skip to main content


Search for: All records

Award ID contains: 2134409

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Abstract

    Teeth scans are essential for many applications in orthodontics, where the teeth structures are virtualized to facilitate the design and fabrication of the prosthetic piece. Nevertheless, due to the limitations caused by factors such as viewing angles, occlusions, and sensor resolution, the 3D scanned point clouds (PCs) could be noisy or incomplete. Hence, there is a critical need to enhance the quality of the teeth PCs to ensure a suitable dental treatment. Toward this end, we propose a systematic framework including a two-step data augmentation (DA) technique to augment the limited teeth PCs and a hybrid deep learning (DL) method to complete the incomplete PCs. For the two-step DA, we first mirror and combine the PCs based on the bilateral symmetry of the human teeth and then augment the PCs based on an iterative generative adversarial network (GAN). Two filters are designed to avoid the outlier and duplicated PCs during the DA. For the hybrid DL, we first use a deep autoencoder (AE) to represent the PCs. Then, we propose a hybrid approach that selects the best completion to the teeth PCs from AE and a reinforcement learning (RL) agent-controlled GAN. Ablation study is performed to analyze each component’s contribution. We compared our method with other benchmark methods including point cloud network (PCN), cascaded refinement network (CRN), and variational relational point completion network (VRC-Net), and demonstrated that the proposed framework is suitable for completing teeth PCs with good accuracy over different scenarios.

     
    more » « less
    Free, publicly-accessible full text available August 1, 2024
  2. Abstract

    Inkjet printing (IJP) is an additive manufacturing process capable to produce intricate functional structures. The IJP process performance and the quality of the printed parts are considerably affected by the deposited droplets’ volume. Obtaining consistent droplets volume during the process is difficult to achieve because the droplets are prone to variations due to various material properties, process parameters, and environmental conditions. Experimental (i.e., IJP setup observations) and computational (i.e., computational fluid dynamics (CFD)) analysis are used to study the droplets variability; however, they are expensive and computationally inefficient, respectively. The objective of this paper is to propose a framework that can perform fast and accurate droplet volume predictions for unseen IJP driving voltage regimes. A two-step approach is adopted: (1) an emulator is constructed from the physics-based droplet volume simulations to overcome the computational complexity and (2) the emulator is calibrated by incorporating the experimental IJP observations. In particular, a scaled Gaussian stochastic process (s-GaSP) is deployed for the emulation and calibration. The resulting surrogate model is able to rapidly and accurately predict the IJP droplets volume. The proposed methodology is demonstrated by calibrating the simulated data (i.e., CFD droplet simulations) emulator with experimental data from two distinct materials, namely glycerol and isopropyl alcohol.

     
    more » « less
  3. Abstract

    Direct ink writing (DIW) process is a facile additive manufacturing technology to fabricate three-dimensional (3D) objects with various materials. Its versatility has attracted considerable interest in academia and industry in recent years. As such, upsurging endeavors are invested in advancing the ink flow behaviors in order to optimize the process resolution and the printing quality. However, so far, the physical phenomena during the DIW process are not revealed in detail, leaving a research gap between the physical experiments and its underlying theories. Here, we present a comprehensive analytical study of non-Newtonian ink flow behavior during the DIW process. Different syringe-nozzle geometries are modeled for the comparative case studies. By using the computational fluid dynamics (CFD) simulation method, we reveal the shear-thinning property during the ink extrusion process. Besides, we study the viscosity, shear stress, and velocity fields, and analyze the advantages and drawbacks of each syringe-nozzle model. On the basis of these investigations and analyses, we propose an improved syringe-nozzle geometry for stable extrusion and high printing quality. A set of DIW printing experiments and rheological characterizations are carried out to verify the simulation studies. The results developed in this work offer an in-depth understanding of the ink flow behavior in the DIW process, providing valuable guidelines for optimizing the physical DIW configuration toward high-resolution printing and, consequently, improving the performance of DIW-printed objects.

     
    more » « less
  4. Abstract

    Inkjet printing (IJP) is one of the promising additive manufacturing techniques that yield many innovations in electronic and biomedical products. In IJP, the products are fabricated by depositing droplets on substrates, and the quality of the products is highly affected by the droplet pinch-off behaviors. Therefore, identifying pinch-off behaviors of droplets is critical. However, annotating the pinch-off behaviors is burdensome since a large amount of images of pinch-off behaviors can be collected. Active learning (AL) is a machine learning technique which extracts human knowledge by iteratively acquiring human annotation and updating the classification model for the pinch-off behaviors identification. Consequently, a good classification performance can be achieved with limited labels. However, during the query process, the most informative instances (i.e., images) are varying and most query strategies in AL cannot handle these dynamics since they are handcrafted. Thus, this paper proposes a multiclass reinforced active learning (MCRAL) framework in which a query strategy is trained by reinforcement learning (RL). We designed a unique intrinsic reward signal to improve the classification model performance. Moreover, how to extract the features from images for pinch-off behavior identification is not trivial. Thus, we used a graph convolutional network for droplet image feature extraction. The results show that MCRAL excels AL and can reduce human efforts in pinch-off behavior identification. We further demonstrated that, by linking the process parameters to the predicted droplet pinch-off behaviors, the droplet pinch-off behavior can be adjusted based on MCRAL.

     
    more » « less
  5. Abstract

    The assumption of normality is usually tied to the design and analysis of an experimental study. However, when dealing with lifetime testing and censoring at fixed time intervals, we can no longer assume that the outcomes will be normally distributed. This generally requires the use of optimal design techniques to construct the test plan for specific distribution of interest. Optimal designs in this situation depend on the parameters of the distribution, which are generally unknown a priori. A Bayesian approach can be used by placing a prior distribution on the parameters, thereby leading to an appropriate selection of experimental design. This, along with the model and number of predictors, can be used to derive the D‐optimal design for an allowed number of experimental runs. This paper explores using this Bayesian approach on various lifetime regression models to select appropriate D‐optimal designs in regular and irregular design regions.

     
    more » « less
  6. Free, publicly-accessible full text available September 1, 2024
  7. Free, publicly-accessible full text available August 26, 2024
  8. Free, publicly-accessible full text available July 31, 2024