11368 results about "Additive layer manufacturing" patented technology

The present invention relates to a method for constructing a digital twin system for an additive manufacturing process with lifecycle data management. The digital twin system for an additive manufacturing process constructed by the method includes a data acquisition and supervisory control system, a data management and storage system, a manufacturing executing system, a configuration model, a simulation system, and a multi-physics simulation system. The present invention can fully and accurately characterize the molding quality of parts, thereby saving a lot of time required for offline data processing, and achieving real-time acquisition and updating of data.

A defect prediction method based on a multi-feature parallel multi-stage neural network (MF-PMSNN), includes: obtaining a trajectory dataset, and preprocessing data of a defect of a workpiece in additive manufacturing (AM); building an MF-PMSNN, and evaluating an output classification result based on evaluation indicators; and performing real-time defect prediction, and deploying a trained MF-PMSNN model to a production environment. The present disclosure combines and effectively matches thermal imaging-based in-situ monitoring data and X-ray computed tomography (XCT)-based in-situ monitoring data to ensure temporal and spatial consistency between the thermal imaging-based in-situ monitoring data and the XCT-based in-situ monitoring data. In this way, a molten pool status and a pore of the workpiece can be captured more comprehensively. The MF-PMSNN is proposed to obtain a molten pool status and the porosity distribution in the data and perform defect prediction.

A method for performing an automated additive manufacturing (AM) process comprises obtaining a current state that includes a set of first AM factors and a set of first characteristics, which are geometric or physical properties of a first AM output are generated using the first AM factors. The current state is provided to a reinforcement learning (RL) framework designed to adjust welding parameters in real-time based on the current state and reward feedback. The RL framework includes an actor network and a critic network, and safety limits are enforced through a custom loss function. The first AM factors are updated based on the critic network's evaluation, resulting in second AM factors used to perform the second AM process and generate a second AM output.

The invention provides an electromagnetic field composite powder feeding type plasma arc additive manufacturing formability regulation and control method and system, and relates to the technical field of plasma arc additive manufacturing. The flowing direction and speed of liquid metal in a molten pool in the deposition process are regulated and controlled through the target composite electromagnetic field, and the morphology and the internal organization structure of a deposition layer are controlled; in the process of regulating and controlling the liquid metal in the molten pool, process parameters and molten pool dynamic image data in the deposition process are collected in real time, and a pre-trained state recognition model is used for conducting self-adaptive adjustment on the process parameters of a subsequent deposition layer; and after deposition of each layer is completed, a laser scanning system is adopted for measuring the actual geometric size and surface appearance of the deposition layer, deposition manufacturing of the next layer is executed based on the optimized composite electromagnetic field control parameters, the corrected layered slicing data and the process path, and the execution is executed circularly till manufacturing of the whole workpiece is completed.

The invention provides a multi-heat-source multi-material additive manufacturing optimization method and system based on machine learning, and relates to the field of additive manufacturing, and the method comprises the following steps: collecting process parameters, material physical properties and target response data in real time, and constructing a multi-source data set; on the basis, a multi-task learning model is trained, common features are extracted, target responses are synchronously predicted, a proxy target function is constructed through predicted values, if errors exceed a threshold value, experimental verification is conducted, and new data is fed back to update the model. And applying the weight coefficient to a multi-objective evolutionary algorithm, iteratively screening a Pareto candidate solution set, verifying a high-uncertainty solution, and updating the model to error convergence. And selecting and deploying an optimal parameter combination by using an entropy weight-TOPSIS method, and embedding an online learning mechanism to form closed-loop optimization. According to the method, multi-task learning and a self-adaptive evolutionary algorithm are combined, and efficient optimization of multi-heat-source multi-material additive manufacturing process parameters can be achieved.

The invention provides a heat input regulation and control method and system for electric arc additive continuous forming, and relates to the technical field of additive manufacturing, and the method comprises the following steps: collecting process parameters in real time, inputting pretreatment process data into a self-adaptive heat input quantity calculation model, and constructing and calculating to obtain a real-time heat input quantity based on a thermodynamic principle and a heat transfer theory; starting the multispectral imaging equipment, performing real-time temperature field scanning, recording temperature field scanning data, extracting temperature gradient and cooling rate information, performing correlation calculation with real-time heat input quantity, and determining an influence relation evaluation result; generating a heat input sequence according to the influence relation evaluation result; and inputting the heat input sequence into a self-adaptive control system constructed based on a reinforcement learning algorithm, calculating an optimal parameter scheme according to a preset target sedimentary layer performance index and a current temperature field state, adjusting corresponding spatial-temporal distribution of control energy input according to the optimal parameter scheme, and performing control heat input on different positions and different layers of the sedimentary layer.

The invention relates to the technical field of additive manufacturing, and particularly discloses a real-time defect detection and in-situ repair method and device in the additive manufacturing process, and the method comprises the steps that a multi-mode sensing system is integrated on additive manufacturing equipment, the multi-mode sensing system comprises a high-resolution CCD camera, a laser scanner and a thermal infrared imager, and data acquisition is synchronized; a hierarchical scanning strategy is adopted, two-dimensional surface images, three-dimensional point cloud data and thermal field distribution information are collected before and after each layer is machined, and the data synchronization precision is smaller than 0.1 ms; according to the invention, a multi-modal sensing system and an advanced algorithm are integrated, so that real-time detection and accurate repair of defects are successfully realized; a high-resolution CCD camera, a laser scanner, a thermal infrared imager and other sensors are adopted, a cross-scale RANSAC algorithm and a depth feature fusion network are combined, surface and internal defects are accurately detected, and laser remelting parameters are adjusted in real time for in-situ repair.

The invention provides an additive manufacturing residual stress optimization method and system, and the method comprises the steps: searching a global optimal solution enabling the residual stress of an additive manufacturing part to be minimum from a technological parameter space through the combination of multi-physics field numerical simulation and an intelligent optimization algorithm; the multi-physics field numerical simulation comprises the steps of sampling from a process parameter space by using an optimization algorithm to obtain process parameters, inputting the sampled process parameters into a finite element model, performing thermal analysis on the process parameters based on the finite element model, and obtaining transient thermal distribution through thermal analysis. And performing structural analysis by using transient heat distribution to obtain residual stress under the current process parameters, and transmitting the obtained residual stress to an intelligent optimization algorithm for realizing process parameter optimization. The method has the advantages of high precision, low cost and the like, and high-precision collaborative optimization of multiple types of process parameters can be realized.

The invention discloses a thin-wall structure lightweight design method based on additive manufacturing, and belongs to the technical field of additive manufacturing, and the thin-wall structure lightweight design method comprises the following steps: S100, designing an initial structure based on function and performance mapping; s200, an additive manufacturing process knowledge base is constructed, and the adaptability of the additive manufacturing process is evaluated; s300, carrying out process and structure bidirectional coupling finite element analysis; s400, collaborative optimization of a process and a structure driven by a multi-objective optimization algorithm; s500, feature part manufacturing verification and design and process scheme iterative optimization are carried out; and S600, generating a design and process integrated scheme, wherein the integrated scheme comprises design parameters and manufacturing parameters. The technical problem that in the prior art, the structure optimization target and the manufacturing adaptive capacity are lack of collaboration can be solved.

An information technology system for a distributed manufacturing network includes an additive manufacturing management platform configured to manage process and production workflows for a set of distributed manufacturing network entities through design, modeling, printing, and supply chain stages. The information technology system includes an artificial intelligence system configured to learn on a training set of outcomes, parameters, and data collected from the set of distributed manufacturing network entities of the distributed manufacturing network to optimize digital production processes and workflows. The information technology system includes a distributed ledger system integrated with a digital thread configured to provide unified views of workflow and transaction information to entities in the distributed manufacturing network.

The invention relates to the technical field of path planning, and discloses a laser fuse additive manufacturing thermal management path planning closed-loop regulation and control system, which comprises a data acquisition module, a data processing module, a temperature distribution prediction module and a path planning regulation and control module, acquiring temperature distribution characteristic data and first characteristic data; the data processing module is used for preprocessing the temperature distribution feature data and the first feature data to obtain a regional feature sequence; the temperature distribution prediction module is used for constructing a temperature distribution prediction model according to the regional feature sequence; and the path planning regulation and control module is used for generating a regulation and control scheme in combination with the improved parrot optimization algorithm and the temperature distribution prediction model. Through combination of temperature prediction, path optimization, multi-dimensional feature extraction and an improved optimization algorithm, global optimization and dynamic regulation and control of the processing process are realized.

Additive manufacturing systems and related methods are disclosed. In some embodiments, a first motion stage may be used to move a recoater and an optics assembly. The optics assembly may be configured to direct laser energy from one or more laser energy sources towards a build plate. The recoater may be configured to form a layer of precursor material on the build plate. In some embodiments, a secondary housing formed of a composite material may be used.

The invention relates to a porous structure manufactured through laser powder bed melting additive manufacturing, in particular to a gradient porous structure with excellent mechanical property and functionality and an LPBF self-adaptive input manufacturing method of the gradient porous structure. According to the method, basic geometric parameters and gradient characteristics of the gradient porous structure are defined by utilizing Grasshopper parameterization design software. A gradient porous structure with excellent mechanical properties and functionality is generated through a grasshopper plug-in of software, and smooth transition from a solid state to a porous state is achieved. An LPBF technology is adopted and combined with an angle partitioning strategy, the gradient porous structure is melted layer by layer, the gradient porous structure is partitioned according to the strut suspension angle on the basis of optimizing process parameters, the optimized process parameters are applied to a model of the partitioned region, and the gradient porous structure is obtained. Scanning of each layer of the overhanging supporting columns at different angles is in appropriate laser parameter input, and the problems of deformation and high porosity caused by heat accumulation in the LPBF process are effectively solved.

The invention relates to the technical field of structure optimization design, and particularly discloses a box-type beam structure lightweight design method based on topological optimization, which comprises the following steps: constructing a multi-physics field coupled three-dimensional parameterized model, and performing cross-scale analysis on integrated structure rigidity, thermal deformation, vibration mode and fatigue life to obtain a three-dimensional parameterized model; a variable density method and level set method mixed topological optimization strategy is adopted, and an initial material distribution scheme meeting the structural function integrity is generated by modeling the relationship between density and stress strain; starting a quantum genetic algorithm and deep reinforcement learning fused intelligent optimization engine; according to the method, through the multi-physics field coupled three-dimensional parameterized model, a variable density method and level set method mixed topological optimization strategy is combined, the relation between the structural lightweight target and the additive manufacturing process is effectively balanced, multi-physics field analysis of thermal response, vibration, fatigue and the like is introduced, and the structural lightweight target is obtained. And it is guaranteed that the box-type beam meets the mechanical property and other functional requirements in actual application.

A friction stir additive manufacturing system is provided. In one aspect, the system includes a spindle configured to rotate about a central axis, and a housing configured to receive at least a portion of the spindle, the housing configured to remain stationary relative to the spindle. The housing includes a wire inlet extending between an exterior surface of the housing and an interior surface of the housing, and a track extending from the wire inlet and partially around a circumference of an interior surface of the housing. The system also includes a feeding system configured to receive a wire from a roller and feed the wire through the wire inlet and into the track of the housing.

A method of joining a first work-piece to a second work-piece is provided. Each of the first work-piece and the second work-piece include a top surface, an opposed bottom surface, and a side surface connecting the top surface and the opposed bottom surface. In one aspect, the method includes positioning the side surface of the first work-piece adjacent to the side surface of the second work-piece, and advancing a friction stir additive manufacturing tool across the top surface of the first work-piece and the top surface of the second work-piece along a weld line between the first work-piece and the second work-piece. As the friction stir additive manufacturing tool advances along the weld line, a filler material is deposited along the weld line and into a plurality of through holes formed in either or both of the first work-piece and the second work-piece. Each of the plurality of through holes includes a first opening on the top surface, a second opening on the opposed bottom surface, and a passageway through the work-piece between the first opening and the second opening. The method further includes joining the first work-piece and the second work-piece together.

An additive manufactured (AM) metal coupon for a turbomachine component is provided. The component includes an airfoil body having a pressure side, a suction side, a trailing edge, and a coupon opening. The AM metal coupon has an AM metal member with at least one slanted coupon side wall at an angle of less than 90° with an exterior surface of the AM metal member. The AM metal member also has a first porous region having a first porosity and a second porous region having a second porosity different than the first porosity. A braze material couples the AM metal coupon in the coupon opening in the airfoil body and infiltrates into at least one of the first porous region based at least on a characteristic of the first porosity and the second porous region based at least on a characteristic of the second porosity.

A device comprises an array of voxels of solidified material defining at least one scan path, along which an error in a variable dielectric quantity at a target voxel is distributed by successive deposition and solidifying of a selected material along the scan path, in accordance with a prescription for the device. The prescription defines the dielectric quantity over the array of voxels.

The invention relates to a hybrid architecture mechanical property prediction method and system for an additive manufacturing lattice structure, and the method comprises the steps: converting a lattice structure node three-dimensional coordinate into a normalized distance from a lattice center, introducing a self-attention mechanism, and constructing a feature prediction model in combination with residual connection and layer normalization; constructing a generative adversarial network comprising a generator and a discriminator; a strategy network based on prediction error rewards is constructed, and a depth deterministic strategy gradient algorithm is adopted for optimization; jointly training the models, and constructing a performance prediction feedback model; finally, the node coordinates of the target structure serve as input, and mechanical property prediction output is achieved. According to the method, the generative adversarial neural network, reinforcement learning and an attention mechanism are mutually combined to generate a hybrid architecture, the problems of gradient disappearance and mode collapse of a traditional GAN can be effectively relieved, the model can accurately recognize implicit association between node positions and mechanical properties, and then the mechanical properties of target lattice structure parameters are rapidly predicted.

The present disclosure relates to a method of using a metal specimen block having a porous region for a component. A method of coupling a metal sample block (200) to a component (202) may include additive manufacturing a metal sample block (200) having a first porous region (300A) having a first porosity and a second porous region (300B) having a second porosity different from the first porosity. A metal specimen block (200) is positioned in a specimen block opening (204) in a body (206) of the component (202). The metallic sample block (200) may be infiltrated with a braze material (310) to couple the metallic sample block (200) in a sample block opening (204) in the body (206). The one or more brazing materials (310) are infiltrated into at least one of the first porous region (300A) and the second porous region (300B) based at least on a characteristic of the first porosity and at least on a characteristic of the second porosity. The cured braze material (310) includes different segments having different physical properties based on different porosities and / or different braze materials.

A component (202) is disclosed that includes a body (206) and an additive manufactured (AM) metal mass (200) that includes a first section (292) and a stress relief section (294). The stress relief section (294) includes a porous region (300) having a porosity in which an open spatial volume accounts for 2% to 50% of the total volume of the stress relief section (294). The stress relief section (294) has a smaller at least one of thermal conductivity, tensile strength, ductility, and fatigue strength than the first section (292). A braze material (310) couples the AM metal specimen block (200) to a specimen block opening (204) in the body (206). The stress relief section (294) creates a low stress zone in the metal specimen block (200), which can be located near or adjacent to a high stress zone. The stress relief section (294) reduces residual stress in the metal sample block (200), which reduces related challenges to couple the metal sample block (200) to the body (206) of the component (202), particularly in the case of the use of superalloy materials.

The invention relates to a metal sample block with a porous area for a component and the component with the metal sample block. A component (202) includes a body (206) and an additive manufactured (AM) metal sample block (200) that includes at least one first porous region (300A) having a first porosity and can include any number of second porous regions (300B) having a second porosity different from the first porosity. A braze material (310) couples the metallic sample block (200) in a sample block opening (204) in the body (206). The braze material (310) is infiltrated into at least one of the first porous region (300A) and any second porous region (300B) based at least on a characteristic of the first porosity and at least on a characteristic of the second porosity. Different porosities can be tailored to provide different physical characteristics for the first porous region (300A) and the second porous region (300B) having the braze material (310) therein.

The invention relates to a porous metal sample block with a pipeline for repairing a component, the component with the porous metal sample block and a related method. A metal sample block (200) for repairing a component (202) includes an additive manufactured (AM) metal component (330) having a conduit (296) inside the AM metal component (330) and a first porous region (300) surrounding the conduit (296). The duct (296) is hollow. A porous metal sample block (200) with conduits (296) allows the brazing material (310) to be directed based on characteristics of the first porous region (300). The second porous region (350) can be disposed within the conduit (296) to increase heat dissipation of the conduit (296).

A method of additive manufacturing a part having integrated passages is provided. In one aspect, the method includes forming a part having a near net shape by moving a friction stir tool to deposit a filler material in a predetermined formation. The tool can include a rotating spindle having a channel configured to hold the filler material. The method can include machining the near net shape part to form a plurality of grooves extending into a surface of the part, the plurality of grooves sized and shaped to each receive a tube. The method can include placing a tube into each of the plurality of grooves and moving the tool across the surface of the part and depositing additional material configured to secure the tubes within the plurality of grooves. The method can include machining the additional material deposited over the tubes to a predetermined shape.

The invention relates to the technical field of additive manufacturing, in particular to a coaxial two-state in-situ material extrusion 3D printing interlayer enhancement method which comprises the steps of (1) data processing, (2) data reading and printing area dividing, dividing the printing area into an outer wall filling type and an inner filling type, and (3) adjusting printing parameters to obtain a coaxial two-state process control method. (4) a printing strategy and process parameters are automatically adjusted according to the printing area and the printing material, and when the program recognizes that the printing area is the outer wall, the normal printing process parameters are kept unchanged; and when the program recognizes that the printing area is internally filled, a coaxial double-state process control method is used for printing. According to the coaxial two-state in-situ material extrusion 3D printing method, on the premise of not additionally integrating parts and not additionally introducing a control system, the material extrusion interlayer strength can be effectively improved, and the coaxial two-state in-situ material extrusion 3D printing method has the advantages of being simple, efficient, free of directional limitation and the like.

The invention relates to the technical field of additive manufacturing, in particular to an air field system with uniform airflow distribution for an additive manufacturing large-breadth forming platform, which comprises an air inlet three-way pipe unit and a negative pressure air draft unit, the air inlet three-way pipe unit comprises a main air supply pipe, an upper air outlet pipe and a lower air outlet pipe; the upper air outlet pipe and the lower air outlet pipe are each internally provided with a flow dividing grating assembly, air outlets of the upper air outlet pipe and the lower air outlet pipe are divided into a plurality of sub air outlets with the same opening size through the flow dividing grating assemblies, and flow guide pipes are arranged at the air outlets of the upper air outlet pipe and the lower air outlet pipe. An airflow dispersion unit is arranged on the side, close to the sub air outlets, in the flow guide pipe, a linear air outlet hole is formed in the other side of the flow guide pipe, and a conical flow channel with a conical section is arranged between the airflow dispersion unit and the linear air outlet hole. By means of the multi-stage flow dividing and guiding design, the effect that airflow in all areas of the large-breadth forming platform is evenly distributed under the condition of low air volume is achieved.

The invention relates to a preparation method of a carbide ceramic reinforced high-temperature alloy, and belongs to the technical field of additive manufacturing. The preparation method comprises the following steps: taking a high-temperature alloy as a matrix, and then adding carbide ceramic to prepare the composite material; the method comprises the following steps: mixing carbide ceramic powder with high-temperature alloy powder; the carbide ceramic is TiC, HfC or NbC; the high-temperature alloy is a CoNiCrW series high-entropy alloy or a NiCrWMo series medium-entropy alloy; the particle size of the carbide ceramic powder is 40-80 microns; the particle size of the high-temperature alloy powder is 40-90 microns; the composite material is prepared through an additive manufacturing process. The W element in the high-temperature alloy powder diffuses towards the surface of the carbide ceramic to form a thin interface layer, so that the interface bonding force between a matrix and the carbide ceramic phase can be ensured, the compatibility between the high-temperature alloy matrix and the carbide ceramic is improved, the interface cracking risk is effectively reduced, and the metallurgical quality of a composite material is greatly improved.

The invention belongs to the technical field of laser processing, and particularly relates to a multi-mode laser coupling high-efficiency and high-quality additive manufacturing method for a metal-based composite material, which comprises the steps of pretreatment, substrate pretreatment, multi-mode coupling laser construction, additive manufacturing and the like. High-power pulse laser is adopted as energy supply main laser to melt the metal matrix composite wire, meanwhile, flowing of a molten pool is accelerated, the nucleation rate is increased, and metal matrix composite parts are machined through the additive manufacturing method. The continuous laser is adopted to effectively slow down the cooling speed of the molten pool, and the residual tensile stress generated in the component due to rapid solidification of the molten pool is greatly reduced. Oscillating laser is adopted to improve the shape of a molten pool and reduce the number of times of transverse lap joint. According to the method, multi-mode laser coupling and cooperation with the flat-topped laser light source are utilized, and the metal-based composite material machining part with the uniform and flat surface appearance macroscopically and the stable and uniform organization structure microcosmically is obtained.

The invention discloses an additive manufacturing parameter optimization method using machine learning. The method comprises the following steps: acquiring a first cladding layer surface topography constructed by powder layers with different powder characteristics under different powder laying parameters, and establishing a first database at least mapping a relationship among the powder laying parameters, the powder characteristics and the first cladding layer surface topography; and according to the first database, a first machine learning model is constructed and trained to generate a first application model used for powder laying parameter prediction, and then the first application model is used for predicting input powder characteristics to output optimal powder laying parameters used for additive manufacturing so as to optimize the additive manufacturing quality.

The invention provides an additive manufacturing method of a short fiber reinforced ceramic composite aircraft engine swirler, which comprises the following manufacturing steps: performing interface preparation on the fiber surface to obtain composite powder, and mixing the powder with silicon carbide powder and resin to obtain mixed powder; carrying out selective laser sintering printing molding on the mixed powder to obtain a ceramic green body, and carrying out degreasing treatment to obtain an intermediate; performing two-step impregnation and cracking on the intermediate through a ceramic precursor and resin to obtain a preform 2, performing gas / liquid phase reaction sintering treatment on the preform 2 to obtain Cf / SiC ceramic, depositing silicon carbide on Cf / SiC through a chemical vapor infiltration method, and performing abrasive flow grinding and polishing to obtain a finished product. The short fiber reinforced silicon carbide powder precise printing forming swirler is achieved, fiber, silicon carbide and resin powder are subjected to composite granulation, fiber agglomeration is weakened, the powder density is increased, the cohesive force between carbon fibers is increased, and therefore the biscuit density is increased; and structure accurate forming and surface quality control of the swirler with the complex structure are facilitated.