5672 results about "Additive layer manufacturing" patented technology

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 invention provides a data correction method and system combined with lattice structure additive manufacturing process characteristics, and the method comprises the steps: firstly employing a Newton iteration method, taking the radius of a pillar as a variable, optimizing the relative density of an iteration target and generating a lattice structure geometric model under the condition that a process constraint condition is satisfied, and extracting actual geometric parameters after forming through CT scanning, the elastic modulus is corrected through the pillar diameter deviation and the defect volume fraction, a compression failure mechanism is combined, a density-related failure criterion is introduced, a nonlinear relation with the relative density is constructed through specific energy absorption data, material plasticity parameters are inversely optimized, and a defect coupling evaluation model is constructed according to the surface powder sticking rate and the pillar diameter deviation. And establishing a Gaussian mixture model based on a stress-strain curve to screen out abnormal data, and finally fusing the parameters to construct a data correction model. The dot matrix structure design precision can be improved, and then a high-quality data basis is provided for performance prediction-structure design two-way feedback.

The invention discloses an engine additive component service life prediction method based on modal polycondensation and expansion, and the method specifically comprises the steps: firstly, achieving the grid discretization of an initial defect structure based on a finite element method, and carrying out the local refinement of a defect region; performing modal polycondensation on the overall model to obtain a low-dimensional system model, and performing rapid calculation under the low-dimensional model to obtain modal response; establishing a conversion relation between a displacement vibration mode and a stress vibration mode, and obtaining full-field stress by utilizing modal response and based on modal extension; and solving a stress intensity factor-time history of the crack tip by adopting a stress extrapolation method, obtaining a delta K-R-n three-variable rain flow matrix by utilizing a rain flow counting method, and finally carrying out residual life evaluation through an iLAPS model. According to the method, system dynamics, fracture mechanics and modal order reduction technologies are fused, a new efficient and accurate fatigue life prediction path adapting to complex working conditions is provided for additive manufacturing components with defects, and the method has remarkable engineering application value and popularization potential.

The invention discloses a dynamic monitoring and analyzing method for a thermal management component molten pool based on image recognition, and relates to the technical field of laser powder bed melting additive manufacturing. The method comprises the following steps: continuously capturing an original thermal management component molten pool image and temperature field distribution data during laser powder bed melting additive manufacturing; and optimizing the original thermal management component molten pool image to generate an optimized thermal management component molten pool image. Molten pool images and temperature field data are captured in real time through a high-frame-rate synchronous camera and an infrared sensor, defect types are recognized online in combination with a lightweight classification model, classification results are fed back to a control system to dynamically adjust laser power or scanning speed, interlayer defect accumulation can be inhibited in time, and the defect quality is improved. The defect diffusion problem caused by response lag of a traditional off-line analysis method is avoided, and the forming precision and the process stability of the heat management component are remarkably improved.

The invention relates to an additive manufacturing method and application of an aluminum-based silicon carbide composite material complex component, and the additive manufacturing method of the aluminum-based silicon carbide composite material complex component comprises the following steps: step 1, uniformly mixing silicon carbide powder and aluminum alloy powder, and drying; 2, establishing a structural model for the target part, and importing the structural model into selective laser melting forming equipment; thirdly, selective laser melting forming is conducted; fourthly, linear cutting and surface treatment are conducted; and fifthly, hot isostatic pressing treatment is conducted. The invention further provides application of the aluminum-based silicon carbide composite material complex component to precise structural components such as aviation structural components, guided missile and satellite components and optical instruments. According to the method, the problem of subsequent large-allowance removal of the aluminum-based silicon carbide composite material component is solved, the wettability between the aluminum alloy and the silicon carbide particles is improved, the mechanical property meets the application requirement, and the aluminum-based silicon carbide structural component with stable performance is obtained.

The invention belongs to the technical field of additive manufacturing, and particularly relates to a multi-scale parallel optimization method for a lightweight structure based on lattice discrete optimization. According to the method, through multi-scale parallel optimization design, a macro structure and a micro lattice structure are described through geometric parameters of a movable deformation rod piece, an improved two-value coding parameterization method, called a BCP method for short, is adopted to solve discrete optimization of the micro lattice structure, and geometric parameters of an optimization result are easy to extract.

The invention relates to the technical field of additive manufacturing, and discloses an additive manufacturing lens surface optimization method based on real-time feedback control. The method comprises the following steps: firstly, acquiring eye biometric data and personalized visual demand parameters of a wearer, establishing a personalized optical model of eyeballs according to the eye biometric data and the personalized visual demand parameters, and deducing a retina defocusing amount distribution map; and determining spatial arrangement and geometric morphology parameters of the distributed out-of-focus microstructure layer on the lens according to the atlas. In the additive manufacturing process, the optical material is deposited and solidified layer by layer, and the three-dimensional shape information of the surface of the optical material is obtained in real time after deposition of each layer. And comparing and analyzing the morphology information with a theoretical model to generate a morphology deviation result. And then, a correction instruction of the printing parameters is calculated by using the correction model, and the printing parameters of the additive manufacturing equipment are adjusted in real time, so that real-time compensation and optimization of the morphology deviation are realized, and finally, a high-precision lens product meeting personalized optical design requirements is manufactured.

The invention relates to the field of computer graphics, reverse engineering and additive manufacturing, discloses a multi-modal fusion and physical constraint three-dimensional point cloud geometric modeling system and method, and aims at overcoming the defects that traditional three-dimensional reconstruction entity attributes are missing, key features are prone to being lost, semantic understanding does not exist, and process automation is low. The system comprises a point cloud preprocessing module, a semantic segmentation and recognition module, a mixed geometric reconstruction module, a multi-component assembly and physical constraint solution module and an entity model output module. The method comprises the following steps: denoising and sampling an original point cloud, realizing semantic and instance double segmentation through a Point Net + + network, endowing a geometry-function composite label, completing hybrid reconstruction through improved Poisson reconstruction, parameterized B-Rep fitting and standard component library matching, and outputting a multi-format engineering available model after physical constraint verification and automatic correction of a violation model. According to the method, automatic, high-fidelity and high-practicability conversion from the point cloud to the engineering-level entity model is realized, and the method is adaptive to multiple industrial application scenes.

The invention relates to the technical field of additive manufacturing, and discloses an additive manufacturing hot-crack-free precipitation strengthening high-temperature alloy and a preparation method thereof.The method comprises the steps that a laying layer is divided into a plurality of parallel scanning strips according to the preset translation direction and the scanning strip interval, strip type scanning is conducted in a laser autorotation and translation motion coupling mode, and the high-temperature alloy is obtained; molten pool disturbance is remarkably enhanced, periodic shear fracture of the tip of dendritic crystal is achieved, epitaxial growth of columnar crystal is broken, grain equiaxalization is achieved, and anisotropy is weakened; in addition, laser scanning is a high-speed scanning strategy with the translation speed larger than or equal to 1500 mm / s, a shallow molten pool is formed through regulation and control of the high scanning speed, surface tension in the shallow molten pool is utilized, convection in the molten pool is enhanced, dendritic crystals are refined, columnar crystals in the high-temperature alloy are further reduced, and anisotropy of mechanical properties is remarkably eliminated; and the transverse strength and creep resistance at high temperature are improved. The isometric crystals can effectively prevent cracks from expanding in the orientation direction of the columnar crystals, and the fatigue life and the damage tolerance are remarkably prolonged.

An information technology system for a distributed manufacturing network includes an additive manufacturing platform configured to manage workflows for a set of distributed manufacturing network entities associated with the distributed manufacturing network. The information technology system includes a set of digital twins generated by the additive manufacturing platform. The information technology system includes an artificial intelligence system configured to be executed by a data processing system in communication with the additive manufacturing platform. The artificial intelligence system is trained to generate process parameters for the workflows managed by the additive manufacturing platform using data collected from the set of distributed manufacturing network entities. The information technology system includes a control system configured to adjust the process parameters during an additive manufacturing process performed by at least one of the set of distributed manufacturing network entities.

An additive manufacturing method based on micro-selective laser melting technology. By using a spot size of 30 μm or less, a metal powder layer thickness of 10 μm or less and ultrafine metal powders having a D90 particle size of 30 μm or less, and in combination with the control of a scanning laser power, a scanning rate, a linear energy density and a volumetric energy density within specific ranges, the method can print complex-structured metal parts having extremely high resolutions and surface smoothness, and can obtain a high-density internal structure of a component even under a relatively low energy density or power condition, thereby effectively protecting an optical system. Moreover, a printed component exhibits a defect-free microstructure, and has excellent electrical properties, thermal properties and mechanical properties. Particularly, ultrafine grains and a high dislocation density provide superior mechanical properties compared to conventional manufacturing materials. An infrared laser device can be used, thereby achieving low costs.

The invention belongs to the technical field of metamaterials, and particularly relates to a diamond substrate lattice metamaterial and an additive manufacturing method thereof. The structure is designed based on the geometric configuration of a diamond lattice, and has excellent high specific absorption mechanical properties. The design process comprises the following steps: firstly, carrying out spatial registration positioning on the basis of a unit cell structure with a preset wall thickness t and a unit cell width a; then, through a multi-unit-cell splicing design, the unit cells are spliced repeatedly for 12 times to form three-dimensional periodic stacking; then, the stacked structure is cut along the six datum planes; then cross plates are inserted into the six cutting faces respectively to enhance the integrity and strength of the structure; and finally, a complete DM plate lattice metamaterial structure is formed. The structure is provided with a plate-plate cross supporting framework, a complex three-dimensional inner cavity and highly symmetrical space distribution, the energy absorption capacity under unit mass is greatly improved, the mechanical properties are basically consistent in multiple directions, and the structure is suitable for the engineering fields of impact protection, energy absorption buffering and the like.

An additive manufacturing real-time process parameter optimization method based on reinforcement learning driving comprises the steps that firstly, a multi-mode online monitoring hardware platform is constructed, and a visible light camera, a thermal imaging camera and an acoustic sensor are integrated to sense the working condition of the additive manufacturing process in real time in an omnibearing mode; secondly, extracting key features, including visible light images, thermal imaging and acoustic signal branches, of modal data on line through a lightweight CNN-Transform hybrid network, and generating a unified low-dimensional state vector through convolution feature extraction and fusion of a Transform encoder; then, a reinforcement learning model is established, a multi-target reward function is designed in combination with the extracted feature data, a process jitter penalty term, an overheating penalty term and the like are covered, and dynamic mapping of parameters and performance is achieved. And finally, an online learning and real-time decision-making system is deployed, the trained strategy network is embedded into manufacturing equipment, self-adaptive adjustment and closed-loop control of technological parameters are achieved, and the stability and product performance of the additive manufacturing process are effectively improved.

The invention provides a post-treatment method for laser additive manufacturing of titanium alloy. The post-treatment method comprises the steps that a titanium alloy workpiece is sequentially subjected to first annealing treatment, beta heat treatment, hot isostatic pressing treatment and second annealing treatment. Through the specific process combining beta heat treatment and hot isostatic pressing treatment, comprehensive regulation and control over the stress, defects and tissue of the titanium alloy workpiece are achieved, the internal stress of the laser additive manufacturing titanium alloy workpiece is eliminated, and meanwhile the microstructure of the laser additive manufacturing titanium alloy workpiece can be regulated and controlled while most metallurgical defects are eliminated; the strength, toughness and damage tolerance performance of the titanium alloy are synergistically improved, and the service scene of the titanium alloy can meet the static strength and fatigue damage tolerance requirements at the same time.

The invention discloses a nickel-based alloy additive manufacturing method for high-frequency ultrasonic dynamic forging printing. The method comprises the steps that nickel-based alloy powder and a base plate are pretreated; scanning the nickel-based alloy powder layer by layer through laser to form a molten pool; in the machining process of each layer, when the temperature of the molten pool ranges from 1000 DEG C to 1400 DEG C, ultrasonic waves are activated to generate compound vibration; the composite vibration comprises axial vibration and transverse vibration; when the ultrasonic vibration phase difference reaches a preset first interval, short pulse laser is triggered; the ultrasonic vibration phase difference is a phase deviation between an ultrasonic vibration waveform and a pulse laser shock triggering moment; and until all layers are machined, a formed part is obtained. According to the scheme, the dislocation density is improved, secondary grain refinement and bubble escape are achieved, and interlayer stress redistribution is made uniform.

The invention discloses a method for preparing spherical metal fine powder by using coarse / waste powder through ultrasonic atomization, which comprises the following steps of: (1) collecting coarse / waste powder raw materials for ultrasonic atomization powder preparation, (2) conveying the coarse / waste powder to an electric arc melting area through argon gas flow, and carrying out melting and ultrasonic atomization powder preparation processing; (3) in the powder preparation process, the powder is continuously collected by using argon circulating airflow, so that the continuity of the powder preparation process is ensured; and (4) finally screening the prepared powder in particle size ranges to obtain high-quality spherical fine powder in different particle size ranges. According to the method, the recycling and reusing problems of 3D printing splashing waste powder and coarse powder in the traditional gas atomization powder manufacturing process are solved, and the powder pollution risk is remarkably reduced; according to the ultrasonic atomization re-powdering technology, the high-quality spherical metal fine powder needed by additive manufacturing can be efficiently prepared, powder waste discharge and environmental burden are reduced, the obtained powder can be directly used as a high-quality raw material for additive manufacturing, and green and sustainable development of the metal additive manufacturing industry is promoted.

The invention provides a concrete 3D printing self-adaptive deviation correction method and system, and relates to the technical field of intelligent construction and additive manufacturing, the method comprises the following steps: determining a deviation field matrix based on three-dimensional point cloud data, a two-dimensional texture image and printing parameters of a printed concrete layer; and extracting a two-dimensional texture image based on a convolutional neural network model, determining a defect feature data set, inputting the deviation field matrix, the defect feature data set and the printing parameters into a deformation trend prediction model to obtain a deformation trend set, adjusting the printing parameters of the to-be-printed concrete layer, and generating a target concrete member. The technical problems that traditional concrete 3D printing depends on a preset program, dynamic changes of material rheological characteristics cannot be sensed in real time, the extrusion shape deviates from a design target, interlayer dislocation and deformation can be accumulated layer by layer, and structural instability is caused are solved, and the effect of improving the stability of a printed and formed concrete member is achieved.

The invention relates to the technical field of metal fatigue life prediction, in particular to an additive manufacturing metal multi-axis high-cycle fatigue life prediction method based on defect characteristics. The method comprises the following steps: performing defect detection on a metal sample to obtain size parameters and position parameters of defects in the metal sample; determining the type of the defect in the metal sample and setting a first correction factor and a second correction factor; calculating the equivalent stress strength factor amplitude of the metal sample under multi-axial loading; acquiring a long crack propagation threshold value of the metal sample; normalizing the position parameters to obtain normalized position parameters; and establishing a fatigue life prediction model of the metal sample according to the normalized position parameters, the equivalent stress strength factor amplitude of the metal sample under multi-axial loading and the long crack propagation threshold value of the metal sample, and calculating the multi-axial high-cycle fatigue life of the metal sample. According to the method, the fatigue life of the metal material containing the additive manufacturing defects under multi-axis high-cycle fatigue loading can be accurately predicted.

The invention discloses a heat-resistant aluminum alloy material and a preparation method and application thereof, and belongs to the technical field of additive manufacturing aluminum alloy materials. The heat-resistant aluminum alloy material comprises the following components in percentage by mass: 0.5-6% of Fe, 0.5-6% of Cr, 0.5-3% of Ti, less than or equal to 2% but not equal to 0 of Mn, less than or equal to 2% but not equal to 0 of Sc, less than or equal to 2% but not equal to 0 of Zr and the balance of Al and inevitable impurities. By optimizing the component proportion, the preparation method and the like, in the microstructure of the heat-resistant aluminum alloy material, the interior of the heat-resistant aluminum alloy material is of a bimodal grain structure, the boundary of a molten pool is mainly isometric crystals, the center of the molten pool is columnar crystals, and an icosahedron nanometer quasi-crystal phase and an intermetallic compound strengthening phase are further distributed on the boundary of the molten pool and the center of the molten pool in a dispersed mode; the problems that when a traditional aluminum alloy material is used for additive manufacturing forming, hot cracks or macroscopic cracks occur, and the mechanical property of a formed product is poor are fundamentally solved.

The invention discloses a TiAl alloy electron beam selective melting and shot peening strengthening in-situ compounding manufacturing method and device, and relates to the technical field of additive manufacturing. The method comprises the following steps: establishing a three-dimensional digital model of a to-be-printed part, and performing slicing and layering to obtain layered scanning data; under the vacuum condition, TiAl alloy powder is spread on the preheated base plate according to the set thickness, and a powder bed is formed; according to the layered scanning data, scanning and melting the powder bed through a focused electron beam, completing single-layer scanning and melting, completing scanning and melting layer by layer until the part is printed and cooled, and recovering unmelted TiAl alloy powder; and under the vacuum condition, the surface of the printed part is scanned and heated through a defocusing electron beam, TiAl alloy powder is adopted as shot blasting powder, the surface of the heated part is subjected to microparticle shot blasting strengthening treatment, after the treatment is finished, cooling is conducted, scattered shot blasting powder is recycled, and the finished TiAl alloy part is obtained. By means of the collaborative process design of electron beam selective melting and in-situ high-temperature microparticle shot blasting and device integration, the problems that in TiAl alloy additive manufacturing, cracking is prone to occurring, and the strengthening effect is poor are solved.

The present application relates to the field of additive manufacturing, and discloses a simulation method for determining a laser powder bed fusion printing process for single-crystal austenitic stainless steel. The simulation method comprises the following steps: S1, establishing a three-dimensional polycrystalline powder bed microstructure model; S2, establishing a three-dimensional temperature field prediction model on the basis of a finite element method; S3, establishing a three-dimensional polycrystalline microstructure evolution model by using a phase-field method; and, S4, coupling the models from steps S1, S2 and S3, and simulating a multi-layer, multi-pass laser powder bed fusion process by using different process parameters, so as to determine appropriate single-crystal process parameters. The present invention replaces conventional trial-and-error experimental methods with numerical simulation methods to determine single-crystal process parameters, thereby greatly reducing the time and economic costs of process exploration, and assisting experiments in revealing the microstructure evolution mechanism of single crystal preparation via laser powder bed fusion additive manufacturing.

This invention provides a method for high-strength aluminum-lithium alloy friction stir deposition additive manufacturing and multi-stage heat treatment, relating to the technical field of aluminum alloy friction stir deposition additive manufacturing. The method includes: fixing a substrate and placing a stirring head in the area to be added to the substrate; loading a base material into the stirring head; starting the program, with a push rod slowly pushing the aluminum-lithium alloy base material to the area to be added; when the aluminum-lithium alloy base material reaches a thermoplastic state, the stirring head advances to complete deposition; lifting the stirring head and adjusting the height of the end face of the stirring head relative to the deposited layer to perform reverse-direction additive manufacturing to complete deposition; repeating the deposition steps layer by layer upwards until the height of the deposited layer reaches the target height to obtain a friction stir deposition additive component; subjecting the friction stir deposition additive component to low-temperature solution treatment and a first aging treatment, followed by high-temperature solution treatment and a second aging treatment to obtain a high-strength aluminum-lithium alloy, effectively solving the problems of difficult forming and easy cracking of ultra-large and moderately complex aluminum-lithium alloy structural parts.

The invention relates to the technical field of additive manufacturing, in particular to a direct aging treatment process of an SLM molded Ti-6Al-4V alloy and a product thereof, and the direct aging treatment process comprises the following steps: firstly, manufacturing a Ti-6Al-4V alloy sample by adopting an SLM technology, and then putting the SLM molded Ti-6Al-4V alloy sample into a vacuum heat treatment furnace for direct aging treatment, and finally, taking out the sample after furnace cooling or air cooling. According to the method, through direct aging treatment, a natural alpha'martensite structure in the Ti-6Al-4V alloy formed through SLM is decomposed into an alpha + beta double-phase structure, the front solid solution-quenching process in traditional solid solution aging treatment is not needed, and the purposes of optimizing structure uniformity and improving plasticity are achieved. The aging treatment cost and the quenching risk of the SLM titanium alloy are reduced, and the plasticity of the SLM titanium alloy can be remarkably improved while high strength is kept. The method is simple in process, low in cost and suitable for large-scale industrial application.

The disclosure provides Si-free aluminum alloys comprising Ce, Zn, and Mg suitable for laser powder bed fusion (LPBF) 3D printing. The printed components can be subjected to hot isostatic pressing and further heat treated to provide 3D printed components exhibiting higher hardness than existing Al-Si based alloys produced under the same conditions. The Si-free aluminum alloy resists coarsening of second phase on HIP, retaining high strength and hardness. The alloy also does not need separate solutionizing and water quenching following HIP, thus saving cost, time and permitting design of more delicate and intricate geometries.

The invention relates to the technical field of additive manufacturing 3D printing, and discloses a 3D printing head for a continuous fiber reinforced composite material and a printing method. A concentric circle type step temperature control module is used for applying preset step type temperature fields distributed from inside to outside in a gradient mode to adjacent printing layer deposition tows and current deposition tows in the printing process, and the grain size and uniformity of crystalline resin in the adjacent printing layer deposition tows and the current deposition tows are regulated and controlled. The large deformation degree of a printed product after forming is avoided; and meanwhile, in the printing process, secondary heating melting is conducted on deposition tows of adjacent printing layers, under the action of a preset pressure field, fusion of the deposition tows of the adjacent printing layers and current deposition tows is promoted, the bonding strength between printing layers / channels is improved, and then the mechanical property of a 3D printing continuous fiber additive manufacturing printing product is improved.

The invention discloses a bypass laser scanning path planning method for additive manufacturing, and relates to the technical field of additive manufacturing, a printing area and an initial position are determined, the whole printing path is divided into a straight line section and an arc section, an area assistant is distributed for each divided area, a communication link is established, and the communication link is connected with the straight line section and the arc section; the regional assistant is provided with an independent virtual computing resource space; self-adaptive segmentation is executed through each regional assistant, communication with adjacent regional assistants is carried out by using a communication link when local control is executed, and a segmentation state and a result are synchronized; generating a virtual adhesive to carry out smooth transition and error compensation on a splicing gap; and after splicing is completed, submitting the whole path after splicing to a printing control system to execute printing. According to the method, adaptive path planning, multi-region parallel path segmentation task processing and segmented region high-precision splicing according to the local features of the printing region are realized, and efficient and high-quality additive manufacturing printing is achieved.

The invention belongs to the technical field of additive manufacturing, and particularly relates to a strong electromagnetic pulse-ultrasonic auxiliary electric arc additive manufacturing platform. The platform body is provided with an upper substrate used for providing an initial plane for electric arc additive manufacturing; the water cooling device comprises a water cooling box used for containing cooling water, and the substrate is contained in the water cooling box; the base plate locking clamp comprises a positioning clamping table and a clamping device. The positioning clamping table and the clamping device are arranged on the two sides of the upper base plate and matched to form a fixing structure for fixing the relative positions of the upper base plate and the platform body. The welding gun head is connected with the six-axis mechanical arm and is used for carrying out additive manufacturing on the upper substrate; the clamping device and the welding gun head are arranged on the two opposite sides of the upper base plate in a spaced mode. And the clamping device is partially arranged outside the water cooling box. The clamping device and the welding gun head are arranged on the two sides of the water cooling box respectively, space interference between the clamping device and the welding gun head in the working process can be effectively avoided, meanwhile, a principle heat source of the clamping device can be guaranteed, and normal work of the clamping device is guaranteed.

The invention relates to the technical field of additive manufacturing, and discloses a method and equipment for restraining the crack defect of a high-temperature alloy difficult to weld in laser additive manufacturing. When the gradient of a first molten pool is larger than a preset temperature gradient threshold value, a metal powder scanning area corresponding to each layered slice of a target part can be fused through a composite laser spot; the central light spot is used for providing enough energy to melt metal powder and form a stable molten pool, and the annular light spot preheats the periphery of the molten pool to adjust temperature distribution of the molten pool. The second laser power needed by the annular light spot is determined according to the molten pool center temperature and the molten pool radius generated by the center light spot in the scanning area at the preset scanning speed, so that accurate control over the gradient and the cooling rate of the molten pool is met, the molten pool can be cooled more uniformly in the solidification process, and the solidification quality of the molten pool is improved. The defects of cracks, air holes and the like caused by high temperature gradient and high cooling rate are effectively reduced, and the problem that high-performance high-temperature alloy laser additive manufacturing cracks are difficult to weld is solved.

The invention discloses an annular furnace heat-resistant supporting forged chassis and an additive manufacturing process and a fixing device thereof, and belongs to the technical field of plating of metal materials, and the annular furnace heat-resistant supporting forged chassis comprises the steps that heat-resistant alloy steel base metal with specific components is prepared; carrying out laser texturing and nickel-based alloy bottom layer pretreatment on the surface of the steel plate; performing laser cladding on high-silicon high-temperature alloy powder containing niobium and rare earth elements to form a functional cladding layer, and performing gradient cladding on the edge of the atmosphere guide hole; and finally, carrying out heat treatment and assembling with a fan-shaped refractory brick fixing device. A composite oxide film and a multi-scale strengthening system are constructed, hydrogen resistance and brittleness resistance are effectively achieved, interface thermal stress is relieved, cracking and stripping of a cladding layer are avoided, a fixing device adapts to thermal expansion, the atmosphere is dredged, and the annealing uniformity of a steel coil is improved; the problems of creep deformation, hydrogen embrittlement, cladding layer stripping and thermal stress cracking of a traditional supporting component under the conditions of high temperature, heavy load and nitrogen and hydrogen atmosphere are solved.

The invention discloses a fiber composite material defect type and distribution prediction method based on comparative learning. The method comprises the following steps: firstly, deploying a data acquisition system, acquiring surface temperature distribution of a composite material by using a thermal imaging camera, monitoring key manufacturing parameters such as laser power, scanning speed and layer thickness through a process parameter sensor, and constructing a multi-modal data set; secondly, designing a double-flow encoder architecture, extracting defect texture features in thermal imaging through a convolutional neural network and a full connection layer, performing standardized embedding on process parameters, and introducing a contrast loss function to realize multi-modal feature alignment; and then constructing a representation fusion module, inputting the image and parameter features into a defect classifier and a spatial distribution regression device, and obtaining a prediction network through training. And developing a defect prediction and evaluation system, deploying a model and evaluating defect influence in combination with a performance database. And finally, a closed-loop feedback mechanism is established, and process parameters of additive manufacturing equipment are adjusted according to a prediction result to reduce the defect generation probability. According to the method, the defect type and distribution of the fiber composite material are effectively predicted, the process is optimized, and the product quality is improved.