Balanced control method and system for metal additive manufacturing assisted by multi-mode electromagnetic field

Abstract

The invention discloses a balance control method and system for multi-mode electromagnetic field assisted additive manufacturing metal, and relates to the technical field of intelligent control, the method comprises the following steps: establishing a vector operator of geometric features of an additive part model, collecting multi-feature data under the assistance of a multi-mode electromagnetic field, and quantifying the relationship between the vector operator and the multi-feature data to generate a mathematical description vector; performing classification and modular deconstruction on the complex additive model based on the vector to form a multi-variety deconstruction unit category; and in combination with the optimal auxiliary electromagnetic field and an additive process, an expert system is established, and target deconstruction and electromagnetic field adaptive equalization control are realized. The technical problem that according to an existing additive manufacturing technology, molten pool flowing and solidification processes of different parts of a complex structural part are difficult to accurately regulate and control, and the forming quality and efficiency are affected is solved, and the purposes of adjusting electromagnetic field parameters in real time according to different geometrical characteristics through dynamic self-adaptive balance control of a multi-mode electromagnetic field and improving the forming quality and efficiency are achieved. And the forming quality and the manufacturing efficiency of the complex structural part are improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, specifically to a method and system for equalization control of metals in multi-mode electromagnetic field-assisted additive manufacturing. Background Technology

[0002] In additive manufacturing, the fabrication of complex structural parts faces significant challenges. The geometric features of different parts (such as size, shape, and wall thickness) have a substantial impact on molten pool flow and forming quality, and traditional techniques struggle to dynamically adapt to these changes, leading to forming defects and inconsistent quality. While electromagnetic field assistance can improve forming quality, it lacks precise adaptive control methods. Therefore, a control technology capable of dynamically adjusting electromagnetic field parameters based on different geometric features is urgently needed to achieve high-quality manufacturing of complex structural parts. Summary of the Invention

[0003] This application provides a method and system for equalization control of metals in multi-mode electromagnetic field-assisted additive manufacturing, which is used to solve the technical problem that existing additive manufacturing technologies are unable to accurately control the flow and solidification process of the molten pool in different parts of complex structural parts, thus affecting the forming quality and efficiency.

[0004] The first aspect of this application provides a method for equalization control of metals in multi-mode electromagnetic field-assisted additive manufacturing. The method includes: establishing a vector operator describing the geometric features of an additive model; collecting multi-feature data of a typical additive model under the assistance of a bidirectional multi-mode electromagnetic field; mathematically characterizing multiple features of the typical additive model during the additive manufacturing process by establishing a quantitative relationship between the vector operator and the multi-feature data, generating a mathematical characterization vector; classifying the characterization vectors of different parts of a complex additive model based on the mathematical characterization vector, generating a vector classification result; modularly deconstructing the constituent units of the complex additive model according to the vector classification result, generating multiple modular deconstruction unit categories applicable to multi-variety additive models; obtaining the optimal auxiliary electromagnetic field and additive process for a typical modular deconstruction unit, and establishing a multi-mode electromagnetic field optimization expert system containing multi-variety deconstruction units in conjunction with the multiple modular deconstruction unit categories; and performing target deconstruction and adaptive electromagnetic field equalization control on a target additive model based on the multi-mode electromagnetic field optimization expert system.

[0005] A second aspect of this application provides a balance control system for multi-mode electromagnetic field-assisted additive manufacturing of metals. The system includes: a vector operator establishment module for establishing vector operators describing the geometric features of an additive model; a multi-feature data acquisition module for acquiring multi-feature data of a typical additive model under the assistance of a bidirectional multi-mode electromagnetic field; a mathematical characterization module for mathematically characterizing multiple features of the typical additive model during the additive manufacturing process by establishing a quantization relationship between the vector operators and the multi-feature data, generating mathematical characterization vectors; and a vector classification module for classifying the characterization vectors of different parts of a complex additive model based on the mathematical characterization vectors. The system classifies quantities and generates vector classification results; a modular deconstruction module for constituent units is used to perform modular deconstruction of the complex additive model based on the vector classification results, generating multiple modular deconstruction unit categories applicable to multi-variety additive models; an expert system establishment module is used to obtain the optimal auxiliary electromagnetic field and additive process of typical modular deconstruction units, and establish a multi-mode electromagnetic field optimization expert system containing multi-variety deconstruction units in combination with the multiple modular deconstruction unit categories; an adaptive equilibrium control module is used to perform target deconstruction and adaptive electromagnetic field equilibrium control on the target additive model based on the multi-mode electromagnetic field optimization expert system.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] This application provides a method and system for equalization control of metals in multi-mode electromagnetic field-assisted additive manufacturing, which relates to the field of intelligent control technology. It establishes vector operators for the geometric features of the additive part model, collects multi-feature data under the assistance of multi-mode electromagnetic fields, and quantifies the relationship between the two to generate a mathematical characterization vector. Based on this vector, complex additive models are classified and modularly deconstructed, forming multiple types of deconstruction unit categories. Combining the optimal auxiliary electromagnetic field and additive manufacturing process, an expert system is established to achieve target deconstruction and adaptive equalization control of the electromagnetic field. This solves the technical problem of existing additive manufacturing technologies struggling to accurately control the molten pool flow and solidification process of different parts of complex structural parts, affecting forming quality and efficiency. It achieves the technical effect of improving the forming quality and manufacturing efficiency of complex structural parts through dynamic adaptive equalization control of multi-mode electromagnetic fields, adjusting electromagnetic field parameters in real time according to different geometric features. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 A schematic flowchart of a method for equalization control of metals in multi-mode electromagnetic field-assisted additive manufacturing provided in an embodiment of this application;

[0010] Figure 2 A schematic diagram of the equalization control system structure for multi-mode electromagnetic field-assisted additive manufacturing of metals provided in an embodiment of this application;

[0011] Figure 3 A schematic diagram of the multi-mode electromagnetic field optimization expert system in the equalization control system for multi-mode electromagnetic field assisted additive manufacturing of metals provided in the embodiments of this application.

[0012] Figure labeling: Vector operator establishment module 11, multi-feature data acquisition module 12, mathematical characterization module 13, vector classification module 14, modular deconstruction module of constituent units 15, expert system establishment module 16, adaptive equilibrium control module 17. Detailed Implementation

[0013] This application provides a method and system for equalization control of metals in multi-mode electromagnetic field-assisted additive manufacturing, which is used to solve the technical problem that existing additive manufacturing technologies are unable to accurately control the flow and solidification process of the molten pool in different parts of complex structural parts, thus affecting the forming quality and efficiency.

[0014] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0015] It should be noted that the terms "first," "second," etc., in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to such processes, methods, products, or devices.

[0016] Example 1, as Figure 1 As shown, this application provides a method for equalization control of metals in multi-mode electromagnetic field-assisted additive manufacturing, the method comprising:

[0017] P10: Establish vector operators to describe the geometric features of the additive part model.

[0018] Specifically, the geometric features of the additive manufacturing model are quantitatively described, and vector operators describing the geometric features of the additive manufacturing model are established so that the additive manufacturing process can be precisely controlled based on these features.

[0019] Specifically, the geometric features of an additive manufacturing model include, but are not limited to, its dimensions, shape, wall thickness, and cross-sectional variations. These features have a significant impact on melt flow, solidification rate, and final forming quality during additive manufacturing. Vector operators are mathematical tools used to transform complex geometric features into quantifiable vector forms. By defining a series of vector operators, the geometric features of an additive manufacturing model can be decomposed and quantified. For example, a dimension vector can be used to describe the length, width, and height of the additive manufacturing model; a shape vector can be used to describe the contour and shape features of the additive manufacturing model; a wall thickness vector can be used to describe the wall thickness distribution of the additive manufacturing model; and a cross-sectional vector can be used to describe the cross-sectional shape and dimensional variations of the additive manufacturing model.

[0020] In developing vector operators, the characteristics and requirements of additive manufacturing processes must be considered. For example, in arc additive manufacturing, the flow and solidification of the molten pool are significantly influenced by the geometric features of the additive part model. Therefore, the design of vector operators should reflect the impact of these features on the flow and solidification processes. Quantitative descriptions of the geometric features of the additive part model can provide fundamental data support for subsequent multi-feature data acquisition and mathematical characterization.

[0021] Furthermore, the establishment of vector operators also requires consideration of specific additive manufacturing equipment and technical parameters. For example, in laser additive manufacturing, the scanning path and energy distribution of the laser beam have a significant impact on the forming quality of the additive part. Therefore, the design of vector operators should be able to match the scanning path and energy distribution of the laser beam in order to achieve precise control of the additive manufacturing process.

[0022] By defining appropriate vector operators, complex geometric features can be transformed into quantifiable vector forms, providing important data support and technical assurance for subsequent multi-feature data acquisition, mathematical characterization, and adaptive equilibrium control of electromagnetic fields.

[0023] P20: Collect multi-feature data of a typical additive model under the assistance of longitudinal and transverse bidirectional multi-mode electromagnetic fields.

[0024] Optionally, acquiring multi-feature data of typical additive manufacturing models under the assistance of longitudinal and transverse bidirectional multi-mode electromagnetic fields is a key step in achieving precise control and optimization of the additive manufacturing process. This process involves real-time monitoring and data acquisition of various physical phenomena and process parameters during additive manufacturing, providing fundamental data support for subsequent mathematical characterization and adaptive control.

[0025] Multi-mode electromagnetic fields refer to the application of different types of electromagnetic fields (such as DC electromagnetic fields, AC electromagnetic fields, pulsed electromagnetic fields, and composite electromagnetic fields) to assist the additive manufacturing process. These electromagnetic fields can improve the flow characteristics of the molten pool, promote uniform material distribution, reduce defect generation, and improve forming quality. Bidirectional multi-mode electromagnetic fields refer to electromagnetic fields acting not only in the horizontal (lateral) direction but also in the vertical (longitudinal) direction during additive manufacturing, thereby achieving comprehensive control over the flow and solidification process of the molten pool. Typical additive manufacturing models refer to representative additive manufacturing models in practical applications, covering common geometric features (such as size, shape, wall thickness, cross-sectional variations, etc.). By studying these typical additive manufacturing models, general control strategies applicable to various complex structures can be summarized.

[0026] The acquired multi-feature data refers to various physical quantities and process parameters related to additive manufacturing quality. These data include, but are not limited to, temperature distribution data, fluid flow data, solidification rate data, and time parameter data. Temperature distribution data is obtained by monitoring the temperature distribution of the molten pool and surrounding area in real time during the additive manufacturing process using sensors such as thermal imagers or thermocouples. This is crucial for understanding the formation and solidification process of the molten pool. Fluid flow data monitors the flow velocity and direction of the fluid within the molten pool using high-speed cameras or laser Doppler velocimeters, which helps optimize electromagnetic field parameters for better flow control. Solidification rate data is obtained by observing and recording the solidification rate of the molten pool using optical or electron microscopes, which is significant for controlling the microstructure and properties of the additive parts. Time parameter data records time parameters during the additive manufacturing process, such as the forming time of each layer and the switching time of the electromagnetic field, which helps optimize the efficiency and quality of additive manufacturing.

[0027] To ensure the accuracy and reliability of the acquired data, high-precision sensors and advanced data acquisition systems are required. For example, high-precision thermocouples or thermal imagers can be used to monitor the temperature distribution of the molten pool in real time; laser Doppler velocimeters or high-speed cameras can accurately measure the flow velocity and direction of the fluid within the molten pool; and optical or electron microscopes can be used to observe and record the solidification process of the molten pool. Simultaneously, high-performance data acquisition cards and real-time processing software enable rapid acquisition and processing of sensor data, ensuring the real-time nature and accuracy of the data.

[0028] To ensure the data is quantifiable and traceable, the aforementioned multi-feature data must be bound one-to-one with the spatial location and geometric vector operators of the corresponding model components, forming a mapping relationship between structure and response. This high-dimensional, multi-modal data will provide a solid data foundation for the subsequent mathematical characterization of additive features, the optimization analysis of multi-mode electromagnetic fields, and the construction of expert systems, ensuring that the system possesses high accuracy, adaptability, and scalability.

[0029] P30: By establishing the quantization relationship between the vector operator and the multi-feature data, multiple features in the additive manufacturing process of a typical additive manufacturing model are mathematically characterized, generating a mathematical characterization vector.

[0030] It should be understood that by establishing the quantitative relationship between vector operators and multi-feature data, multiple features in the additive manufacturing process of a typical additive manufacturing model can be mathematically characterized, generating mathematical characterization vectors. In other words, by constructing a clear function mapping relationship, the vector operators describing geometric features are coupled with the multi-physical feature data collected under the assistance of multi-mode electromagnetic fields for calculation, thereby realizing the mathematical expression of the additive manufacturing process features and outputting them in a unified vector form for subsequent classification and control.

[0031] Specifically, the core of this step is to establish a quantification relationship, combining the vector operators describing the geometric features of the additive manufacturing model with the collected multi-feature data to generate a mathematical characterization vector that comprehensively reflects multiple features in the additive manufacturing process. This quantification relationship can be expressed by the following formula:

[0032]

[0033] Among them, F i Let G represent the mathematical characterization vector of the i-th typical additive manufacturing model region, which is a numerical output describing the physical behavior characteristics of this region during the additive manufacturing process. i =g i1 ,g i2 ,…,g in This is the geometric vector operator for the region, composed of the region's geometric parameters, such as wall thickness, radius of curvature, cross-sectional gradient, aspect ratio, etc., Φ(G i f is the overall quantization mapping function, which is a nonlinear function mapping from the geometric feature space to the physical feature space. j (g i1 ,g i2 ,…,g in ) is the mapping sub-function for the j-th feature data, corresponding to a certain type of response parameter (such as temperature gradient, cooling rate, molten pool flow rate, etc.), w jis the weight coefficient of the j-th type feature in the total characterization vector, which can be determined by expert system experience, entropy weighting method or training data fitting results, m is the number of features included in the model (i.e. the number of data dimensions), and n is the number of dimensions of the geometric vector operator.

[0034] By establishing the aforementioned quantification relationships, the geometric and physical characteristics of the additive manufacturing process can be comprehensively quantified to generate a mathematical characterization vector. This mathematical characterization vector provides an important theoretical foundation for subsequent adaptive control, enabling the additive manufacturing process to be dynamically adjusted and optimized based on real-time monitored geometric and physical characteristic data. For example, if abnormalities occur in the real-time monitored temperature distribution data or fluid flow data during additive manufacturing, these abnormalities can be corrected by adjusting the electromagnetic field parameters, thereby ensuring the stability of the additive manufacturing process and the forming quality.

[0035] P40: Based on the mathematical characterization vectors, classify the characterization vectors of different parts of the complex additive model and generate vector classification results.

[0036] Specifically, based on the aforementioned mathematical characterization vectors, the characterization vectors of different parts of the complex additive model are classified to generate vector classification results, aiming to leverage the mathematical characterization vector F constructed above. i This allows for the identification and differentiation of the response characteristics of different regions in a complex additive manufacturing model during the additive manufacturing process, thereby enabling the classification of modular additive manufacturing features and the preparatory work for structural optimization control.

[0037] In additive manufacturing, different parts of a complex additive model often possess different geometric and physical characteristics. For example, some parts may have thicker walls, while others may have complex shapes or smaller cross-sectional areas. These different characteristics lead to variations in physical phenomena such as melt flow and solidification rate during additive manufacturing, thus affecting the forming quality and performance. Therefore, classifying the characterization vectors of different parts of a complex additive model can provide a targeted basis for subsequent adaptive control.

[0038] In the specific implementation process, the entire complex additive model first needs to be divided into several independent regional units according to a preset geometric grid or block strategy. For each region, the corresponding geometric vector operator is extracted, and the mathematical characterization vector is obtained through the aforementioned quantization mapping function. Subsequently, unsupervised or semi-supervised classification algorithms based on distance metrics are used to perform clustering analysis or similarity classification on all vectors. Commonly used methods include K-Nearest Neighbors (K-NN), Support Vector Machine (SVM), K-means clustering, and density clustering (DBSCAN).

[0039] Taking the K-NN algorithm as an example, a standard sample set is first established, which contains known mathematical characterization vectors of different typical additive manufacturing regions and their corresponding class labels. For any characterization vector F to be classified... i Calculate the Euclidean distance or cosine similarity between the vector and all vectors in the standard sample set, select the K closest samples, and calculate the most frequent class label among them as the predicted classification for the current vector. The classification result can be expressed as:

[0040] Among them, C i c is the category label corresponding to the i-th region. k Let δ(c) represent the category label of the k-th nearest neighbor. k =c) is an indicator function.

[0041] The generated vector classification results not only identify the behavioral characteristics of different regions during the additive manufacturing process, such as heat input sensitive areas, unstable molten pool areas, and high-risk areas for solidification shrinkage, but also serve as key index information for modular deconstruction and electromagnetic field configuration optimization in subsequent steps, enabling precise, on-demand control at the structural level. Therefore, this classification process not only has an identification function but also forms the basis for systematic process matching decisions; its accuracy and robustness directly affect the overall system's control performance and manufacturing quality.

[0042] This classification process allows for the categorization of different parts of a complex additive manufacturing model into distinct categories, each possessing similar geometric and physical characteristics. This classification provides a crucial basis for subsequent adaptive control, enabling the additive manufacturing process to implement differentiated control strategies based on the unique characteristics of different parts. For example, for parts with thicker walls, the electromagnetic field intensity can be appropriately increased to improve molten pool flow; for parts with complex shapes, the electromagnetic field frequency can be adjusted to optimize forming quality. Therefore, this classification step is of great significance in the equilibrium control method of multi-mode electromagnetic field-assisted additive manufacturing of metals, laying the foundation for refined and intelligent control of the additive manufacturing process.

[0043] P50: Based on the vector classification results, perform modular deconstruction of the constituent units of the complex additive manufacturing model to generate multiple modular deconstruction unit categories applicable to multi-variety additive manufacturing models.

[0044] Optionally, based on the vector classification results, the constituent units of the complex additive model are modularly deconstructed to generate multiple modular deconstruction unit categories applicable to various additive models. The aim is to restructure the originally continuous, complex, and structurally heterogeneous additive model according to its additive response characteristics based on the preceding mathematical characterization and classification results, thereby realizing the functional area division of components and the standardization of process paths, and providing a basic unit-level carrier for the subsequent optimization configuration of multi-mode electromagnetic fields and expert system matching.

[0045] Specifically, firstly, the classification label C is determined based on the characterization vector of each local region obtained in step P40. i Regions with similar or identical additive manufacturing characteristics are grouped into the same category. Each category can be considered a "modular deconstruction unit," which exhibits high consistency in geometric features, electromagnetic response, and thermal behavior, making it suitable for unified additive manufacturing strategies and electromagnetic field control parameters. For example, standard module categories such as "thin-walled rapid cooling unit," "thick-walled thermal retention unit," "sharp-corner easily cracked unit," and "variable cross-section multi-gradient stress unit" can be formed.

[0046] To ensure the accuracy and engineering practicality of the modular deconstruction, logical adjacency judgment and combination optimization can be performed by combining spatial continuity, boundary adjacency rules, and structural constraints to ensure that adjacent regions have complete boundaries, manufacturability, and process independence. During the deconstruction process, each modular unit will be accompanied by the following information: ① geometric structure sub-model (i.e., the geometric boundary volume containing the region); ② corresponding geometric vector operator; ③ corresponding mathematical characterization vector; ④ classification label; ⑤ preliminary recommended electromagnetic field-assisted strategy and additive manufacturing path suggestions.

[0047] Ultimately, this modular deconstruction process generates a modular unit database for complex models with multiple varieties and structures, namely, a "multi-variety additive manufacturing model modular deconstruction unit category set." This structured classification system possesses excellent reusability, retrieval capabilities, and process adaptability, becoming a key interface module for subsequent expert system establishment and control strategy generation. It also provides theoretical support and technical carrier for multi-mode electromagnetic field zoning and process refinement of complex components. This modular deconstruction process provides an important foundation for subsequent adaptive control, enabling the additive manufacturing process to implement differentiated control strategies based on the characteristics of different modules. For example, for modules with larger wall thicknesses, the electromagnetic field intensity can be appropriately increased to improve molten pool flow; for modules with complex shapes, the electromagnetic field frequency can be adjusted to optimize forming quality. Therefore, this modular deconstruction step is of great significance in the equilibrium control method of multi-mode electromagnetic field-assisted additive manufacturing of metals, laying a solid foundation for achieving refined and intelligent control of the additive manufacturing process.

[0048] P60: Obtain the optimal auxiliary electromagnetic field and additive manufacturing process for typical modular deconstruction units, and establish a multi-mode electromagnetic field optimization expert system that includes multiple types of deconstruction units, based on the aforementioned multiple modular deconstruction unit categories.

[0049] Furthermore, such as Figure 3 As shown, the multi-mode electromagnetic field optimization expert system includes:

[0050] The system includes a data storage module for storing the optimal auxiliary electromagnetic field and additive manufacturing process parameters for typical modular deconstruction units; a model decomposition module for decomposing the target additive body model into multiple basic modular units and extracting the additive model feature vector for each basic modular unit; a query and matching module for retrieving the optimal auxiliary electromagnetic field and additive manufacturing process parameters that match the input additive model feature vector, and generating a combined additive body model of the target deconstruction units; an analysis and optimization module for analyzing the influence of multi-mode electromagnetic auxiliary fields in arc additive manufacturing of multiple deconstruction units and outputting the influence analysis results; and a control strategy generation module for generating an adaptive electromagnetic field equilibrium control strategy based on the influence analysis results.

[0051] It should be understood that by obtaining the optimal auxiliary electromagnetic field and corresponding additive process parameters of typical modular deconstruction units, and combining them with the previously classified multiple modular deconstruction unit categories, a multi-mode electromagnetic field optimization expert system for multiple types of deconstruction units can be further established. The aim is to achieve knowledge matching and intelligent reasoning between different geometric feature regions and the optimal process path and electromagnetic field excitation mode, thereby constructing a data-driven adaptive control core in the additive manufacturing process.

[0052] Specifically, obtaining the optimal auxiliary electromagnetic field for typical modular units mainly relies on the accumulation and analysis of a large amount of experimental and simulation data. For each type of modular unit, through multiple rounds of electromagnetic field-assisted additive manufacturing experiments, the forming quality, microstructure, and process stability under different electromagnetic field frequencies, intensities, phase structures, and directional superposition conditions are analyzed. Then, the optimal parameter combination within a given additive manufacturing process window is extracted. This parameter set includes, but is not limited to, electromagnetic field mode type (such as low-frequency AC / high-frequency pulse / composite orthogonal field), amplitude range, frequency range, application direction, heat source power, scanning speed, wire / powder feeding rate, etc., constituting an optimized mapping of "additive response-control parameters".

[0053] Based on this, the established multi-mode electromagnetic field optimization expert system not only undertakes information storage and retrieval functions, but also possesses model recognition, knowledge reasoning, and strategy generation capabilities. This expert system specifically includes the following functional modules:

[0054] Data storage module: Used to store the optimal auxiliary electromagnetic field parameters and additive manufacturing process configurations corresponding to each type of typical modular deconstruction unit, including historical data, experimental records, simulation results, etc., forming a knowledge sample base oriented towards structure type.

[0055] Model decomposition module: After receiving the target complex additive model input, it automatically calls vector operators and mathematical characterization rules to decompose it into multiple basic module units, and extracts the feature vector of each unit as matching input.

[0056] Query and Matching Module: Receives the feature vector output by the model decomposition module, retrieves the closest matching record by calculating the similarity index (such as Euclidean distance, cosine similarity, etc.) with the module units stored in the database, and outputs the optimal auxiliary electromagnetic field and additive manufacturing process configuration.

[0057] Analysis and Optimization Module: Based on the completion of unit-level matching, further analyze the electromagnetic field interaction mechanism under the combination of multiple modules, identify possible coupling interference, thermal field concentration or stress accumulation problems, establish a multi-unit combination response model based on physical laws and empirical rules, and output the analysis results of the impact on the overall system performance.

[0058] The control strategy generation module, based on the combined influence results provided by the analysis and optimization module and considering the geometric continuity and process constraints of the target structure, generates an adaptive electromagnetic field equilibrium control strategy adapted to the current target additive manufacturing model. This strategy includes spatial distribution parameters, time-series strategies, and real-time adjustment thresholds, which are then implemented by the downstream control system. This step, by coupling the modular deconstruction results with typical optimal process knowledge, completes the systematic mapping from "additive model geometric characteristics" to "electromagnetic field configuration decisions," serving as a key supporting unit for achieving closed-loop control throughout the high-performance additive manufacturing process of complex structural components. This expert system possesses excellent scalability and versatility, making it suitable for additive manufacturing tasks of complex metal structures in various product types and application scenarios.

[0059] P70: Based on the multi-mode electromagnetic field optimization expert system, target deconstruction and electromagnetic field adaptive equilibrium control are performed on the target additive model.

[0060] Furthermore, step P70 in this embodiment of the application also includes:

[0061] P71: Based on the multi-mode electromagnetic field optimization expert system, the target additive model is deconstructed to generate a target deconstruction unit combined additive model; P72: Using the TOPSIS algorithm, a multi-level modular integrated electromagnetic field suitable for the target deconstruction unit combined additive model is designed; P73: The spatial magnetic field strength of the multi-level modular integrated electromagnetic field is measured to establish a multi-mode integrated electromagnetic field spatial distribution model; P74: Based on the multi-mode integrated electromagnetic field spatial distribution model, a dynamic polling algorithm is used to perform real-time adaptive equilibrium control of the integrated electromagnetic field for the geometric vector operator of the model during the additive manufacturing process.

[0062] Optionally, based on the multi-mode electromagnetic field optimization expert system, target deconstruction and electromagnetic field adaptive equilibrium control are performed on the target additive model. The aim is to actually deploy the optimal auxiliary electromagnetic field strategy matched by the aforementioned expert system into the specific target additive model, complete the entire process of transformation from "theoretical configuration" to "on-site application", and achieve adaptive equilibrium control with minimal electromagnetic interference and optimal response among multiple module units.

[0063] Specifically, after receiving the target additive model input, the system first invokes the model decomposition module and query matching module of the multi-mode electromagnetic field optimization expert system to structurally deconstruct the target model. This involves breaking down the overall model into several basic module units. Based on the geometric vector operator and characterization vector of each unit, the system retrieves the most relevant electromagnetic field and process parameters, ultimately forming a "target deconstructed unit combined additive model." This model not only preserves the construction logic of the original structure but also assigns an independent control strategy interface to each module, forming the basic framework for multi-module integrated control.

[0064] Next, the TOPSIS multi-objective optimization algorithm is used to integrate all matched modular deconstruction units and their corresponding electromagnetic field parameters at the system level. The TOPSIS method defines the ideal optimal solution and the worst solution, calculates the distance difference between each candidate electromagnetic field configuration combination and the ideal solution, and selects the optimal solution based on relative proximity ranking. This method ensures that, while considering the performance indicators of multiple modules (such as forming stability, energy input uniformity, and heat-affected zone control), a globally optimal "multi-level modular integrated electromagnetic field" application scheme is designed, specifically including the combination of parameters such as the application position, electromagnetic field type, frequency, and intensity of each unit.

[0065] Furthermore, to achieve precise control and establish a subsequent feedback loop, it is necessary to measure the spatial response of the multi-level modular integrated electromagnetic field after actual application and construct a spatial magnetic field intensity distribution model. The spatial distribution model can be represented by the following mathematical expression:

[0066] Where B(x,y,z,t) represents the magnetic field strength vector at any spatial position (x,y,z) at any time t. i (x,y,z) is the magnetic field intensity distribution function of the i-th modular unit under static conditions, γ i (t) represents the time control coefficient (i.e., the dynamic excitation function), and M is the total number of deconstruction elements. The above model, combining the principle of magnetic field superposition and the timing control function, reflects the combined effect of multiple electromagnetic sources in space and time.

[0067] Based on the established spatial magnetic field distribution model, the system employs a dynamic polling algorithm to perform real-time adaptive control of the electromagnetic field application to each module unit during the additive manufacturing process. The polling algorithm periodically acquires the geometric vector operator sampling results at each position of the current model, analyzes their changing trends, determines whether there are geometric feature transformations (such as abrupt changes in thickness or curvature), and dynamically adjusts the excitation coefficient γ in the electromagnetic field spatial model accordingly. i (t) is used to adjust parameters such as electromagnetic field strength, frequency and phase in real time, thereby ensuring that each stage of the additive manufacturing process is in the optimal auxiliary state and avoiding process problems such as uneven heat and unstable molten pool caused by static configuration.

[0068] Through the coordinated implementation of the above steps, this invention can realize a real-time closed-loop control system for electromagnetic fields driven by an expert system, ensuring that the additive manufacturing process of complex structures has high responsiveness, adaptability and multi-module synergy, and providing key technical guarantees for the consistency and reliability of high-performance metal components.

[0069] Furthermore, step P72 in this embodiment of the application also includes:

[0070] P71-1: Decompose the target additive model into multiple basic module units; P71-2: Based on the additive model feature vector of each basic module unit, select the corresponding optimal auxiliary electromagnetic field and additive process to generate the target deconstruction unit combined additive model.

[0071] Specifically, the process of target deconstruction based on a multi-mode electromagnetic field optimization expert system can be described in more detail, including the decomposition of the target additive body model and the selection of the optimal auxiliary electromagnetic field and additive process parameters according to the feature vector of each basic module unit, thereby generating a target deconstruction unit combined additive body model.

[0072] First, the model decomposition module in the expert system is used to perform structural analysis on the input target additive model. A 3D CAD model preprocessing and geometric feature extraction algorithm is employed to divide the overall model into multiple basic modular units. Each basic modular unit refers to the smallest structural sub-block with internal consistency in terms of geometric continuity, additive path planning, and process response characteristics. The partitioning method can combine indicators such as spatial partitioning, geometric gradient change, curvature threshold, and abrupt cross-section changes, and modular partitioning can be achieved through mesh division or algorithms oriented towards solid boundaries. For example, for target models with alternating thicknesses, corners, concave cavities, and thin columns, different regions will be cut and independently identified as basic modular units in this step, establishing a spatial topology mapping and unit index table.

[0073] Next, for each identified basic module unit, its corresponding geometric feature vector is extracted and used as input to call the multi-mode electromagnetic field optimization expert system. By performing feature matching with the established database of typical module deconstruction units, the optimal auxiliary electromagnetic field application method and corresponding additive manufacturing process parameters are retrieved. This matching process is based on the aforementioned feature space distance measurement mechanism, such as Euclidean distance or cosine similarity criteria, and can set weight coefficients to prioritize matching key process features (such as temperature sensitivity, flow response, etc.). The system outputs the matching results to the target model, realizing the mapping and assignment from geometric structure to process control parameters. Finally, several matched and assigned basic module units are combined to form a "target deconstruction unit combined additive manufacturing model." This model not only maintains the consistency of the original components at the structural level but also injects targeted optimal electromagnetic fields and additive manufacturing strategies into each module unit at the control level, laying a complete foundation for subsequent TOPSIS optimization combination and dynamic control strategy deployment.

[0074] This process fully utilizes the intelligent functions of the multi-mode electromagnetic field optimization expert system, combined with advanced feature analysis and matching technologies, providing strong support for the refined and intelligent control of the additive manufacturing process.

[0075] Furthermore, step P72 in this embodiment of the application also includes:

[0076] P72-1: Determine the positive and negative ideal solutions of the multimode electromagnetic field; P72-2: Calculate the degree of closeness between the multimode electromagnetic field of each deconstruction unit combined additive model and the positive and negative ideal solutions; P72-3: Based on the degree of closeness, select the optimal combination of multimode electromagnetic fields as the multi-level modular integrated electromagnetic field.

[0077] In one possible embodiment of this application, the TOPSIS algorithm is used to design a multi-level modular integrated electromagnetic field suitable for the target deconstruction unit combination additive model. This process involves not only determining the ideal solution of the multi-mode electromagnetic field, but also calculating the approximation of the electromagnetic field of each deconstruction unit combination additive model to the ideal solution, and selecting the optimal electromagnetic field combination.

[0078] Specifically, firstly, an evaluation index system for multi-mode electromagnetic field configurations is constructed, and based on system performance objectives, the positive and negative ideal solutions of the multi-mode electromagnetic fields are determined. A positive ideal solution refers to the ideal electromagnetic field combination that achieves the best additive manufacturing effect in the multi-mode electromagnetic field parameter space; while a negative ideal solution refers to the electromagnetic field combination that is the worst relative to the best effect. By defining positive and negative ideal solutions, clear reference standards can be provided for subsequent electromagnetic field optimization. Positive ideal solutions typically correspond to optimal additive manufacturing performance, such as the minimum defect rate, optimal melt pool flow characteristics, and the highest forming accuracy; while negative ideal solutions correspond to the worst performance. The determination of these two extreme solutions provides a benchmark for evaluating the merits of different electromagnetic field combinations.

[0079] After determining the positive and negative ideal solutions, the next step is to calculate the proximity of the multimode electromagnetic fields of each deconstructed unit composite additive model to the positive and negative ideal solutions. This process is achieved by quantifying the distance between each electromagnetic field combination and the positive and negative ideal solutions, which can be calculated using Euclidean distance or other suitable distance metrics. Specifically, for each deconstructed unit composite additive model, the distance between its multimode electromagnetic field parameters and the positive ideal solution, as well as the distance to the negative ideal solution, is calculated. The ratio or difference between these two distances can be used to measure the quality of the electromagnetic field combination. Electromagnetic field combinations that are close to the positive ideal solution are considered better, while those that are close to the negative ideal solution are considered worse.

[0080] Based on the calculated proximity, the optimal multi-mode electromagnetic field combination is selected as the multi-level modular integrated electromagnetic field. This selection process is based on evaluating the merits of each electromagnetic field combination, choosing the one closest to the positive ideal solution. The selected optimal electromagnetic field combination achieves the best additive manufacturing effect in a given deconstructed unit combination additive body model. In this way, it can be ensured that the configuration of the electromagnetic field in different deconstructed unit combinations can optimize the additive manufacturing process to the greatest extent, improving forming quality and efficiency.

[0081] Through the above steps, the optimized design of the multi-level modular integrated electromagnetic field for the target deconstruction unit combined additive model was achieved. This process fully utilizes the advantages of the TOPSIS algorithm, ensuring that the multi-module combined model achieves optimal balance of multiple indicators at the overall performance level, while providing a systematic decision-making basis and process adaptability for the multi-mode electromagnetic field configuration. This is one of the core technical paths to achieve the high-performance additive manufacturing goal of this invention.

[0082] Furthermore, step P74 in this embodiment of the application also includes:

[0083] P74-1: Periodically sample the vector operators of the target additive model during the additive manufacturing process to obtain the operator sampling results; P74-2: Calculate the vector operator deviation based on the operator sampling results; P74-3: Dynamically adjust the model parameters of the multi-mode integrated electromagnetic field spatial distribution model based on the vector operator deviation to perform electromagnetic field equilibrium control and real-time matching with the geometric features of the target additive model.

[0084] Optionally, based on a multi-mode integrated electromagnetic field spatial distribution model, a dynamic polling algorithm is used for real-time adaptive equilibrium control. This process involves periodically sampling the vector operators of the target additive model during the additive manufacturing process, calculating the vector operator deviation, and dynamically adjusting the spatial distribution model of the electromagnetic field according to the deviation, so as to achieve real-time matching between the electromagnetic field and the geometric features of the target additive model.

[0085] Specifically, the first step is to periodically sample the vector operators of the target additive model during the additive manufacturing process to obtain the operator sampling results. This process is achieved through high-precision sensors and a data acquisition system, ensuring that the geometric feature changes of the model during additive manufacturing can be acquired in real time. The periodic sampling of the vector operators provides real-time data on the geometric features of the additive model, such as its size, shape, wall thickness, and cross-sectional changes, laying the foundation for subsequent deviation calculations and electromagnetic field adjustments.

[0086] After obtaining the operator sampling results, the next step is to calculate the vector operator bias based on these results. Vector operator bias refers to the difference between the currently sampled vector operator and the preset or expected vector operator. By calculating the bias, the gap between the actual state and the target state of the model's geometric features during additive manufacturing can be quantified. Bias can be calculated using various mathematical methods, such as Euclidean distance, Mahalanobis distance, or other suitable distance metrics. The magnitude and direction of the bias provide crucial information for subsequent electromagnetic field adjustments.

[0087] Based on the calculated vector operator deviation, the model parameters of the multi-mode integrated electromagnetic field spatial distribution model are dynamically adjusted to achieve electromagnetic field equilibrium control and real-time matching with the geometric features of the target additive model. This process is realized through a feedback control system, which adjusts parameters such as the intensity, frequency, and phase of the electromagnetic field according to the magnitude and direction of the deviation to optimize physical phenomena such as molten pool flow and solidification rate, thereby achieving real-time matching between the geometric features of the additive model and the target features. The dynamic adjustment process can employ PID control, fuzzy control, or other advanced control algorithms to ensure that the electromagnetic field adjustment can respond quickly and accurately to changes in geometric features during the additive manufacturing process.

[0088] This process fully leverages the advantages of dynamic polling algorithms, enabling real-time perception and response adjustment of dynamic changes in additive components. This ensures that the multi-mode electromagnetic field and structural evolution process remain in an adaptive state, thereby improving forming stability, microstructure uniformity, and manufacturing precision.

[0089] Furthermore, step P74-3 of the embodiments of this application also includes:

[0090] P74-31: Calculate the electromagnetic field parameter adjustment amount based on the vector operator deviation; P74-32: Dynamically adjust the intensity, frequency, and phase of the electromagnetic field based on the electromagnetic field parameter adjustment amount to generate an adaptive equalization control strategy for the electromagnetic field; P74-33: Based on the adaptive equalization control strategy for the electromagnetic field, perform equalization control of the electromagnetic field and real-time matching with the geometric features of the target additive model.

[0091] Specifically, the electromagnetic field parameters are dynamically adjusted based on the vector operator deviation to generate an adaptive equilibrium control strategy for the electromagnetic field, and to achieve real-time matching between the electromagnetic field and the geometric features of the target additive model.

[0092] First, the adjustment amount of the electromagnetic field parameters is calculated based on the vector operator deviation. The vector operator deviation reflects the difference between the geometric features of the current additive model and the target features. By analyzing these deviations, it can be determined what adjustments to the electromagnetic field parameters are needed to reduce this difference. Specifically, the calculation of the electromagnetic field parameter adjustment amount can be based on the following formula:

[0093] ΔP = K·E; where ΔP is the adjustment amount of the electromagnetic field parameters, including intensity adjustment, frequency adjustment, and phase adjustment. K is the adjustment coefficient matrix, used to convert the vector operator deviation into specific electromagnetic field parameter adjustments. E is the vector operator deviation, representing the difference between the current geometric feature and the target feature. The adjustment coefficient matrix K can be optimized using experimental data or machine learning methods to ensure that the adjustment amount effectively reduces the deviation.

[0094] Based on the calculated electromagnetic field parameter adjustments, the intensity, frequency, and phase of the electromagnetic field are dynamically adjusted. For example, if the vector operator deviation indicates insufficient molten pool flow or uneven wall thickness, the electromagnetic field intensity can be increased to improve molten pool flow characteristics. Conversely, if the molten pool flow is too strong, the electromagnetic field intensity can be appropriately reduced. The electromagnetic field frequency is adjusted according to changes in the geometric features of the additive model to optimize the solidification rate and flow characteristics of the molten pool. For example, for complex shapes, the frequency can be appropriately increased to improve detail forming. By adjusting the electromagnetic field phase, fine-tuning of the molten pool flow direction can be achieved, thereby better adapting to changes in the geometric features of the additive model. These adjustments generate an adaptive electromagnetic field equalization control strategy, which dynamically adjusts the electromagnetic field parameters based on real-time monitored changes in geometric features to optimize the additive manufacturing process.

[0095] P74-33: Based on the electromagnetic field adaptive equalization control strategy, perform equalization control of the electromagnetic field and real-time matching of the geometric features of the target additive model.

[0096] Based on the generated adaptive equalization control strategy for the electromagnetic field, equalization control of the electromagnetic field is performed to ensure real-time matching between the electromagnetic field and the geometric features of the target additive model. For example, high-precision sensors are used to monitor changes in the geometric features of the model in real time during the additive manufacturing process, acquiring the latest vector operator data. Based on the real-time monitoring data, the deviation between the current geometric features and the target features is calculated. Based on the deviation calculation results, the intensity, frequency, and phase of the electromagnetic field are dynamically adjusted to ensure that the electromagnetic field parameters are always in an optimal state. Through a feedback mechanism, the electromagnetic field parameter adjustment strategy is continuously optimized to ensure the stability of the additive manufacturing process and the forming quality.

[0097] Through the above steps, real-time monitoring and dynamic adjustment of the electromagnetic field of the target additive model during the additive manufacturing process are achieved. This real-time adaptive equilibrium control method not only improves the stability and forming quality of the additive manufacturing process, but also enhances the system's adaptability to complex geometric features and dynamically changing process conditions.

[0098] In summary, the embodiments of this application have at least the following technical effects:

[0099] This application establishes a vector operator for the geometric features of the additive manufacturing model and collects multi-feature data under the assistance of multi-mode electromagnetic fields, quantifying the relationship between the two to generate a mathematical characterization vector. Based on this vector, complex additive manufacturing models are classified and modularly deconstructed, forming multiple categories of deconstruction units. By combining these categories to obtain the optimal auxiliary electromagnetic field and additive manufacturing process, a multi-mode electromagnetic field optimization expert system is constructed, thereby achieving target deconstruction and adaptive electromagnetic field equilibrium control of the target additive manufacturing model.

[0100] The technology achieves the effect of improving the forming quality and manufacturing efficiency of complex structural parts by dynamically adaptively equalizing and controlling the electromagnetic field in multiple modes and adjusting the electromagnetic field parameters in real time according to different geometric features.

[0101] Example 2, based on the same inventive concept as the multi-mode electromagnetic field-assisted additive manufacturing metal equalization control method in the foregoing examples, such as... Figure 2 As shown, this application provides a multi-mode electromagnetic field-assisted additive manufacturing equalization control system for metals. The system and method embodiments in this application are based on the same inventive concept. The system includes:

[0102] Vector operator creation module 11 is used to create vector operators that describe the geometric features of the additive part model.

[0103] The multi-feature data acquisition module 12 is used to acquire multi-feature data of a typical additive model under the assistance of longitudinal and transverse bidirectional multi-mode electromagnetic fields.

[0104] The mathematical characterization module 13 is used to mathematically characterize multiple features in the additive manufacturing process of a typical additive manufacturing model by establishing the quantization relationship between the vector operator and the multi-feature data, and to generate a mathematical characterization vector.

[0105] The vector classification module 14 is used to classify the characterization vectors of different parts of the complex additive model based on the mathematical characterization vectors, and generate vector classification results.

[0106] The modular deconstruction module 15 is used to perform modular deconstruction of the component units of the complex additive model based on the vector classification results, and generate multiple modular deconstruction unit categories applicable to multi-variety additive models.

[0107] The expert system establishment module 16 is used to obtain the optimal auxiliary electromagnetic field and additive manufacturing process of typical modular deconstruction units, and to establish a multi-mode electromagnetic field optimization expert system that includes multiple types of deconstruction units by combining the multiple modular deconstruction unit categories.

[0108] The adaptive equilibrium control module 17 is used to perform target deconstruction and adaptive electromagnetic field equilibrium control on the target additive model based on the multi-mode electromagnetic field optimization expert system.

[0109] Furthermore, the multi-mode electromagnetic field optimization expert system includes:

[0110] The system includes a data storage module for storing the optimal auxiliary electromagnetic field and additive manufacturing process parameters for typical modular deconstruction units; a model decomposition module for decomposing the target additive body model into multiple basic modular units and extracting the additive model feature vector for each basic modular unit; a query and matching module for retrieving the optimal auxiliary electromagnetic field and additive manufacturing process parameters that match the input additive model feature vector, and generating a combined additive body model of the target deconstruction units; an analysis and optimization module for analyzing the influence of multi-mode electromagnetic auxiliary fields in arc additive manufacturing of multiple deconstruction units and outputting the influence analysis results; and a control strategy generation module for generating an adaptive electromagnetic field equilibrium control strategy based on the influence analysis results.

[0111] Furthermore, the adaptive equalization control module 17 is also used to perform the following steps:

[0112] Based on the aforementioned multi-mode electromagnetic field optimization expert system, the target additive model is deconstructed to generate a target deconstruction unit combined additive model. Using the TOPSIS algorithm, a multi-level modular integrated electromagnetic field suitable for the target deconstruction unit combined additive model is designed. The spatial magnetic field strength of the multi-level modular integrated electromagnetic field is measured to establish a multi-mode integrated electromagnetic field spatial distribution model. Based on the multi-mode integrated electromagnetic field spatial distribution model, a dynamic polling algorithm is used to perform real-time adaptive equilibrium control of the integrated electromagnetic field on the geometric vector operators of the model during the additive manufacturing process.

[0113] Furthermore, the adaptive equalization control module 17 is also used to perform the following steps:

[0114] Determine the positive and negative ideal solutions of the multimode electromagnetic field; calculate the degree of closeness between the multimode electromagnetic field of each deconstruction unit combined additive model and the positive and negative ideal solutions; select the optimal combination of multimode electromagnetic fields as the multi-level modular integrated electromagnetic field based on the degree of closeness.

[0115] Furthermore, the adaptive equalization control module 17 is also used to perform the following steps:

[0116] The vector operators of the target additive model are periodically sampled during the additive manufacturing process to obtain the operator sampling results; the vector operator deviation is calculated based on the operator sampling results; and the model parameters of the multi-mode integrated electromagnetic field spatial distribution model are dynamically adjusted based on the vector operator deviation to achieve electromagnetic field equilibrium control and real-time matching with the geometric features of the target additive model.

[0117] Furthermore, the adaptive equalization control module 17 is also used to perform the following steps:

[0118] Based on the vector operator deviation, the electromagnetic field parameter adjustment amount is calculated; based on the electromagnetic field parameter adjustment amount, the intensity, frequency, and phase of the electromagnetic field are dynamically adjusted to generate an adaptive equalization control strategy for the electromagnetic field; based on the adaptive equalization control strategy for the electromagnetic field, the equalization control of the electromagnetic field is performed and the geometric features of the target additive model are matched in real time.

[0119] Furthermore, the adaptive equalization control module 17 is also used to perform the following steps:

[0120] The target additive model is decomposed into multiple basic module units; based on the additive model feature vector of each basic module unit, the corresponding optimal auxiliary electromagnetic field and additive process are selected to generate the target deconstruction unit combined additive model.

[0121] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0122] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0123] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. A method for equalization control of metals in multi-mode electromagnetic field-assisted additive manufacturing, characterized in that, The method includes: Establish vector operators to describe the geometric features of the additive part model; Collect multi-feature data of a typical additive model under the assistance of longitudinal and transverse bidirectional multi-mode electromagnetic fields; By establishing the quantization relationship between the vector operator and the multi-feature data, multiple features in the additive manufacturing process of a typical additive manufacturing model are mathematically characterized, generating a mathematical characterization vector. Based on the mathematical characterization vectors, the characterization vectors of different parts of the complex additive model are classified to generate vector classification results; Based on the vector classification results, the constituent units of the complex additive manufacturing model are modularly deconstructed to generate multiple modular deconstruction unit categories applicable to multi-variety additive manufacturing models. To obtain the optimal auxiliary electromagnetic field and additive manufacturing process of a typical modular deconstruction unit, and to establish a multi-mode electromagnetic field optimization expert system that includes multiple types of deconstruction units, based on the aforementioned multiple modular deconstruction unit categories. Based on the aforementioned multi-mode electromagnetic field optimization expert system, target deconstruction and adaptive electromagnetic field equilibrium control are performed on the target additive model.

2. The method for equalization control of metals in multi-mode electromagnetic field-assisted additive manufacturing as described in claim 1, characterized in that, Based on the aforementioned multi-mode electromagnetic field optimization expert system, target deconstruction and adaptive electromagnetic field equalization control are performed on the target additive model, including: Based on the multi-mode electromagnetic field optimization expert system, the target additive model is deconstructed to generate a target deconstruction unit combined additive model; Using the TOPSIS algorithm, a multi-level modular integrated electromagnetic field suitable for target deconstruction unit combination additive model is designed; Measure the spatial magnetic field strength of the multi-level modular integrated electromagnetic field and establish a spatial distribution model of the multi-mode integrated electromagnetic field. Based on the multi-mode integrated electromagnetic field spatial distribution model, a dynamic polling algorithm is used to perform real-time adaptive equilibrium control of the integrated electromagnetic field using the geometric vector operator of the model during the additive manufacturing process.

3. The method for equalization control of metals in multi-mode electromagnetic field-assisted additive manufacturing as described in claim 1, characterized in that, The multi-mode electromagnetic field optimization expert system includes: The data storage module is used to store the optimal auxiliary electromagnetic field and additive process parameters of a typical modular deconstruction unit; The model decomposition module is used to decompose the target additive model into multiple basic module units and extract the additive model feature vector of each basic module unit. The query matching module is used to retrieve the optimal auxiliary electromagnetic field and additive process parameters that match the input additive model feature vector, and generate the target deconstruction unit combination additive model. The analysis and optimization module is used to analyze the influence of multi-mode electromagnetic auxiliary fields in multi-variety deconstruction unit arc additive manufacturing and output the influence analysis results. The control strategy generation module is used to generate an electromagnetic field adaptive equilibrium control strategy based on the influence analysis results.

4. The method for equalization control of metals in multi-mode electromagnetic field-assisted additive manufacturing as described in claim 2, characterized in that, Using the TOPSIS approximation algorithm, a multi-level modular integrated electromagnetic field suitable for deconstructing additive models of unit assembly is designed, including: Determine the positive and negative ideal solutions of the multimode electromagnetic field; Calculate the approximation of the multimode electromagnetic field of each deconstructed unit combined additive model to the positive and negative ideal solutions; Based on the degree of proximity, the optimal combination of multi-mode electromagnetic fields is selected as the multi-level modular integrated electromagnetic field.

5. The method for equalization control of metals in multi-mode electromagnetic field-assisted additive manufacturing as described in claim 2, characterized in that, Based on the aforementioned multi-mode integrated electromagnetic field spatial distribution model, a dynamic polling algorithm is employed to perform real-time adaptive equalization control of the integrated electromagnetic field using the geometric vector operator of the model during the additive manufacturing process, including: The vector operators of the target additive body model described in the additive manufacturing process are periodically sampled to obtain the operator sampling results; Calculate the vector operator deviation based on the operator sampling results; Based on the vector operator deviation, the model parameters of the multi-mode integrated electromagnetic field spatial distribution model are dynamically adjusted to achieve electromagnetic field equilibrium control and real-time matching with the geometric features of the target additive model.

6. The method for equalization control of metals in multi-mode electromagnetic field-assisted additive manufacturing as described in claim 5, characterized in that, Based on the vector operator deviation, the model parameters of the multi-mode integrated electromagnetic field spatial distribution model are dynamically adjusted to perform electromagnetic field equilibrium control and real-time matching with the geometric features of the target additive model, including: The adjustment amount of the electromagnetic field parameters is calculated based on the vector operator deviation; Based on the electromagnetic field parameter adjustment amount, the intensity, frequency, and phase of the electromagnetic field are dynamically adjusted to generate an adaptive equalization control strategy for the electromagnetic field. Based on the aforementioned electromagnetic field adaptive equalization control strategy, the equalization control of the electromagnetic field is performed and the geometric features of the target additive model are matched in real time.

7. The method for equalization control of metals in multi-mode electromagnetic field-assisted additive manufacturing as described in claim 2, characterized in that, The target additive model is deconstructed, including: The target additive model is decomposed into multiple basic modular units; Based on the additive model feature vector of each basic module unit, the corresponding optimal auxiliary electromagnetic field and additive process are selected to generate the target deconstruction unit combined additive body model.

8. A balanced control system for multi-mode electromagnetic field-assisted additive manufacturing of metals, characterized in that, The system includes: The vector operator creation module is used to create vector operators that describe the geometric features of the additive part model; The multi-feature data acquisition module is used to acquire multi-feature data of typical additive models under the assistance of longitudinal and transverse bidirectional multi-mode electromagnetic fields. The mathematical characterization module is used to mathematically characterize multiple features in the additive manufacturing process of a typical additive manufacturing model by establishing the quantization relationship between the vector operator and the multi-feature data, and to generate a mathematical characterization vector. The vector classification module is used to classify the characterization vectors of different parts of the complex additive model based on the mathematical characterization vectors, and generate vector classification results. The modular deconstruction module is used to perform modular deconstruction of the component units of the complex additive manufacturing model based on the vector classification results, and generate multiple modular deconstruction unit categories applicable to multi-variety additive manufacturing models. An expert system establishment module is used to obtain the optimal auxiliary electromagnetic field and additive manufacturing process of typical modular deconstruction units. Combining the multiple modular deconstruction unit categories, a multi-mode electromagnetic field optimization expert system containing multiple types of deconstruction units is established. The adaptive equilibrium control module is used to perform target deconstruction and adaptive electromagnetic field equilibrium control on the target additive model based on the multi-mode electromagnetic field optimization expert system.

Images