Search for: All records

Inkjet three-dimensional (3D) printing has emerged as a transformative manufacturing technique, finding applications in diverse fields such as biomedical, metal fabrication, and functional materials production. It involves precise deposition of materials onto a moving substrate through a nozzle, achieving submillimeter scale resolution. However, the dynamic nature of droplet deposition introduces uncertainties, challenging consistent quality control. Current process monitoring, relying on image-based techniques, is slow and limited, hindering real-time feedback in erratic droplet ejection. In response to these challenges, we present the zero-dimensional ultrafast sensing (0-DUS) system, a novel, cost-effective, in situ monitoring tool designed to assess the quality of drop-on-demand inkjet printing. The 0-DUS system leverages the sensitivity of the light-beam field interference effect to rapidly and precisely detect and analyze localized droplets. Two core technical advancements drive this innovation: first, the exploration of integral sensing of the computational light-beam field, which allows for efficient extraction of temporal and spatial information about droplet evolution, introducing a novel in situ sensing modality; second, the establishment of a robust mapping mechanism that aligns sensor data with image-based data, facilitating accurate estimation of droplet characteristics. We successfully implemented the 0-DUS system within a commercial inkjet printer and conducted a comparative analysis with ground truth data. Our experimental results demonstrate a detection accuracy exceeding 95%, even at elevated speeds, allowing for an impressive in situ certification throughput of up to 500 Hz. Consequently, our proposed 0-DUS system meets the stringent quality assurance requirements, thereby expanding the potential applications of inkjet printing across a wide spectrum of industrial sectors. 

Abstract In recent years, inkjet 3D printing has rapidly gained prominence as a disruptive fabrication technique that has witnessed ever-increasing demand in the fields of biomedicine, metal manufacturing, electronics, and functional material production. This innovative approach involves precise deposition of controlled amounts of material onto a moving substrate through a nozzle, achieving impressive sub-millimeter scale resolution by leveraging the concepts of micro-droplet deposition. However, the dynamic nature of the process introduces significant challenges related to consistency and quality control, especially in terms of reproducibility and repeatability. The key input parameters governing this process, such as pressure, voltage, jetting frequency, and duty cycle, are interrelated, entailing the identification of optimal settings in order to realize high-quality jetting. At present, the data collection heavily relies on image-based methods which are inherently slow and often fail to encompass the entirety of the data, making it difficult to determine the relation between the input parameters and jet characteristics. To address this multidimensional difficulty, we developed a unique approach based on light-beam field interruption to collect critical jet data at high speeds. This novel approach collects both temporal and spatial information on droplet evolution, making it a vital tool for enhancing our ability to attain high accuracy and control in inkjet 3D printing. To illustrate the efficacy of our approach, we model the extracted features derived from the process parameters and the extracted data to predict the droplet jetting behavior and droplet size. Specifically, a decision tree classifier is used to predict the jetting behavior and discern between “ideal” and “non-ideal” jetting behaviors. Simultaneously, a linear regression model was employed to predict the droplet size within the “ideal jetting” class based on the interplay of process parameters and the extracted features. The results emphasize the system’s accuracy in capturing the droplet behavior and size using our light-beam field interference sensing module. Furthermore, these findings establish a crucial foundation for the implementation of real-time feedback control loop in the inkjet printing process, promising advancements in adaptability and precision. 

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. 

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. 

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. 

Abstract Electrospinning is a promising process to fabricate functional parts from macrofibers and nanofibers of bio-compatible materials including collagen, polylactide (PLA), and polyacrylonitrile (PAN). However, the functionality of the produced parts highly rely on quality, repeatability, and uniformity of the electrospun fibers. Due to the variations in material composition, process settings, and ambient conditions, the process suffers from large variations. In particular, the fiber formation in the stable regime (i.e., Taylor cone and jet) and its propagation to the substrate plays the most significant role in the process stability. This work aims to designing a fast process monitoring tool from scratch for monitoring the dynamic electrospinning process based on the Taylor cone and jet videos. Nevertheless, this is challenging since the videos are of high frequency and high dimension, and the monitoring statistics may not have a parametric distribution. To achieve this goal, a framework integrating image analysis, sketch-based tensor decomposition, and non-parametric monitoring, is proposed. In particular, we use Tucker tensor-sketch (Tucker-TS) based tensor decomposition to extract the sparse structure representations of the videos. Additionally, the extracted monitoring variables are non-normally distributed, hence non-parametric bootstrap Hotelling T2 control chart is deployed to handle this issue during the monitoring. The framework is demonstrated by electrospinning a PAN-based polymeric solution. Finally, it is demonstrated that the proposed framework, which uses Tucker-TS, largely outperformed the computational speed of the alternating least squares (ALS) approach for the Tucker tensor decomposition, i.e., Tucker-ALS, in various anomaly detection tasks while keeping the comparable anomaly detection accuracy.