Data-Driven Microstructure and Microhardness Design in Additive Manufacturing Using a Self-Organizing Map

To design microstructure and microhardness in the additive manufacturing(AM)of nickel(Ni)-based superalloys,the present work develops a novel data-driven approach that combines physics-based models,experimental measurements,and a data-mining method.The simulation is based on a computational thermal-fluid dynamics(CtFD)model,which can obtain thermal behavior,solidification parameters such as cooling rate,and the dilution of solidified clad.Based on the computed thermal information,dendrite arm spacing and microhardness are estimated using well-tested mechanistic models.Experimental microstructure and microhardness are determined and compared with the simulated values for validation.To visualize process-structure-properties(PSPs)linkages,the simulation and experimental datasets are input to a data-mining model-a self-organizing map(SOM).The design windows of the process parameters under multiple objectives can be obtained from the visualized maps.The proposed approaches can be utilized in AM and other data-intensive processes.Data-driven linkages between process,structure,and properties have the potential to benefit online process monitoring control in order to derive an ideal microstructure and mechanical properties.

Enriched reproducing kernel particle method for fractional advection–diffusion equation

The reproducing kernel particle method （RKPM） has been efficiently applied to problems with large deformations, high gradients and high modal density. In this paper, it is extended to solve a nonlocal problem modeled by a fractional advectiondiffusion equation （FADE）, which exhibits a boundary layer with low regularity. We formulate this method on a moving least-square approach. Via the enrichment of fractional-order power functions to the traditional integer-order basis for RKPM, leading terms of the solution to the FADE can be exactly reproduced, which guarantees a good approximation to the boundary layer. Numerical tests are performed to verify the proposed approach.

Reduced Order Machine Learning Finite Element Methods:Concept,Implementation,and Future Applications Dedicated to Professor Karl Stark Pister for his 95th birthday

This paper presents the concept of reduced order machine learning finite element(FE)method.In particular,we propose an example of such method,the proper generalized decomposition(PGD)reduced hierarchical deeplearning neural networks(HiDeNN),called HiDeNN-PGD.We described first the HiDeNN interface seamlessly with the current commercial and open source FE codes.The proposed reduced order method can reduce significantly the degrees of freedom for machine learning and physics based modeling and is able to deal with high dimensional problems.This method is found more accurate than conventional finite element methods with a small portion of degrees of freedom.Different potential applications of the method,including topology optimization,multi-scale and multi-physics material modeling,and additive manufacturing,will be discussed in the paper.

Mechanistic data-driven prediction of as-built mechanical properties in metal additive manufacturing

Metal additive manufacturing provides remarkable flexibility in geometry and component design,but localized heating/cooling heterogeneity leads to spatial variations of as-built mechanical properties,significantly complicating the materials design process.To this end,we develop a mechanistic data-driven framework integrating wavelet transforms and convolutional neural networks to predict location-dependent mechanical properties over fabricated parts based on process-induced temperature sequences,i.e.,thermal histories.The framework enables multiresolution analysis and importance analysis to reveal dominant mechanistic features underlying the additive manufacturing process,such as critical temperature ranges and fundamental thermal frequencies.We systematically compare the developed approach with other machine learning methods.The results demonstrate that the developed approach achieves reasonably good predictive capability using a small amount of noisy experimental data.It provides a concrete foundation for a revolutionary methodology that predicts spatial and temporal evolution of mechanical properties leveraging domain-specific knowledge and cutting-edge machine and deep learning technologies.

Modeling process-structure-property relationships for additive manufacturing

This paper presents our latest work on comprehensive modeling of process-structure-property relationships for additive manufacturing （AM） materials, including using data-mining techniques to close the cycle of design-predict-optimize. To illustrate the process- structure relationship, the multi-scale multi-physics pro- cess modeling starts from the micro-scale to establish a mechanistic heat source model, to the meso-scale models of individual powder particle evolution, and finally to the macro-scale model to simulate the fabrication process of a complex product. To link structure and properties, a high- efficiency mechanistic model, self-consistent clustering analyses, is developed to capture a variety of material response. The model incorporates factors such as voids, phase composition, inclusions, and grain structures, which are the differentiating features of AM metals. Furthermore, we propose data-mining as an effective solution for novel rapid design and optimization, which is motivated by the numerous influencing factors in the AM process. We believe this paper will provide a roadmap to advance AM fundamental understanding and guide the monitoring and advanced diagnostics of AM processing.