperature data and humidity data, and the material data including resin viscoelasticity data and fiber impregnation state data; Processing the surface curvature distribution characteristics based on a preset path planning algorithm to generate an initial wire laying path; Based on a preset tension mapping table and a temperature compensation coefficient, the placement head is driven to perform reverse pre-tension control; wherein the reverse pre-tension value is positively correlated with the square of the real-time placement speed of the placement head; Acquiring actual fiber orientation data based on the polarization laser polarimeter according to a preset sampling period, and extracting fiber angle deviations from the actual fiber orientation data; Processing the fiber angle deviation and the resin viscoelasticity data based on a preset Bayesian optimization algorithm to dynamically correct the placement path and generate an update instruction; wherein the update instruction includes a three-dimensional position compensation vector and a tension compensation coefficient; The spatial position and tension of the fiber placement head are adjusted according to the update instruction.

10. A non-volatile computer storage medium for dynamic optimization of composite material automatic fiber placement path, storing computer executable instructions, characterized in that: The computer executable instructions are configured to: Obtaining a three-dimensional model of the component to be laid, and obtaining surface curvature distribution characteristics and fiber placement angle constraints based on the three-dimensional model; wherein the fiber placement angle constraints are dynamically modified based on environmental data and material data of the component to be laid, the environmental data including temperature data and humidity data, and the material data including resin viscoelasticity data and fiber impregnation state data; Processing the surface curvature distribution characteristics based on a preset path planning algorithm to generate an initial wire laying path; Based on a preset tension mapping table and a temperature compensation coefficient, the placement head is driven to perform reverse pre-tension control; wherein the reverse pre-tension value is positively correlated with the square of the real-time placement speed of the placement head; Acquiring actual fiber orientation data based on the polarization laser polarimeter according to a preset sampling period, and extracting fiber angle deviations from the actual fiber orientation data; Processing the fiber angle deviation and the resin viscoelasticity data based on a preset Bayesian optimization algorithm to dynamically correct the placement path and generate an update instruction; wherein the update instruction includes a three-dimensional position compensation vector and a tension compensation coefficient; The spatial position and tension of the fiber placement head are adjusted according to the update instruction.

Images