Search

• Defect monitoring via convolutional neural networks (CNN). • Augmentation of experimental CNN training data with simulated data. • Finite element modeling of DMLS process. • Evaluation of the approach using standard CNN performance metrics. In the additive manufacturing (AM) industry, the direct metal laser solidification (DMLS) process has received significant research interest because of its ultra-high precision and geometry variability. However, many possible process errors can happen during the printing process and in-situ quality control is quite challenging because of the lack of appropriate monitoring and analysis capabilities. Thus, in this work, a part-scale finite element method (FEM) model is developed to investigate the heat transfer behavior of the DMLS process and to extract experimentally relevant thermal features. Specifically, a microscopic and a mesoscale sub-model are initially developed to describe powder properties and the laser behaviors, respectively, and their outputs are directly incorporated in the part-scale FEM model. The FEM model-generated data are then processed to replicate the long-wave infrared (LWIR) camera sensor outputs. Finally, both the experimental and FEM model-generated images are used to train machine learning algorithms for in-situ defect detection applications. In addition, we are endeavoring to look into a convolutional neural network utilizing such realistic thermal features from LWIR images with and without a variety of simulated data augmentation to examine its contribution to the CNN training. The thermal feature extraction and the machine learning algorithm are then utilized for the data reduction purpose. Also, a transmission strategy is demonstrated to filter out a significant amount of redundant data while maintaining high model prediction quality. [ABSTRACT FROM AUTHOR]

• Kinetic Monte-Carlo modeling of PEALD. • Calculation of kMC model parameters via DFT. • Comparison with experimental data. • Neural network modeling for determining optimal operating conditions. Plasma enhanced atomic layer deposition (PEALD) is one of the most widely adopted deposition methods used in the semiconductor industry. It is chosen largely due to its superior ability to produce ultra-thin high-k dielectric films, which are needed for the further miniaturization of microelectronic devices with the pace of Moore's Law. In contrast to the traditional thermal atomic layer deposition (ALD) method, PEALD allows for high deposition growth per cycle (GPC) under low operating temperature with the help of high energy plasma species. Despite the experimental effort in finding new precursors and plasmas, the detailed surface structures and reaction mechanisms in various PEALD processes remain hard to understand because of the limitation of current in-situ monitoring techniques and the deficiency of the first-principles based analysis. Therefore, in this work, an accurate, yet efficient kinetic Monte Carlo (kMC) model and an associated machine learning (ML) analysis are proposed to capture the surface deposition mechanism and to propose optimal operating conditions of the HfO 2 thin-film PEALD using tetrakis-dimethylamino-Hafnium (TDMAHf) and oxygen plasma. Density Functional Theory (DFT) calculations are performed to obtain the key kinetic parameters and the structural details, subsequently employed in the kMC model. After the kMC model is validated by experimental data, a database is generated to explore a variety of precursor partial pressure and substrate temperature combinations using the kMC algorithm. A feed-forward Bayesian regularized artificial neural network (BRANN) is then constructed to characterize the input–output relationship and to investigate the optimal operating conditions. [ABSTRACT FROM AUTHOR]

• Multiscale computational fluid dynamics (CFD) modeling of ALD reactor. • Machine-learning modeling using multiscale CFD model data. • Use of machine learning model to optimize ALD cycle time. • Significant reduction of ALD cycle time versus fixed-time deposition. Atomic layer deposition (ALD) is a widely utilized deposition technology in the semiconductor industry due to its superior ability to generate highly conformal films and to deposit materials into high aspect-ratio geometric structures. However, ALD experiments remain expensive and time-consuming, and the existing first-principles based models have not yet been able to provide solutions to key process outputs that are computationally efficient, which is necessary for on-line optimization and real-time control. In this work, a multiscale data-driven model is proposed and developed to capture the macroscopic process domain dynamics with a linear parameter varying model, and to characterize the microscopic domain film growth dynamics with a feed-forward artificial neural network (ANN) model. The multiscale data-driven model predicts the transient deposition rate from the following four key process operating parameters that can be manipulated, measured or estimated by process engineers: precursor feed flow rate, operating pressure, surface heating, and transient film coverage. Our results demonstrate that the multiscale data-driven model can efficiently characterize the transient input-output relationship for the SiO 2 thermal ALD process using bis(tertiary-butylamino)silane (BTBAS) as the Si precursor. The multiscale data-driven model successfully reduces the computational time from 0.6 to 1.2 h for each time step, which is required for the first-principles based multiscale computational fluid dynamics (CFD) model, to less than 0.1 s, making its real-time usage feasible. The developed data-driven modeling methodology can be further generalized and used for other thermal ALD or similar deposition systems, which will greatly enhance the feasibility of industrial manufacturing processes. [ABSTRACT FROM AUTHOR]

• Computational fluid dynamics modeling of ALD gas phase. • Multiscale CFD modeling of entire ALD chamber. • Numerical analysis of multiscale CFD model. • Chamber geometry optimization for spatial thin film uniformity. This work develops a first-principles-based three-dimensional, multiscale computational fluid dynamics (CFD) model, together with reactor geometry optimizations, of SiO 2 thin-film thermal atomic layer deposition (ALD) using bis(tertiary-butylamino)silane (BTBAS) and ozone as precursors. Specifically, an accurate macroscopic CFD model of the ALD reactor chamber gas-phase development is integrated with a detailed microscopic kinetic Monte Carlo (kMC) model that was developed in Ding et al. (2019) , accounting for the microscopic lattice structure, atomic interactions and detailed surface chemical reactions. The multiscale information exchange and the transient simulation of the microscopic distributed kMC algorithms and the macroscopic CFD model are achieved through a parallel processing message passing interface (MPI) structure. Additionally, density functional theory (DFT)-based calculations are adopted to compute the key thermodynamic and kinetic parameters for the microscopic thin-film growth process. Recognizing the transient non-uniformity and the possibility to reduce the current ALD cycle time, the optimal configuration of reactor geometry is designed and evaluated including a showerhead panel adjustment and geometry modifications on reactor inlet and upstream. It is demonstrated that with suitable reactor chamber design the required BTBAS ALD half-cycle time can be reduced by 39.6%. [ABSTRACT FROM AUTHOR]

• DFT-based calculation of microscopic model parameters. • Microscopic modeling of ALD. • Understanding of operational limits of ALD. • Cycle time optimization of ALD using ANN. This work develops a comprehensive framework for first-principles-based microscopic modeling, data-driven input/output modeling and optimal operation of thermal atomic layer deposition (ALD) of SiO 2 thin-films using bis(tertiary-butylamino)silane (BTBAS) and ozone as precursors. Specifically, we initially utilize Density Functional Theory (DFT)-based calculations for the computation of the key thermodynamic and kinetic parameters, which are then used in the microscopic modeling of the ALD process. Subsequently, a detailed microscopic model is constructed, accounting for the microscopic lattice structure and atomic interactions, as well as multiple microscopic film growth processes including physisorption, abstraction and competing chemical reaction pathways. Kinetic Monte-Carlo (kMC) algorithms are utilized to obtain computationally efficient microscopic model solutions while preserving model fidelity. The obtained kMC simulation results are used to train Artificial Neural Network (ANN)-based data-driven models that capture the relationship between operating process parameters and time to ALD cycle completion. Specifically, a dense two-hidden-layer feed-forward ANN is constructed to find a feasible range of ALD operating conditions accounting for industrial considerations, and a Bayesian Regularized ANN is constructed to implement the cycle-to-cycle optimization of ALD cycle time. Extensive simulation results demonstrate the effectiveness of the proposed approaches. The kMC models successfully achieves a growth per cycle (GPC) of 1.8 Å per cycle, which is in the range of reported experimental values. The ANN models accurately predict deposition time to steady-state from the given operating condition input, and the cycle time optimization using BRANN model reduces the conventional BTBAS cycle time by 60%. [ABSTRACT FROM AUTHOR]