Control system for layered cutting of composite material

Abstract

The invention relates to the technical field of intelligent cutting, and discloses a composite material layered cutting control system which comprises a multi-modal data analysis module, a multi-physical field simulation planning module, a real-time monitoring module, a core regulation and control module and an optimization execution module. Performing digital image processing on the interlayer interface characteristics of the composite material to obtain digital characteristic parameters; based on the digital characteristic parameters, multi-physics field simulation prediction is conducted on stress distribution and thermal conductivity in the cutting process, and a layered cutting path is obtained; based on the layered cutting path, multi-source data fusion is conducted on vibration characteristics and temperature distribution in the machining process of the composite material, and real-time working condition data is obtained; performing multi-criterion decision fusion on the real-time working condition data to obtain target process parameters; correcting and coding the target process parameters to obtain a cutting instruction of the composite material; the layered cutting control efficiency of the composite material can be improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent cutting technology, and in particular to a control system for layered cutting of composite materials. Background Technology

[0002] In the field of composite material layer cutting, existing control systems often rely on a single data dimension for cutting path planning and process parameter setting, making it difficult to comprehensively integrate the physical property parameters and structural image information of composite materials. When digitally processing the interlayer interface features of composite materials, problems such as incomplete feature extraction and low correlation of material properties often occur. This results in the generated cutting path failing to accurately match the interlayer structural differences of the composite material, easily leading to stress concentration or excessively large heat-affected zones during the cutting process, thereby reducing cutting quality and material utilization, and failing to meet the requirements of high-precision processing.

[0003] Meanwhile, existing technologies lack effective real-time monitoring and dynamic control mechanisms. During the cutting process, most systems can only monitor single operating condition data such as vibration or temperature, failing to achieve deep fusion analysis of multi-source data and making it difficult to accurately reflect real-time changes in operating conditions along the layered cutting path. Furthermore, in the process parameter adjustment stage, a scientific multi-criteria decision-making model has not been established, relying solely on fixed thresholds or empirical values ​​for parameter correction. This results in parameter adjustments lagging behind changes in operating conditions, not only affecting processing efficiency but also potentially exacerbating equipment wear and tear due to insufficient parameter adaptability, increasing production risks and costs. Therefore, improving the processing efficiency of composite materials has become an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a control system for layered cutting of composite materials to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides a control system for layered cutting of composite materials, characterized in that the system includes a multimodal data analysis module, a multiphysics simulation planning module, a real-time monitoring module, a core control module, and an optimization execution module, wherein: The multimodal data parsing module is used to perform digital image processing on the interlayer interface features of the composite material based on the physical property parameters and structural images of the composite material, so as to obtain the digital feature parameters of the composite material. The multiphysics simulation planning module is used to perform multiphysics simulation and prediction of stress distribution and thermal conductivity during the cutting process of the composite material based on the digital feature parameters, so as to obtain the layered cutting path of the composite material. The real-time monitoring module is used to perform multi-source data fusion on the vibration characteristics and temperature distribution of the composite material during processing based on the layered cutting path, so as to obtain real-time working condition data of the layered cutting path. The core control module is used to perform multi-criteria decision fusion on the real-time operating data to obtain the target process parameters of the layered cutting path; The optimization execution module is used to correct and encode the target process parameters to obtain the cutting instructions for the composite material.

[0006] In a preferred embodiment, when the multimodal data parsing module performs digital image processing on the interlayer interface features of the composite material based on the physical property parameters and structural images of the composite material to obtain the digital feature parameters of the composite material, it is specifically used for: Edge contours are extracted from the structural images to obtain interlayer boundary information of the composite material; Based on the physical property parameters of the composite material, the interlayer boundary information is correlated with material properties to obtain the material data of the composite material. The material data is reconstructed in three dimensions to obtain the interlayer structure representation data of the composite material; Multi-dimensional feature fusion is performed on the interlayer structure expression data to obtain the digital feature parameters of the composite material.

[0007] In a preferred embodiment, the multiphysics simulation planning module, based on the digital feature parameters, performs multiphysics simulation prediction of stress distribution and thermal conductivity during the cutting process of the composite material to obtain the layered cutting path of the composite material, specifically for: Based on the digital feature parameters, a framework for the cutting process of the composite material is established to obtain a prediction framework for the composite material. Multi-field coupling behavior analysis was performed on the prediction framework to obtain the thermodynamic response data of the composite material; Based on the thermodynamic response data, the cutting trajectory of the composite material is optimized to obtain the layered cutting path of the composite material.

[0008] In a preferred embodiment, when the multiphysics simulation planning module performs framework establishment for the cutting process of the composite material based on the digital feature parameters to obtain a predictive framework for the composite material, it is specifically used for: The geometric morphological features in the digital feature parameters are used to construct a three-dimensional spatial topology to obtain the spatial structural expression of the composite material. By performing attribute association mapping on the material attribute features in the digital feature parameters, the material attribute relationships of the composite material are obtained; By performing cross-scale correlation between the spatial structure representation and the material properties, the process analysis environment of the composite material is obtained; The structural integrity of the process analysis environment is verified to obtain the prediction framework for the composite material.

[0009] In a preferred embodiment, when the multiphysics simulation planning module performs cutting trajectory optimization on the composite material based on the thermodynamic response data to obtain the layered cutting path of the composite material, it is specifically used for: A potential risk assessment is performed on the stress concentration and thermally affected area distribution in the thermodynamic response data to obtain the risk cutting area of ​​the composite material. The distribution features of the risk cutting area are extracted to obtain the initial cutting trajectory scheme of the composite material; The initial cutting trajectory scheme is continuously optimized to obtain the target cutting trajectory parameters of the composite material; Based on the target cutting trajectory parameters, a layered cutting path for the composite material is generated.

[0010] In a preferred embodiment, when the real-time monitoring module performs multi-source data fusion on the vibration characteristics and temperature distribution during the processing of the composite material based on the layered cutting path to obtain real-time operating condition data of the layered cutting path, it is specifically used for: Based on the layered cutting path, vibration monitoring data and temperature monitoring data during the material processing are collected to obtain vibration signal data and temperature distribution data of the material processing process. The vibration signal data is analyzed for signal characteristics to obtain the vibration signal parameters during the material processing. Thermal field feature analysis is performed on the temperature distribution data to obtain the temperature distribution parameters during the material processing. Multimodal data fusion analysis is performed on the vibration signal parameters and the temperature distribution parameters to obtain real-time operating data of the layered cutting path.

[0011] In a preferred embodiment, when the core control module performs multi-criteria decision fusion on the real-time operating data to obtain the target process parameters of the layered cutting path, it is specifically used for: A multi-dimensional evaluation of the real-time operating condition data is constructed to obtain a benchmark evaluation framework for the real-time operating condition data. Dynamically weight the benchmark evaluation framework to obtain the importance allocation relationship of the benchmark evaluation framework; The importance allocation relationship is evaluated using a multi-objective optimization method to obtain the target process parameters for the layered cutting path.

[0012] In a preferred embodiment, when the core control module performs a multi-dimensional evaluation of the real-time operating data to obtain a benchmark evaluation framework for the real-time operating data, it is specifically used for: Feature data extraction is performed on the real-time operating data to obtain cutting quality feature data, processing efficiency feature data, and equipment status feature data of the real-time operating data; The cutting quality feature data is quantified and integrated to obtain the cutting quantification index of the real-time working condition data. The processing efficiency feature data is fused to obtain the processing efficiency evaluation benchmark of the real-time operating data; The equipment status feature data is quantified to obtain the equipment status quantification index of the real-time operating condition data. An evaluation benchmark is constructed for the cutting quantification index, the processing efficiency evaluation benchmark, and the equipment status quantification index to obtain the benchmark evaluation framework for the real-time operating data.

[0013] In a preferred embodiment, when the core control module performs dynamic weight configuration on the benchmark evaluation framework to obtain the importance allocation relationship of the benchmark evaluation framework, it is specifically used for: Based on the aforementioned benchmark evaluation framework, information entropy data for the evaluation dimensions are generated. The dynamic weighting coefficients of the evaluation dimensions are calculated based on the information entropy data, wherein the calculation formula for the dynamic weighting coefficients is as follows: ; In the formula, The real-time operating condition data is in the first... The weighting coefficients of each evaluation dimension, The real-time operating condition data is in the first... Information entropy value of each evaluation dimension The total number of evaluation dimensions for the real-time operating condition data. The real-time operating condition data is in the first... The information entropy value of each evaluation dimension.

[0014] In a preferred embodiment, when the optimization execution module performs the modification encoding of the target process parameters to obtain the cutting instructions for the composite material, it is specifically used for: The target process parameters are calibrated by parameter standardization to obtain the standardized parameters of the target process parameters; The standardized parameters are encoded to obtain the cutting instruction sequence of the composite material; Logical verification is performed on the cutting instruction sequence to obtain the cutting instructions for the composite material.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention uses a multimodal data analysis module to digitally process the physical property parameters and structural images of composite materials, which can accurately extract interlayer interface features and complete multi-dimensional feature fusion to generate comprehensive and accurate digital feature parameters. This provides high-quality data support for subsequent cutting path planning, effectively ensures the compatibility of the layered cutting path with the interlayer structure of the composite material, and effectively improves cutting accuracy and material utilization. 2. This invention constructs a complete control process of "simulation planning - real-time monitoring - core control - optimized execution". The multi-physics simulation planning module can accurately predict the stress and heat conduction during the cutting process. The real-time monitoring module can integrate multi-source data of vibration and temperature to accurately reflect the working conditions. The core control module generates suitable target process parameters through multi-criteria decision-making. The optimized execution module ensures the accuracy and reliability of the cutting command. The entire system works in concert, effectively improving the processing efficiency of composite material layer cutting, while reducing equipment wear and reducing production risks and costs. Attached Figure Description

[0016] Figure 1 A system architecture diagram of a control system for composite material layer cutting according to an embodiment of the present invention; The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments belong to some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] In practice, the server-side equipment deployed in a composite material layer-cutting control system may consist of one or more devices. This composite material layer-cutting control system can be implemented as a business instance, a virtual machine, or hardware devices. For example, it can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, it can be understood as software deployed on a cloud node, providing a composite material layer-cutting control system to various user terminals. Alternatively, it can be implemented as a virtual machine deployed on one or more devices in a cloud node, with application software installed to manage each user terminal. Or, it can also be a server-side system composed of numerous identical or different types of hardware devices, with one or more hardware devices configured to provide a composite material layer-cutting control system to each user terminal.

[0019] In terms of implementation, the control system and user terminal for composite material layer cutting are mutually compatible. That is, if the control system for composite material layer cutting is implemented as an application installed on a cloud service platform, the user terminal is implemented as a client that establishes a communication connection with the application; or if the control system for composite material layer cutting is implemented as a website, the user terminal is implemented as a webpage; or if the control system for composite material layer cutting is implemented as a cloud service platform, the user terminal is implemented as a mini-program in an instant messaging application.

[0020] like Figure 1 The figure shown is a system architecture diagram of a composite material layer cutting control system provided in an embodiment of the present invention.

[0021] The composite material layer cutting control system 100 described in this invention can be located on a cloud server. In terms of implementation, it can function as one or more service devices, or as an application installed in the cloud (e.g., a mobile service operator's server, server cluster, etc.), or it can be developed into a website. Depending on the functions implemented, the composite material layer cutting control system 100 may include a multimodal data analysis module 101, a multiphysics simulation planning module 102, a real-time monitoring module 103, a core control module 104, and an optimization processing module 105. The modules described in this invention can also be referred to as units, which are a series of computer program segments that can be executed by an electronic device's processor and perform a fixed function, stored in the electronic device's memory.

[0022] In this embodiment of the invention, in a control system for layered cutting of composite materials, each of the above-mentioned modules can be implemented independently and can call other modules. Here, "calling" can be understood as one module connecting to multiple modules of another type and providing corresponding services to those connected modules. In the control system for layered cutting of composite materials provided by this embodiment of the invention, without modifying the program code, the applicable scope of a control system architecture for layered cutting of composite materials can be adjusted by adding modules and directly calling them, achieving cluster-based horizontal expansion to quickly and flexibly expand the control system for layered cutting of composite materials. In practical applications, the above-mentioned modules can be set in the same device or different devices, or they can be set in a virtual device, such as a service instance in a cloud server.

[0023] The following describes, with reference to specific embodiments, the various components and specific workflow of a control system for layered cutting of composite materials: The multimodal data parsing module 101 is used to perform digital image processing on the interlayer interface features of the composite material based on the physical property parameters and structural images of the composite material, so as to obtain the digital feature parameters of the composite material. In this embodiment of the invention, when the multimodal data parsing module performs digital image processing on the interlayer interface features of the composite material based on the physical property parameters and structural images of the composite material to obtain the digital feature parameters of the composite material, it is specifically used for: Edge contours are extracted from the structural image to obtain the interlayer boundary information of the composite material; Based on the physical property parameters, the material properties of the interlayer boundary information are correlated to obtain the material data of the composite material. The material data is reconstructed in three dimensions to obtain the interlayer structure representation data of the composite material; Multi-dimensional feature fusion is performed on the interlayer structure expression data to obtain the digital feature parameters of the composite material.

[0024] Specifically, when extracting the edge contour of the structural image, the structural image is first preprocessed to remove noise interference and make the interlayer region in the image clearer. Then, the gray value changes of the image are analyzed pixel by pixel to identify the locations where the gray value changes abruptly. These locations are candidate points of the interlayer boundary. Then, adjacent candidate points are connected into continuous lines to form a complete closed contour. Finally, interlayer boundary information that can accurately reflect the boundary position between the layers of the composite material is obtained.

[0025] Furthermore, when associating material properties with the interlayer boundary information based on the physical property parameters, the specific material type corresponding to the physical property parameters is first determined. For example, a certain combination of physical property parameters corresponds to a specific fiber material, and another combination corresponds to a resin material. Then, according to the different regions divided by the interlayer boundary information, each region is matched with the corresponding physical property parameters to determine the material type of each region. Finally, all regions and their corresponding material types are compiled and summarized to obtain material data containing the types and distribution range of materials in each layer.

[0026] Furthermore, when performing three-dimensional geometric reconstruction on the material data, based on the two-dimensional planar position and range of each region in the material data, and combined with the actual thickness information of the composite material, each two-dimensional region is stretched along the thickness direction to form a three-dimensional region with a certain thickness. At the same time, the boundary information between the three-dimensional regions of different materials and the interlayer boundary information are kept consistent, accurately reflecting the stacking relationship and contact state of each layer in space, and finally obtaining interlayer structure expression data that can completely present the spatial structure and material distribution of each layer of the composite material.

[0027] Furthermore, when performing multi-dimensional feature fusion on the interlayer structure expression data, multiple dimensions of features are extracted from the interlayer structure expression data, including the thickness of each layer, the volume ratio of each material region in three-dimensional space, the area of ​​the interlayer interface, the parallelism between adjacent layers, etc. Then, these features of different dimensions are correlated and integrated. For example, the thickness of a certain layer is correlated with the physical property parameters of the material of that layer, and the area of ​​the interlayer interface is combined with the materials of the two adjacent layers to form a set of digital feature parameters that can comprehensively and accurately reflect the interlayer interface characteristics of composite materials.

[0028] In general, edge contour extraction of structural images involves processing the images to obtain edge lines that reflect the boundaries between different layers of the composite material, thereby obtaining interlayer boundary information.

[0029] In summary, associating material properties with interlayer boundary information based on physical property parameters involves mapping physical property parameters to the regions defined by the boundaries, determining the material type of each region, and thus obtaining material data.

[0030] In general, three-dimensional geometric reconstruction of material data involves constructing a three-dimensional structure based on the two-dimensional information of the material data and factors such as thickness, thereby obtaining interlayer structure expression data.

[0031] In summary, multi-dimensional feature fusion of interlayer structure representation data involves extracting and integrating structural features from different dimensions to obtain digital feature parameters of composite materials.

[0032] The multiphysics simulation planning module 102 is used to perform multiphysics simulation prediction of stress distribution and thermal conductivity during the cutting process of the composite material based on the digital feature parameters, so as to obtain the layered cutting path of the composite material. In this embodiment of the invention, the multiphysics simulation planning module, based on the digital feature parameters, performs multiphysics simulation prediction of the stress distribution and thermal conductivity during the cutting process of the composite material to obtain the layered cutting path of the composite material, specifically for: Based on the digital feature parameters, a framework for the cutting process of the composite material is established to obtain a prediction framework for the composite material. Multi-field coupling behavior analysis was performed on the prediction framework to obtain the thermodynamic response data of the composite material; Based on the thermodynamic response data, the cutting trajectory of the composite material is optimized to obtain the layered cutting path of the composite material.

[0033] When the multiphysics simulation planning module performs the framework establishment for the cutting process of the composite material based on the digital feature parameters to obtain the prediction framework of the composite material, it is specifically used for: The geometric morphological features in the digital feature parameters are used to construct a three-dimensional spatial topology to obtain the spatial structural expression of the composite material. By performing attribute association mapping on the material attribute features in the digital feature parameters, the material attribute relationships of the composite material are obtained; By performing cross-scale correlation between the spatial structure representation and the material properties, the process analysis environment of the composite material is obtained; The structural integrity of the process analysis environment is verified to obtain the prediction framework for the composite material.

[0034] When the multiphysics simulation planning module performs cutting trajectory optimization on the composite material based on the thermodynamic response data to obtain the layered cutting path of the composite material, it is specifically used for: A potential risk assessment is performed on the stress concentration and thermally affected area distribution in the thermodynamic response data to obtain the risk cutting area of ​​the composite material. The distribution features of the risk cutting area are extracted to obtain the initial cutting trajectory scheme of the composite material; The initial cutting trajectory scheme is continuously optimized to obtain the target cutting trajectory parameters of the composite material; Based on the target cutting trajectory parameters, a layered cutting path for the composite material is generated.

[0035] Specifically, when establishing a framework for the cutting process of the composite material based on the digital feature parameters, the information such as the material type, thickness, and interlayer interface distribution of each layer contained in the digital feature parameters is first sorted out to clarify the overall structural characteristics of the composite material. Then, the key elements involved in the cutting process are determined, including the shape of the cutting tool, the direction and speed range of movement during cutting, and the types of forces that may be generated during cutting. Subsequently, the structural characteristics of the composite material are correlated with the cutting elements to clarify the interaction between the two, such as the difference in resistance of different material layers to the cutting tool and the influence of interlayer interfaces on the transmission of cutting force. Finally, these correlations are integrated to construct an overall framework that can completely describe the interaction between the material structure and the cutting behavior during the cutting process, which is the prediction framework for the composite material.

[0036] Furthermore, when performing multi-field coupling behavior analysis on the prediction framework, the initial conditions of the stress field and temperature field that may be generated during the cutting process are first extracted from the prediction framework. The initial conditions of the stress field include the initial pressure distribution generated by the contact between the cutting tool and the material, and the initial conditions of the temperature field include the initial temperature of the material before cutting and the initial heat distribution generated by the friction between the cutting tool and the material. Then, the interaction between the stress field and the temperature field is analyzed. Changes in the stress field will lead to changes in the density of the internal structure of the material, thereby affecting the heat transfer efficiency in the material. Changes in the temperature field will change the mechanical properties of the material, thereby affecting the stress distribution state in the material. By continuously tracking the changes in the magnitude and distribution of stress, the temperature and the conduction path under this interaction, the stress state and temperature changes at each position of the composite material during the cutting process are recorded, and the thermodynamic response data of the composite material are obtained after processing.

[0037] Furthermore, based on the thermodynamic response data, when optimizing the cutting trajectory of the composite material, the regions of stress concentration and excessively high temperature during the cutting process are first identified from the thermodynamic response data. These regions are key locations that are prone to interlayer separation or material damage in the composite material. Then, the direction of the cutting trajectory is adjusted for these regions. For stress concentration regions, the cutting trajectory is made to bypass the core part of the region, or the cutting direction is made to form a specific angle with the stress distribution direction to disperse the stress. For excessively high temperature regions, the path of the cutting trajectory is adjusted to shorten the dwell time of the cutting tool in the region and reduce heat accumulation. At the same time, combined with the layered structure of the composite material, it is ensured that the optimized trajectory can adapt to the characteristics of each layer of material. For example, a smoother trajectory change is used in the material layer with higher hardness, and a more stable cutting path is used at the more fragile interlayer interface. The trajectory that can minimize cutting damage is finally determined as the layered cutting path of the composite material.

[0038] Specifically, when constructing a three-dimensional spatial topology for the geometric features in the digital feature parameters, the geometric features are first extracted from the digital feature parameters, including the thickness of each layer, the outline shape of the interlayer interface, and the relative position of each layer in three-dimensional space. Then, the connection method and spatial arrangement relationship between each layer are determined, such as which layer is above another layer, the contact area and contact method between layers, etc. Subsequently, based on this information, the geometric model of each layer is established in three-dimensional space, and the boundary and coordinate range of each geometric model are clarified. Finally, the geometric models of all layers are combined according to the actual spatial relationship to form a three-dimensional structural model that can completely reflect the spatial position, connection state and overall shape of each layer of the composite material, thus obtaining the spatial structural expression of the composite material.

[0039] Furthermore, when performing attribute association mapping on the material attribute features in the digital feature parameters, the material attribute features are first extracted from the digital feature parameters, including the material type of each layer, the mechanical properties of each material, thermal properties, and other information. Then, these material attribute features are mapped to the regions divided in the spatial structure representation to clarify which region corresponds to which material and the specific attributes of that material. At the same time, the contact boundaries between different material regions are recorded to determine the differences and relationships in the physical properties of adjacent materials. For example, how the difference in thermal conductivity between two adjacent materials affects heat transfer. Finally, a mapping result containing the material attributes of each region and their interrelationships is formed, which yields the material attribute relationships of the composite material.

[0040] Furthermore, when integrating the spatial structure representation and the material property relationship, the three-dimensional geometric information of each layer in the spatial structure representation is bound to the corresponding material property information in the material property relationship, so that each three-dimensional geometric region is given a clear material property. At the same time, based on the connection relationship of each layer in the spatial structure, the interaction scenarios that different material regions may generate during the process are determined, such as the contact sequence and action mode when the cutting tool passes through different material layers. Then, the basic conditions required for process analysis are added, such as ambient temperature and initial stress state, etc. Finally, a comprehensive analysis scenario that includes both the three-dimensional structural morphology of the composite material and the material properties and interaction conditions of each region is formed, that is, the process analysis environment of the composite material is obtained.

[0041] Furthermore, when verifying the structural integrity of the process analysis environment, each item in the process analysis environment is checked one by one to confirm whether the spatial structure expression completely covers all interlayer structures of the composite material, whether the spatial position and connection relationship of each layer are accurate, whether the material property relationships are correctly bound to the corresponding spatial regions, and whether there are any missing or mismatched properties. At the same time, it is verified whether the interaction conditions in the process analysis environment are consistent with the actual situation of the composite material, such as whether the property association between adjacent materials is reasonable. If structural missing, property mismatch or condition contradiction is found, it is supplemented and corrected in time to ensure that the process analysis environment can comprehensively and accurately reflect the structural and property characteristics of the composite material. The process analysis environment after verification and correction is the prediction framework of the composite material.

[0042] Specifically, when assessing the potential risks of stress concentration and heat-affected zone distribution in the thermodynamic response data, the specific location of stress concentration, the range of stress action, and the duration of stress are first extracted from the thermodynamic response data. At the same time, the boundaries of the heat-affected zone, the magnitude of temperature change, and the heat conduction path inside the material are identified. Then, combined with the interlayer interface characteristics of the composite material and the tolerance of each layer, it is determined whether the stress concentration area may lead to interlayer separation or material fracture, and whether the heat-affected zone will change the physical properties of the material due to excessive temperature. In this way, it is determined which areas are prone to damage during the cutting process, and these areas are designated as areas that need to be avoided, thus obtaining the risk cutting areas of the composite material.

[0043] Furthermore, when extracting the distribution features of the risk cutting areas, the spatial distribution of the risk cutting areas is first observed, and the geometric shape of each risk area, its specific coordinate position in the three-dimensional structure of the composite material, the relative distance between areas and the overlap are recorded. Then, the correspondence between these risk areas and the interlayer interfaces and different material layers of the composite material is analyzed. For example, which risk areas are located at the interlayer interfaces and which are distributed inside specific material layers. Then, based on these distribution features, a preliminary cutting route that can bypass the core part of the risk area and adapt to the layered structure of the material is planned. The starting point and ending point of the route are determined according to the cutting requirements, and the intermediate path passes through the safe gap between the risk areas as much as possible, thus obtaining the initial cutting trajectory scheme of the composite material.

[0044] Furthermore, when optimizing the continuity of the initial cutting trajectory scheme, first check whether there are any parts in the initial cutting trajectory scheme where the trajectory direction suddenly changes or the path turning angle is too large. These parts may cause additional stress impact to the cutting tool during the movement. Then, adjust these discontinuous parts by connecting adjacent trajectory segments with smooth transition curves to make the trajectory direction change uniform and the turning angle controlled within the range that the material and cutting tool can withstand. At the same time, ensure that the optimized trajectory still avoids risky cutting areas and can adapt to the cutting characteristics of each layer of material. For example, maintain a more stable trajectory direction in material layers with higher hardness and reduce trajectory fluctuations at interlayer interfaces. The final determined trajectory information, including details such as continuous path direction and turning method, is the target cutting trajectory parameter of the composite material.

[0045] In summary, establishing a framework for the cutting process of composite materials based on digital feature parameters involves integrating the material's structural and property information with cutting-related elements to construct an overall framework that describes the interaction between the material and cutting behavior during the cutting process, thereby obtaining a prediction framework.

[0046] In summary, multi-field coupling behavior analysis of the prediction framework involves tracking the interaction and changes between the stress field and the temperature field within the framework, recording the stress state and temperature changes at various locations of the material, and thus obtaining thermodynamic response data.

[0047] In summary, optimizing the cutting trajectory of composite materials based on thermodynamic response data involves identifying risk areas and adjusting the trajectory to reduce damage, thereby obtaining a layered cutting path.

[0048] In general, constructing a three-dimensional spatial topology from the geometric features in the digital feature parameters involves extracting information such as the thickness of each layer, the outline of the interlayer interface, and the spatial relative position from the geometric features, combining the geometric models of each layer according to the actual spatial relationship, and then obtaining a spatial structural expression that can reflect the overall three-dimensional structure of the composite material.

[0049] In general, attribute association mapping of material attribute features in digital feature parameters involves extracting information such as material type, mechanical and thermal properties from the material attribute features, mapping them to each layer region in the spatial structure expression, clarifying the relationship between adjacent materials, and thus obtaining the material attribute relationship that includes the material attributes of each region and their interrelationships.

[0050] In summary, cross-scale correlation between spatial structure representation and material property relationship involves binding the three-dimensional geometric information of the spatial structure with the material properties of the corresponding region, clarifying the process interaction scenarios of different material regions by combining the material layering structure, and supplementing the basic process conditions, thereby obtaining a process analysis environment that combines structural morphology and property information.

[0051] In summary, structural integrity verification of the process analysis environment involves checking the integrity of the spatial structure, the accuracy of attribute binding, and the rationality of the process conditions. Problems discovered can be supplemented and corrected in a timely manner, thereby obtaining a predictive framework that can comprehensively and accurately reflect the material structure and properties.

[0052] In summary, assessing the potential risks of stress concentration and thermally affected area distribution in thermodynamic response data involves combining material tolerance to identify vulnerable areas and thus identifying high-risk cutting areas that need to be avoided.

[0053] In summary, extracting the distribution characteristics of the risk cutting area involves analyzing the spatial distribution of the risk area and its correspondence with the material structure, thereby planning a preliminary route to avoid the core of the risk and obtaining an initial cutting trajectory scheme.

[0054] In summary, optimizing the continuity of the initial cutting trajectory involves adjusting the discontinuous parts of the trajectory to achieve a smooth transition, ensuring adaptation to material properties, and thus obtaining target cutting trajectory parameters that include continuous path details.

[0055] In summary, generating a layered cutting path for composite materials based on target cutting trajectory parameters involves determining the final cutting route that adapts to the layered structure of the material based on optimized trajectory parameters, thereby obtaining the layered cutting path.

[0056] The real-time monitoring module 103 is used to perform multi-source data fusion on the vibration characteristics and temperature distribution of the composite material during processing based on the layered cutting path, so as to obtain real-time working condition data of the layered cutting path. In this embodiment of the invention, when the real-time monitoring module performs multi-source data fusion on the vibration characteristics and temperature distribution during the processing of the composite material based on the layered cutting path to obtain real-time operating data of the layered cutting path, it is specifically used for: Based on the layered cutting path, vibration monitoring data and temperature monitoring data during the material processing are collected to obtain vibration signal data and temperature distribution data of the material processing process. The vibration signal data is analyzed for signal characteristics to obtain the vibration signal parameters during the material processing. Thermal field feature analysis is performed on the temperature distribution data to obtain the temperature distribution parameters during the material processing. Multimodal data fusion analysis is performed on the vibration signal parameters and the temperature distribution parameters to obtain real-time operating data of the layered cutting path.

[0057] Specifically, based on the layered cutting path, when collecting vibration and temperature monitoring data during material processing, vibration sensors are first installed at key locations where the cutting tool contacts the composite material, according to the direction and key nodes of the layered cutting path. Temperature sensors are then evenly distributed along the cutting path on the surface of the composite material to ensure that the sensors can cover all areas that may generate vibration and temperature changes during the cutting process. Once the cutting process begins, the vibration sensors capture the vibration fluctuations generated by the interaction between the cutting tool and the material in real time, recording the changes in vibration at fixed time intervals to form a continuous vibration signal sequence. The temperature sensors simultaneously record the temperature values ​​at the corresponding locations. Through the collaborative work of multiple sensors, the temperature changes at each point on the cutting path are completely recorded, and finally, the vibration signal data and temperature distribution data of the material processing process are obtained.

[0058] Furthermore, when performing signal feature analysis on the vibration signal data, interference signals in the vibration signal data are first filtered out to remove noise caused by irrelevant factors such as environmental vibration, and the effective vibration signals directly related to the cutting process are retained. Then, the variation law of the effective vibration signals is observed to identify the peak and valley points of vibration intensity, record the maximum and minimum values ​​of vibration intensity, and analyze the variation trend of vibration signals in the time dimension, such as whether the vibration gradually increases or decreases, and whether there are periodic fluctuations. At the same time, the duration of vibration and the differences in vibration characteristics at different cutting stages are determined. These analyzed feature information are organized into a standardized form to obtain the vibration signal parameters in the material processing process.

[0059] Furthermore, when performing thermal field feature analysis on the temperature distribution data, the temperature distribution data is first organized according to the spatial location of the cutting path, and the temperature value corresponding to each location is determined. By comparing the temperature data at different locations, the areas with the highest and lowest temperatures during the cutting process are identified, the boundary range and coverage area of ​​the high-temperature areas are marked, and the spatial distribution pattern of temperature is analyzed. For example, whether the temperature gradually increases along the cutting path or exhibits a local accumulation state. At the same time, the temperature changes over time are tracked, and the time point when the temperature reaches its peak and the rate of temperature decrease are recorded. These features of temperature spatial distribution and temporal change are summarized to obtain the temperature distribution parameters during the material processing process.

[0060] Furthermore, when performing multimodal data fusion analysis on the vibration signal parameters and the temperature distribution parameters, the vibration signal parameters and temperature distribution parameters are first matched according to time sequence and spatial location to ensure that the vibration characteristics and temperature characteristics at the same time and location can match each other. Then, the correlation between the two is analyzed. For example, when the vibration intensity reaches a peak, does the temperature at the corresponding location also rise? Does the high-temperature area overlap with the area of ​​severe vibration? Through this correlation analysis, it is determined whether the vibration and temperature changes conform to the normal processing state and possible abnormal situations are identified, such as abnormally enhanced vibration accompanied by a sudden rise in local temperature. Finally, these correlation analysis results are compared with the standard characteristics of normal processing and integrated to form an information set that can comprehensively reflect the current cutting process state, that is, to obtain the real-time working condition data of the layered cutting path.

[0061] In summary, the data acquisition of vibration and temperature monitoring data during material processing based on the layered cutting path involves arranging vibration and temperature sensors according to the path direction and key nodes, capturing vibration fluctuations and temperature changes at various locations in real time during the cutting process, and recording them in a regular manner, thereby obtaining vibration signal data and temperature distribution data of the material processing process.

[0062] In general, signal feature analysis of vibration signal data involves first filtering out irrelevant interference noise from the data, then identifying the extreme values ​​of vibration intensity, the trend of time variation, and the characteristic differences of different cutting stages. These analyzed features are then organized into a standardized form to obtain the vibration signal parameters during the material processing.

[0063] In general, analyzing the thermal field characteristics of temperature distribution data involves organizing the temperature data according to the spatial location of the cutting path, determining the range of high and low temperature regions, the spatial distribution pattern of temperature, and its changes over time, summarizing these thermal field characteristics, and then obtaining the temperature distribution parameters during the material processing.

[0064] In summary, multimodal data fusion analysis of vibration signal parameters and temperature distribution parameters involves matching the two types of parameters according to time and spatial location, analyzing their correlation and determining whether they conform to normal processing rules, and then combining the results with standard features to obtain real-time working condition data of the layered cutting path.

[0065] The core control module 104 is used to perform multi-criteria decision fusion on the real-time operating data to obtain the target process parameters of the layered cutting path. In this embodiment of the invention, when the core control module performs multi-criteria decision fusion on the real-time operating data to obtain the target process parameters of the layered cutting path, it is specifically used for: A multi-dimensional evaluation of the real-time operating condition data is constructed to obtain a benchmark evaluation framework for the real-time operating condition data. Dynamically weight the benchmark evaluation framework to obtain the importance allocation relationship of the benchmark evaluation framework; The importance allocation relationship is evaluated using a multi-objective optimization method to obtain the target process parameters for the layered cutting path.

[0066] When the core control module performs multi-dimensional evaluation of the real-time operating data to construct a benchmark evaluation framework for the real-time operating data, it is specifically used for: Feature data extraction is performed on the real-time operating data to obtain cutting quality feature data, processing efficiency feature data, and equipment status feature data of the real-time operating data; The cutting quality feature data is quantified and integrated to obtain the cutting quantification index of the real-time working condition data. The processing efficiency feature data is fused to obtain the processing efficiency evaluation benchmark of the real-time operating data; The equipment status feature data is quantified to obtain the equipment status quantification index of the real-time operating condition data. An evaluation benchmark is constructed for the cutting quantification index, the processing efficiency evaluation benchmark, and the equipment status quantification index to obtain the benchmark evaluation framework for the real-time operating data.

[0067] When the core control module performs dynamic weight configuration on the benchmark evaluation framework to obtain the importance allocation relationship of the benchmark evaluation framework, it is specifically used for: Based on the aforementioned benchmark evaluation framework, information entropy data for the evaluation dimensions are generated. The dynamic weighting coefficients of the evaluation dimensions are calculated based on the information entropy data, wherein the calculation formula for the dynamic weighting coefficients is as follows: ; In the formula, The real-time operating condition data is in the first... The weighting coefficients of each evaluation dimension, The real-time operating condition data is in the first... Information entropy value of each evaluation dimension The total number of evaluation dimensions for the real-time operating condition data. For summation index variables, The real-time operating condition data is in the first... The information entropy value of each evaluation dimension.

[0068] Specifically, when constructing a multi-dimensional evaluation of the real-time operating data, key dimensions related to processing quality are first extracted from the real-time operating data, including vibration stability, temperature control accuracy, cutting efficiency, and interlayer interface integrity. Then, clear evaluation criteria are set for each dimension. For example, the criteria for vibration stability are whether the vibration intensity is within the material's tolerance range and whether continuous and severe vibration occurs. The criteria for temperature control accuracy are whether the temperature exceeds the material's thermal deformation threshold and whether the high-temperature area is concentrated at the interlayer interface. Subsequently, these dimensions and their evaluation criteria are integrated according to logical relationships to clarify the correlation between each dimension, such as the linkage effect between abnormal vibration and sudden temperature rise. Finally, a structured evaluation system that can comprehensively measure the processing status is formed, which is the benchmark evaluation framework of the real-time operating data.

[0069] Furthermore, when dynamically configuring the weights of the benchmark evaluation framework, the characteristics of the current processing stage are first analyzed. If it is in the interlayer interface cutting stage of composite materials, the interlayer interface integrity dimension has a greater impact on processing quality, and its importance ratio in the framework needs to be increased. If it is in the thick material layer cutting stage, the temperature control accuracy dimension is more critical, and its weight is increased accordingly. Then, the weight is adjusted according to the characteristics of the processed material. For materials with high thermal sensitivity, the weight of temperature-related dimensions is higher than that of vibration-related dimensions. For brittle materials, the weight of vibration stability dimension is higher. Through this adjustment based on the processing stage and material characteristics, the importance ratio of each evaluation dimension under the current working condition is clarified, thus obtaining the importance allocation relationship of the benchmark evaluation framework.

[0070] Furthermore, when performing multi-objective optimization evaluation on the importance allocation relationship, the optimization objectives are first determined, including reducing vibration damage to the interlayer interface, controlling the temperature within the material's tolerance range, and ensuring that the cutting efficiency meets production requirements. Then, based on the weights of each dimension in the importance allocation relationship, different combinations of process parameters are simulated and evaluated. For example, when the vibration stability weight is high, the effect of reducing the cutting speed on mitigating vibration intensity is evaluated first. When the temperature control weight is high, the focus is on analyzing the effect of enhancing cooling intensity on improving temperature distribution. Subsequently, the achievement of each objective under different combinations is compared, and the optimal parameter combination that can simultaneously meet the requirements of multiple objectives such as vibration, temperature, and efficiency is selected, which is the target process parameter of the layered cutting path.

[0071] Specifically, when extracting feature data from the real-time operating data, information related to cutting quality is first filtered out, including whether cracks appear at the interlayer interface, the flatness of the cut surface, and whether burrs exist on the cut edge. This information is categorized as cutting quality feature data. Then, information related to processing efficiency is extracted, including the current cutting speed, the completed cutting length, the remaining cutting workload, and the estimated completion time. This information is categorized as processing efficiency feature data. Finally, information related to equipment operating status is extracted, including the wear degree of the cutting tool, the current fluctuation during equipment operation, and the speed stability of the cutting spindle. This information is categorized as equipment status feature data. Ultimately, the cutting quality feature data, processing efficiency feature data, and equipment status feature data of the real-time operating data are obtained.

[0072] Furthermore, when performing feature quantification and integration on the cutting quality feature data, a clear quantification standard is first set for each cutting quality feature. For example, the "interlayer interface cracking" feature is divided into "no cracking, slight cracking, and severe cracking" and corresponding to clear descriptive states, and the "cutting surface flatness" feature is divided into "flat, slightly uneven, and severely uneven" and corresponding to clear descriptive states. Then, the quantification results of each individual cutting quality feature are summarized. For example, if there is no interlayer interface cracking and the cutting surface is flat, the quantification results of these two features are integrated into "excellent cutting quality". If there is slight interlayer interface cracking and the cutting surface is slightly uneven, it is integrated into "average cutting quality". In this way, a comprehensive description covering all cutting quality features is formed, which is the cutting quantification index of the real-time working condition data.

[0073] Furthermore, when performing efficiency data fusion on the processing efficiency feature data, the current cutting speed data is first compared with the preset standard cutting speed to determine whether the current speed meets expectations; then, the current cutting progress is calculated by combining the completed cutting length and the total cutting length; and finally, the comparison result of the cutting speed is combined with the cutting progress data.

[0074] For example, if the current cutting speed reaches the standard speed and the cutting progress meets the plan, these two types of data are merged into "current processing efficiency meets the standard". If the current cutting speed is lower than the standard speed and the cutting progress lags behind the plan, they are merged into "current processing efficiency is lower than the standard".

[0075] Furthermore, by incorporating the comparison information between the estimated completion time and the planned completion time, the basis for efficiency evaluation is further supplemented, ultimately forming a reference standard that can intuitively reflect the processing efficiency level, i.e., the processing efficiency evaluation benchmark of the real-time working condition data.

[0076] Furthermore, when quantifying the equipment status characteristic data, an observable quantitative description is first set for each equipment status characteristic. For example, the "wear degree of cutting tool" is divided into "no wear, slight wear, moderate wear, severe wear" and corresponding clear status descriptions, and the "equipment operating current" is divided into "normal range, slightly high, excessively high" and corresponding clear status descriptions. Then, the quantitative descriptions of all equipment status characteristics are organized.

[0077] For example, if the cutting tool is slightly worn and the equipment operating current is normal, the quantitative results of these two characteristics are integrated into "the equipment is in good condition". If the cutting tool is moderately worn and the equipment operating current is slightly high, it is integrated into "the equipment condition needs attention". In the end, an indicator that can comprehensively reflect the equipment's operating status is formed, which is the equipment status quantitative indicator that obtains the real-time operating data.

[0078] Furthermore, when constructing evaluation benchmarks for the cutting quantification index, the processing efficiency evaluation benchmark, and the equipment status quantification index, the evaluation dimensions corresponding to each of the three indicators are first determined. The cutting quantification index is taken as the core content of the "cutting quality dimension," and the specific content to be evaluated under this dimension is clarified as the quality of the cut surface, the integrity of the interlayer interface, etc., and the description in the cutting quantification index is used as the evaluation basis. The processing efficiency evaluation benchmark is taken as the core content of the "processing efficiency dimension," and the specific content to be evaluated under this dimension is clarified as the cutting speed compliance, progress completion, etc., and the description in the processing efficiency evaluation benchmark is used as the evaluation basis. The equipment status quantification index is taken as the core content of the "equipment status dimension," and the specific content to be evaluated under this dimension is clarified as the tool wear, equipment operating stability, etc., and the description in the equipment status quantification index is used as the evaluation basis. Then, the three dimensions are arranged in logical order, and the evaluation standards and judgment methods of each dimension are clarified, forming a structured evaluation system that includes three core dimensions: quality, efficiency, and equipment, and each dimension has clear evaluation content and basis, thus obtaining the benchmark evaluation framework for the real-time working condition data.

[0079] Specifically, when generating information entropy data for evaluation dimensions based on the benchmark evaluation framework, firstly, all evaluation dimensions included in the benchmark evaluation framework are identified, such as cutting quality dimension, processing efficiency dimension, and equipment status dimension. Then, for each evaluation dimension, real-time operating condition data samples are collected at different processing time periods. For example, for the cutting quality dimension, cutting quantitative index data at different time periods are collected; for the processing efficiency dimension, processing efficiency evaluation benchmark data at different time periods are collected; and for the equipment status dimension, equipment status quantitative index data at different time periods are collected. Next, the frequency of different data results within each evaluation dimension is statistically analyzed. For example, the frequency of results such as "excellent cutting quality," "average cutting quality," and "poor cutting quality" in the cutting quality dimension, and the frequency of results such as "processing efficiency meets standards" and "processing efficiency is below standard" in the processing efficiency dimension. By analyzing these frequencies, the uniformity of data distribution within each dimension is analyzed. The more uniform the data distribution, the higher the information uncertainty contained in that dimension, and the larger the information entropy value. Conversely, the more concentrated the data distribution, the lower the information uncertainty, and the smaller the information entropy value. The information entropy value of each evaluation dimension is determined one by one in this way, and finally, the information entropy data of the evaluation dimension is obtained.

[0080] Furthermore, when calculating the dynamic weight coefficients of the evaluation dimensions based on the information entropy data, firstly, for each evaluation dimension, the information entropy value corresponding to that dimension is subtracted from the overall benchmark value to obtain the "difference between the overall benchmark value and the information entropy value" for each evaluation dimension. For example, if the information entropy value of a certain evaluation dimension is the entropy value of the corresponding dimension, the difference between the overall benchmark value and that entropy value is calculated. Then, the results of the "difference between the overall benchmark value and the information entropy value" for all evaluation dimensions are summarized to obtain the sum of the "difference between the overall benchmark value and the information entropy value" for all evaluation dimensions. That is, the results of the "difference between the overall benchmark value and the information entropy value" for each evaluation dimension are sequentially merged. The results are summed to obtain the total result. Then, the sum is proportionally calculated using the difference between the overall benchmark value and the information entropy value for each evaluation dimension. The resulting ratio is the dynamic weight coefficient for that evaluation dimension. For example, the ratio between the difference between the overall benchmark value and the information entropy value for a certain evaluation dimension and the sum of the differences between the overall benchmark value and the information entropy value for all evaluation dimensions is the weight coefficient for that dimension. The dynamic weight coefficient for each evaluation dimension is determined in this way. These coefficients clearly reflect the importance proportion of each evaluation dimension in the benchmark evaluation framework, and together they constitute the importance distribution relationship of the benchmark evaluation framework.

[0081] In summary, constructing a multi-dimensional evaluation framework for real-time operating data involves extracting key dimensions related to processing quality, such as vibration stability and temperature control accuracy, from the data, setting clear evaluation standards for each dimension, and integrating the correlation methods of each dimension to obtain a benchmark evaluation framework that can comprehensively measure the processing status.

[0082] In summary, dynamic weighting of the benchmark assessment framework involves adjusting the importance proportion of each assessment dimension based on the characteristics of the current processing stage and material properties, thereby obtaining the importance distribution relationship of the benchmark assessment framework.

[0083] In general, the multi-objective optimization evaluation of importance allocation relationship first determines the optimization objectives such as reducing vibration damage and controlling temperature, then evaluates the effect of different combinations of process parameters according to the weight of each dimension, compares and selects the optimal parameter combination that meets the requirements of multiple objectives, and then obtains the target process parameters for the layered cutting path.

[0084] In summary, feature data extraction from real-time operating data involves filtering and classifying information related to cutting quality, processing efficiency, and equipment status from the real-time operating data, thereby obtaining cutting quality feature data, processing efficiency feature data, and equipment status feature data.

[0085] In general, the feature quantification and integration of cutting quality feature data involves setting clear quantification standards for each cutting quality feature, summarizing the quantification results of each feature to form a comprehensive description, and then obtaining the cutting quantification index.

[0086] In general, efficiency data fusion of processing efficiency characteristic data involves comparing the current cutting speed with the standard speed, calculating the cutting progress, and combining the comparison information of the estimated completion time with the planned time to form a reference standard reflecting the efficiency level, thereby obtaining a processing efficiency evaluation benchmark.

[0087] In general, quantifying equipment status characteristic data involves setting observable quantitative descriptions for each equipment status characteristic, then organizing the quantification results of each characteristic to form an index that comprehensively reflects the equipment's operating status, thus obtaining the equipment status quantification index.

[0088] In summary, constructing evaluation benchmarks for cutting quantification indicators, processing efficiency evaluation benchmarks, and equipment status quantification indicators involves using these three indicators as the core content of the dimensions of cutting quality, processing efficiency, and equipment status, respectively. This clarifies the evaluation content and basis for each dimension, forms a structured evaluation system, and ultimately yields a benchmark evaluation framework.

[0089] In summary, generating information entropy data for evaluation dimensions based on the benchmark evaluation framework involves first identifying all evaluation dimensions included in the framework, then collecting real-time operating condition data samples from different processing periods under each dimension, statistically analyzing the frequency of different data results within each dimension, determining the information entropy value of each evaluation dimension by analyzing the uniformity of data distribution, and thus obtaining the information entropy data for the evaluation dimensions.

[0090] In general, the dynamic weight coefficients of the evaluation dimensions are calculated based on the information entropy data. First, for each evaluation dimension, the information entropy value of that dimension is subtracted from the overall benchmark value to obtain the difference. Then, the differences of this type for all evaluation dimensions are accumulated. Finally, the difference of each evaluation dimension is divided by the accumulated sum to obtain the dynamic weight coefficient of the corresponding evaluation dimension. These coefficients together constitute the importance allocation relationship of the benchmark evaluation framework.

[0091] The optimization execution module 105 is used to correct and encode the target process parameters to obtain the cutting instructions for the composite material.

[0092] In this embodiment of the invention, when the optimization execution module performs the modification encoding of the target process parameters to obtain the cutting instructions for the composite material, it is specifically used for: The target process parameters are calibrated by parameter standardization to obtain the standardized parameters of the target process parameters; The standardized parameters are encoded to obtain the cutting instruction sequence of the composite material; Logical verification is performed on the cutting instruction sequence to obtain the cutting instructions for the composite material.

[0093] Specifically, when standardizing and calibrating the target process parameters to obtain the standardized parameters, the specific contents of the target process parameters are first clarified, such as cutting speed, cutting tool pressure, cooling intensity, etc. Then, based on the general standards of the composite material processing industry and the rated working range of the cutting equipment used, the standard range of each process parameter is determined. For example, the standard range of cutting speed needs to be set in combination with the speed range in which the equipment can operate stably and the conventional speed requirements when cutting different composite materials. The standard range of tool pressure needs to match the upper limit of the equipment output pressure and the material's pressure tolerance threshold.

[0094] Next, the current value of each target process parameter is compared with the corresponding standard range. If the parameter value is within the standard range, the value is retained and marked as compliant. If the value exceeds the upper limit of the standard range, it is adjusted to the maximum value of the standard range, and the reason for the adjustment is recorded to avoid equipment overload or material damage. If the value is below the lower limit of the standard range, it is adjusted to the minimum value of the standard range to ensure that the processing efficiency meets the basic requirements. After adjustment, the synergy between the parameters needs to be checked, such as whether the adjusted cutting speed and cooling intensity can control the material cutting temperature to avoid problems of excessively high or low temperatures. Finally, all parameters that meet the standards and are synergistically adapted are compiled to obtain the standardized parameters of the target process parameters.

[0095] Furthermore, when encoding the standardized parameters to obtain the cutting instruction sequence of the composite material, a unified encoding rule is first established to clarify the encoding format corresponding to different types of standardized parameters. For example, the cutting speed parameter uses "speed" as a prefix, followed by a specific character combination corresponding to the speed level; the tool pressure parameter uses "pressure" as a prefix; and the cooling intensity parameter uses "cold" as a prefix. The character combination corresponding to each parameter needs to be divided according to the standard range of the parameter, and different level segments within the standard range are respectively assigned to unique characters or character combinations.

[0096] Furthermore, within the standard range of cutting speed, the low level segment corresponds to "low," the medium level segment to "medium," and the high level segment to "high." Then, following the sequence of composite material cutting, each standardized parameter is sequentially converted into its corresponding code. For example, the cutting speed parameter is processed first, and its code is determined as "speed medium" based on the speed segment it belongs to. Next, the tool pressure parameter is processed to obtain the code "pressure high," and then the cooling intensity parameter is processed to obtain the code "cold medium." Subsequently, the codes of these individual parameters are arranged according to the processing flow order, and different codes of different parameters are distinguished by specific separators to avoid code confusion, forming a continuous code string such as "speed medium, pressure high, cold medium." Finally, it is checked whether the code of each parameter accurately matches its standardized parameter level and whether the coding order is consistent with the actual cutting flow, ensuring that there are no coding errors or reversed order. The resulting ordered code string is the cutting instruction sequence of the composite material.

[0097] Furthermore, the cutting instruction sequence is logically verified. When obtaining the cutting instructions for the composite material, the core logical rules in the composite material cutting process are first sorted out, including parameter coordination logic, processing sequence logic, and equipment adaptation logic. Then, the cutting instruction sequence is checked one by one according to these logical rules. First, it is checked whether the coding order conforms to the processing sequence logic. For example, whether the tool pressure code appears before the cutting speed code. If the order is incorrect, it is marked and the coding arrangement is adjusted. Next, it is checked whether the level corresponding to each parameter code conforms to the parameter coordination logic. For example, when the cutting speed code is "high speed", is the cooling intensity code "high cooling"? If a mismatch occurs, analyze the cause. For example, it may be due to a deviation during encoding conversion. The correspondence between standardized parameters and encoding needs to be rechecked and corrected. Then check whether the parameter levels corresponding to all codes conform to the device adaptation logic. For example, does the pressure value corresponding to the tool pressure code "extremely high pressure" exceed the maximum output pressure of the device? If it does, adjust the code to the range that the device can withstand. If problems are found during the verification process, correct them in time according to the logical rules. After correction, conduct a comprehensive check again to ensure that there are no logical contradictions in the instruction sequence in terms of parameter coordination, order, and device adaptation. The cutting instruction sequence that has been verified and has no logical problems is the cutting instruction for the composite material.

[0098] In general, standardizing and calibrating the target process parameters involves clarifying the specific content of the parameters, determining the standard range of each parameter based on industry standards and equipment range, adjusting the parameters to within the standard range, and checking their compatibility, thereby obtaining the standardized parameters of the target process.

[0099] In general, encoding standardized parameters involves establishing unified encoding rules to correspond to different parameter types and levels, converting standardized parameters into codes according to the cutting process, and arranging them in an orderly manner to obtain the cutting instruction sequence for composite materials.

[0100] In general, logical verification of the cutting instruction sequence involves checking and correcting problems in the sequence based on logical rules such as parameter coordination, processing order, and equipment compatibility to ensure there are no logical contradictions, thereby obtaining the cutting instructions for composite materials.

[0101] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0102] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A control system for layered cutting of composite materials, characterized in that, The system includes a multimodal data parsing module, a multiphysics simulation planning module, a real-time monitoring module, a core control module, and an optimization execution module, wherein: The multimodal data parsing module is used to perform digital image processing on the interlayer interface features of the composite material based on the physical property parameters and structural images of the composite material, so as to obtain the digital feature parameters of the composite material. The multiphysics simulation planning module is used to perform multiphysics simulation and prediction of stress distribution and thermal conductivity during the cutting process of the composite material based on the digital feature parameters, so as to obtain the layered cutting path of the composite material. The real-time monitoring module is used to perform multi-source data fusion on the vibration characteristics and temperature distribution of the composite material during processing based on the layered cutting path, so as to obtain real-time working condition data of the layered cutting path. The core control module is used to perform multi-criteria decision fusion on the real-time operating data to obtain the target process parameters of the layered cutting path; The optimization execution module is used to correct and encode the target process parameters to obtain the cutting instructions for the composite material.

2. The control system for composite material layer cutting as described in claim 1, characterized in that, When the multimodal data parsing module performs digital image processing on the interlayer interface features of the composite material based on the physical property parameters and structural images of the composite material to obtain the digital feature parameters of the composite material, it is specifically used for: Edge contour extraction is performed on the structural image of the composite material to obtain the interlayer boundary information of the composite material; Based on the physical property parameters of the composite material, the interlayer boundary information is correlated with material properties to obtain the material data of the composite material. The material data is reconstructed in three dimensions to obtain the interlayer structure representation data of the composite material; Multi-dimensional feature fusion is performed on the interlayer structure expression data to obtain the digital feature parameters of the composite material.

3. The control system for layered cutting of composite materials as described in claim 1, characterized in that, The multiphysics simulation planning module, based on the digital feature parameters, performs multiphysics simulation prediction of stress distribution and thermal conductivity during the cutting process of the composite material, and obtains the layered cutting path of the composite material, specifically for: Based on the digital feature parameters, a framework for the cutting process of the composite material is established to obtain a prediction framework for the composite material. Multi-field coupling behavior analysis was performed on the prediction framework to obtain the thermodynamic response data of the composite material; Based on the thermodynamic response data, the cutting trajectory of the composite material is optimized to obtain the layered cutting path of the composite material.

4. The control system for composite material layer cutting as described in claim 3, characterized in that, When the multiphysics simulation planning module performs the framework establishment for the cutting process of the composite material based on the digital feature parameters to obtain the prediction framework of the composite material, it is specifically used for: The geometric morphological features in the digital feature parameters are used to construct a three-dimensional spatial topology to obtain the spatial structural expression of the composite material. By performing attribute association mapping on the material attribute features in the digital feature parameters, the material attribute relationships of the composite material are obtained; By performing cross-scale correlation between the spatial structure representation and the material properties, the process analysis environment of the composite material is obtained; The structural integrity of the process analysis environment is verified to obtain the prediction framework for the composite material.

5. The control system for composite material layer cutting as described in claim 3, characterized in that, When the multiphysics simulation planning module performs cutting trajectory optimization on the composite material based on the thermodynamic response data to obtain the layered cutting path of the composite material, it is specifically used for: A potential risk assessment is performed on the stress concentration and thermally affected area distribution in the thermodynamic response data to obtain the risk cutting area of ​​the composite material. The distribution features of the risk cutting area are extracted to obtain the initial cutting trajectory scheme of the composite material; The initial cutting trajectory scheme is continuously optimized to obtain the target cutting trajectory parameters of the composite material; Based on the target cutting trajectory parameters, a layered cutting path for the composite material is generated.

6. The control system for composite material layer cutting as described in claim 1, characterized in that, When the real-time monitoring module performs multi-source data fusion on the vibration characteristics and temperature distribution during the processing of the composite material based on the layered cutting path to obtain real-time operating data of the layered cutting path, it is specifically used for: Based on the layered cutting path, vibration monitoring data and temperature monitoring data during the material processing are collected to obtain vibration signal data and temperature distribution data of the material processing process. The vibration signal data is analyzed for signal characteristics to obtain the vibration signal parameters during the material processing. Thermal field feature analysis is performed on the temperature distribution data to obtain the temperature distribution parameters during the material processing. Multimodal data fusion analysis is performed on the vibration signal parameters and the temperature distribution parameters to obtain real-time operating data of the layered cutting path.

7. The control system for composite material layer cutting as described in claim 1, characterized in that, When the core control module performs multi-criteria decision fusion on the real-time operating data to obtain the target process parameters of the layered cutting path, it is specifically used for: A multi-dimensional evaluation of the real-time operating condition data is constructed to obtain a benchmark evaluation framework for the real-time operating condition data. Dynamically weight the benchmark evaluation framework to obtain the importance allocation relationship of the benchmark evaluation framework; The importance allocation relationship is evaluated using a multi-objective optimization method to obtain the target process parameters for the layered cutting path.

8. The control system for composite material layer cutting as described in claim 7, characterized in that, When the core control module performs multi-dimensional evaluation of the real-time operating data to construct a benchmark evaluation framework for the real-time operating data, it is specifically used for: Feature data extraction is performed on the real-time operating data to obtain cutting quality feature data, processing efficiency feature data, and equipment status feature data of the real-time operating data; The cutting quality feature data is quantified and integrated to obtain the cutting quantification index of the real-time working condition data. The processing efficiency feature data is fused to obtain the processing efficiency evaluation benchmark of the real-time operating data; The equipment status feature data is quantified to obtain the equipment status quantification index of the real-time operating condition data. An evaluation benchmark is constructed for the cutting quantification index, the processing efficiency evaluation benchmark, and the equipment status quantification index to obtain the benchmark evaluation framework for the real-time operating data.

9. A control system for layered cutting of composite materials as described in claim 7, characterized in that, When the core control module performs dynamic weight configuration on the benchmark evaluation framework to obtain the importance allocation relationship of the benchmark evaluation framework, it is specifically used for: Based on the aforementioned benchmark evaluation framework, information entropy data for the evaluation dimensions are generated. The dynamic weighting coefficients of the evaluation dimensions are calculated based on the information entropy data, wherein the calculation formula for the dynamic weighting coefficients is as follows: ； In the formula, The weighting coefficient of the real-time operating condition data in the th evaluation dimension is given by [the relevant factor]. The real-time operating condition data is in the first... Information entropy value of each evaluation dimension The total number of evaluation dimensions for the real-time operating condition data. For summation index variables, The real-time operating condition data is in the first... The information entropy value of each evaluation dimension.

10. A control system for layered cutting of composite materials as described in claim 1, characterized in that, When the optimization execution module performs the modification encoding of the target process parameters to obtain the cutting instructions for the composite material, it is specifically used for: The target process parameters are calibrated by parameter standardization to obtain the standardized parameters of the target process parameters; The standardized parameters are encoded to obtain the cutting instruction sequence of the composite material; Logical verification is performed on the cutting instruction sequence to obtain the cutting instructions for the composite material.

Images