Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userA Physics-Informed Machine Learning Model for Porosity Analysis in Laser Powder Bed Fusion Additive Manufacturing
139
0
0.0
(
0
)
Added by
Rui Liu
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
To control part quality, it is critical to analyze pore generation mechanisms, laying theoretical foundation for future porosity control. Current porosity analysis models use machine setting parameters, such as laser angle and part pose. However, these setting-based models are machine dependent, hence they often do not transfer to analysis of porosity for a different machine. To address the first problem, a physics-informed, data-driven model (PIM), which instead of directly using machine setting parameters to predict porosity levels of printed parts, it first interprets machine settings into physical effects, such as laser energy density and laser radiation pressure. Then, these physical, machine independent effects are used to predict porosity levels according to pass, flag, fail categories instead of focusing on quantitative pore size prediction. With six learning methods evaluation, PIM proved to achieve good performances with prediction error of 10$sim$26%. Finally, pore-encouraging influence and pore-suppressing influence were analyzed for quality analysis.
rate research
Read More
Quality control in additive manufacturing can be achieved through variation control of the quantity of interest (QoI). We choose in this work the microstructural microsegregation to be our QoI. Microsegregation results from the spatial redistribution of a solute element across the solid-liquid interface that forms during solidification of an alloy melt pool during the laser powder bed fusion process. Since the process as well as the alloy parameters contribute to the statistical variation in microstructural features, uncertainty analysis of the QoI is essential. High-throughput phase-field simulations estimate the solid-liquid interfaces that grow for the melt pool solidification conditions that were estimated from finite element simulations. Microsegregation was determined from the simulated interfaces for different process and alloy parameters. Correlation, regression, and surrogate model analyses were used to quantify the contribution of different sources of uncertainty to the QoI variability. We found negligible contributions of thermal gradient and Gibbs-Thomson coefficient and considerable contributions of solidification velocity, liquid diffusivity, and segregation coefficient on the QoI. Cumulative distribution functions and probability density functions were used to analyze the distribution of the QoI during solidification. Our approach, for the first time, identifies the uncertainty sources and frequency densities of the QoI in the solidification regime relevant to additive manufacturing.
Melt pool (MP) temperature is one of the determining factors and key signatures for the properties of printed components during metal additive manufacturing (AM). The state-of-the art measurement systems are hindered by both the equipment cost and the large-scale data acquisition and processing demands. In this work, we introduce a novel coaxial high-speed single-camera two-wavelength imaging pyrometer (STWIP) system as opposed to the typical utilization of multiple cameras for measuring MP temperature profiles through a laser powder bed fusion (LPBF) process. Developed on a commercial LPBF machine (EOS M290), the STWIP system is demonstrated to be able to quantitatively monitor MP temperature and variation for 50 layers at high framerates (> 30,000 fps) during a print of five standard fatigue specimens. High performance computing is employed to analyze the acquired big data of MP images for determining each MPs average temperature and 2D temperature profile. The MP temperature evolution in the gage section of a fatigue specimen is also examined at a temporal resolution of 1ms by evaluating the derived MP temperatures of the printed samples first, middle and last layers. This paper is first of its kind on monitoring MP temperature distribution and evolution at such a large, detailed scale for longer durations in practical applications. Future work includes MP registration and machine learning of MP-Part Property relations.
Powder-based additive manufacturing techniques provide tools to construct intricate structures that are difficult to manufacture using conventional methods. In Laser Powder Bed Fusion, components are built by selectively melting specific areas of the powder bed, to form the two-dimensional cross-section of the specific part. However, the high occurrence of defects impacts the adoption of this method for precision applications. Therefore, a control policy for dynamically altering process parameters to avoid phenomena that lead to defect occurrences is necessary. A Deep Reinforcement Learning (DRL) framework that derives a versatile control strategy for minimizing the likelihood of these defects is presented. The generated control policy alters the velocity of the laser during the melting process to ensure the consistency of the melt pool and reduce overheating in the generated product. The control policy is trained and validated on efficient simulations of the continuum temperature distribution of the powder bed layer under various laser trajectories.
We develop a physics-informed machine learning approach for large-scale data assimilation and parameter estimation and apply it for estimating transmissivity and hydraulic head in the two-dimensional steady-state subsurface flow model of the Hanford Site given synthetic measurements of said variables. In our approach, we extend the physics-informed conditional Karhunen-Lo{e}ve expansion (PICKLE) method for modeling subsurface flow with unknown flux (Neumann) and varying head (Dirichlet) boundary conditions. We demonstrate that the PICKLE method is comparable in accuracy with the standard maximum a posteriori (MAP) method, but is significantly faster than MAP for large-scale problems. Both methods use a mesh to discretize the computational domain. In MAP, the parameters and states are discretized on the mesh; therefore, the size of the MAP parameter estimation problem directly depends on the mesh size. In PICKLE, the mesh is used to evaluate the residuals of the governing equation, while the parameters and states are approximated by the truncated conditional Karhunen-Lo{e}ve expansions with the number of parameters controlled by the smoothness of the parameter and state fields, and not by the mesh size. For a considered example, we demonstrate that the computational cost of PICKLE increases near linearly (as $N_{FV}^{1.15}$) with the number of grid points $N_{FV}$, while that of MAP increases much faster as $N_{FV}^{3.28}$. We demonstrated that once trained for one set of Dirichlet boundary conditions (i.e., one river stage), the PICKLE method provides accurate estimates of the hydraulic head for any value of the Dirichlet boundary conditions (i.e., for any river stage).
The future of space exploration missions will rely on technologies increasing their endurance and self-sufficiency, including for manufacturing objects on-demand. We propose a process for handling and additively manufacturing powders that functions independently of the gravitational environment and with no restriction on feedstock powder flowability. Based on a specific sequence of boundary loads applied to the granular packing, powder is transported to the printing zone, homogenized and put under compression to increase the density of the final part. The powder deposition process is validated by simulations that show the homogeneity and density of deposition to be insensitive to gravity and cohesion forces within the DEM model. We further provide an experimental proof of concept of the process by successfully 3D printing parts on-ground and in weightlessness, on parabolic flight. Powders exhibiting high and low flowability are used as model feedstock material to demonstrate the versatility of the process, opening the way for additive manufacturing of recycled material.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
