Advancements in machine learning for material design and process optimization in the field of additive manufacturing

Additive manufacturing technology is highly regarded due to its advantages,such as high precision and the ability to address complex geometric challenges.However,the development of additive manufacturing process is constrained by issues like unclear fundamental principles,complex experimental cycles,and high costs.Machine learning,as a novel artificial intelligence technology,has the potential to deeply engage in the development of additive manufacturing process,assisting engineers in learning and developing new techniques.This paper provides a comprehensive overview of the research and applications of machine learning in the field of additive manufacturing,particularly in model design and process development.Firstly,it introduces the background and significance of machine learning-assisted design in additive manufacturing process.It then further delves into the application of machine learning in additive manufacturing,focusing on model design and process guidance.Finally,it concludes by summarizing and forecasting the development trends of machine learning technology in the field of additive manufacturing.

Compression behavior of 316L lattice structures produced by indirect additive manufacturing

As a new type of lightweight structure,metallic lattice structure has higher stiffness and strength to weight ratio.To freely obtain 316L lattice structures with designed cell structure and adjustable porosity,additive manufacturing combined with investment casting was conducted to fabricate the 316L lattice structures with Kelvin cell.The compression simulation of 316L lattice structures with different porosities was carried out by using the finite element method.The numerical simulation results were verified by compression experiment,and the simulated results were consistent with the compression tests.The compressive mechanical properties of 316L lattice structures are directly related to porosity and independent of strut diameters.The 316L lattice structures with Kelvin cell have a smooth stress-strain curve and obvious plastic platform,and the hump stress-strain curves are avoided.

Numerical simulation and experimental validation on fabrication of nickel-based superalloy Kagome lattice sandwich structures

Nickel-based superalloy lattice sandwich structures present higher stiffness,higher strength and higher temperature resistance in comparison with other metals.In this study,the Kagome unit was adopted to design the lattice sandwich structure and ProCAST software was used to simulate the filling and solidification processes of the nickel-based superalloy.Grain morphology and sizes of the nickel-based superalloy lattice sandwich structures were simulated by using of cellular automaton coupled with finite element model(CAFE),and indirect additive manufacture combining with investment casting were carried out to fabricate the nickel-based superalloy lattice sandwich structures.The calculated grain morphology and sizes are in good agreement with the experimental results.The grains are mainly equiaxed with an average size of about 500µm.The simulated results also show that the superheat of melting and the mold preheated temperature have significant influence on the grain size of the Kagome lattice sandwich structures,lower superheat of melting and mold preheated temperatures are encouraged to obtain the fine grains while assuring the integrity of the Kagome lattice sandwich structures for industrial application.

Effects of laser power density on static and dynamic mechanical properties of dissimilar stainless steel welded joints

The mechanical properties of laser welded joints under impact loadings such as explosion and car crash etc. are critical for the engineering designs. The hardness, static and dynamic mechanical properties of AISI304 and AISI316L dissimilar stainless steel welded joints by CO2 laser were experimentally studied. The dynamic strainstress curves at the strain rate around 103 s-1 were obtained by the split Hopkinson tensile bar （SHTB）. The static mechanical properties of the welded joints have little changes with the laser power density and all fracture occurs at 316 L side. However, the strain rate sensitivity has a strong depen- dence on laser power density. The value of strain rate factor decreases with the increase of laser power density. The welded joint which may be applied for the impact loading can be obtained by reducing the laser power density in the case of welding quality assurance.

Parametric study on single shot peening by dimensional analysis method incorporated with finite element method

Shot peening is a widely used surface treatment method by generating compressive residual stress near the surface of metallic materials to increase fatigue life and re- sistance to corrosion fatigue, cracking, etc. Compressive re- sidual stress and dent profile are important factors to eval- uate the effectiveness of shot peening process. In this pa- per, the influence of dimensionless parameters on maximum compressive residual stress and maximum depth of the dent were investigated. Firstly, dimensionless relations of pro- cessing parameters that affect the maximum compressive residual stress and the maximum depth of the dent were de- duced by dimensional analysis method. Secondly, the in- fluence of each dimensionless parameter on dimensionless variables was investigated by the finite element method. Fur- thermore, related empirical formulas were given for each di- mensionless parameter based on the simulation results. Fi- nally, comparison was made and good agreement was found between the simulation results and the empirical formula, which shows that a useful approach is provided in this pa- per for analyzing the influence of each individual parameter.