More Like this

1. In-situ particle analysis with heterogeneous background: a machine learning approach

   https://doi.org/10.1038/s41598-024-59558-7  

   Alam, Adeeb Ibne; Rahman, Md Hafizur; Zia, Akhter; Lowry, Nate; Chakraborty, Prabuddha; Hassan, Md Rafiul; Khoda, Bashir (May 2024, Scientific Reports)

   Abstract We propose a novel framework that combines state-of-the-art deep learning approaches with pre- and post-processing algorithms for particle detection in complex/heterogeneous backgrounds common in the manufacturing domain. Traditional methods, like size analyzers and those based on dilution, image processing, or deep learning, typically excel with homogeneous backgrounds. Yet, they often fall short in accurately detecting particles against the intricate and varied backgrounds characteristic of heterogeneous particle–substrate (HPS) interfaces in manufacturing. To address this, we've developed a flexible framework designed to detect particles in diverse environments and input types. Our modular framework hinges on model selection and AI-guided particle detection as its core, with preprocessing and postprocessing as integral components, creating a four-step process. This system is versatile, allowing for various preprocessing, AI model selections, and post-processing strategies. We demonstrate this with an entrainment-based particle delivery method, transferring various particles onto substrates that mimic the HPS interface. By altering particle and substrate properties (e.g., material type, size, roughness, shape) and process parameters (e.g., capillary number) during particle entrainment, we capture images under different ambient lighting conditions, introducing a range of HPS background complexities. In the preprocessing phase, we apply image enhancement and sharpening techniques to improve detection accuracy. Specifically, image enhancement adjusts the dynamic range and histogram, while sharpening increases contrast by combining the high pass filter output with the base image. We introduce an image classifier model (based on the type of heterogeneity), employing Transfer Learning with MobileNet as a Model Selector, to identify the most appropriate AI model (i.e., YOLO model) for analyzing each specific image, thereby enhancing detection accuracy across particle–substrate variations. Following image classification based on heterogeneity, the relevant YOLO model is employed for particle identification, with a distinct YOLO model generated for each heterogeneity type, improving overall classification performance. In the post-processing phase, domain knowledge is used to minimize false positives. Our analysis indicates that the AI-guided framework maintains consistent precision and recall across various HPS conditions, with the harmonic mean of these metrics comparable to those of individual AI model outcomes. This tool shows potential for advancing in-situ process monitoring across multiple manufacturing operations, including high-density powder-based 3D printing, powder metallurgy, extreme environment coatings, particle categorization, and semiconductor manufacturing. 

   more » « less
2. Size-Based Filtration of Poly-Disperse Micro-Particle by Dipping

   https://doi.org/10.1115/MSEC2022-85680  

   Khalil, Md Ibrahim; Khoda, Bashir (June 2022, Proceedings of the ASME 2022 17th International Manufacturing Science and Engineering Conference)

   Abstract In manufacturing industries, spherical micro-particles are commonly used as (e.g., brazing powder, metal filler, and 3D printing powder) which are produced with droplet-based particle fabrication techniques. Such processes create spherical morphology but introduce polydispersity and follow a continuous exponential pattern commonly expressed with Rosin-Rammler expression. Sorting those micro-particles in a narrower size range is an important but difficult, costly, and challenging process. Here we demonstrate the successful separation of the particles from a poly-disperse mixture with a particle volume fraction of 10% by dipping process. Nickel-based micro-particles (avg. dia. 5.69 μm) are added in a binder-based liquid carrier system. To encounter the gravitational force, external kinetic energy in the form of agitation is applied to ensure the uniform dispersion of the particles. The cylindrical substrate is prepared and dipped in the ‘pseudo suspension’ to separate the particles by adhering to it. The substrate is dried, and images are taken to characterize the separated particles using image J software. A clear size distribution can be observed which is also plotted. Additionally, a relationship between the process parameter and sorted particles has been established. The proposed method is quick, controllable, and easy to implement, which can be a useful tool for sorting wide-range poly-disperse particles. 

   more » « less
3. Model-driven directed-energy-deposition process workflow incorporating powder flowrate as key parameter

   https://doi.org/10.1016/j.mfglet.2020.08.005  

   Traxel, Kellen; Malihi, Darin; Starkey, Kyler; Bandyopadhyay, Amit (August 2020, Manufacturing letters)

   null (Ed.)

   Process optimization for directed-energy-deposition, an industrial laser-based additive manufacturing technique, is a time-intensive endeavor for manufacturers. Herein we investigate the use of a modified analytical process-model based on powder-bed-fusion techniques, to predict quality build parameters by incorporating the effects of three key parameters: laser-power, scanning-speed, and powder flowrate. Titanium alloy (Ti6Al4V) tracks of varying parameters were built, studied, and used to predict parameters for quality builds used at different parameters. The model agreed well with experimental build quality at powder flowrates less than 6.5g/min, whereas, higher flowrates created significant unmelted-particle regions, despite optimal parameter predictions. Processing of multi-layer bulk samples revealed that parameters in the optimal range account for relative densities >99%, indicating quality bulk processing parameters. Our results indicate that process modeling with the incorporation of powder feedrate as a key parameter is possible using a commercial laser-based additive manufacturing system. 

   more » « less
4. Effect of dry or wet substrate deposition on the organic volume fraction of core–shell aerosol particles

   https://doi.org/10.5194/amt-12-2033-2019  

   Lee, Hansol D.; Kaluarachchi, Chathuri P.; Hasenecz, Elias S.; Zhu, Jonic Z.; Popa, Eduard; Stone, Elizabeth A.; Tivanski, Alexei V. (January 2019, Atmospheric Measurement Techniques)

   Abstract. Understanding the impact of sea spray aerosol (SSA) on theclimate and atmosphere requires quantitative knowledge of their chemicalcomposition and mixing states. Furthermore, single-particle measurements areneeded to accurately represent large particle-to-particle variability. Toquantify the mixing state, the organic volume fraction (OVF), defined as therelative organic volume with respect to the total particle volume, ismeasured after generating and collecting aerosol particles, often usingdeposition impactors. In this process, the aerosol streams are either driedor kept wet prior to impacting on solid substrates. However, the atmosphericcommunity has yet to establish how dry versus wet aerosol depositioninfluences the impacted particle morphologies and mixing states. Here, weapply complementary offline single-particle atomic force microscopy (AFM)and bulk ensemble high-performance liquid chromatography (HPLC) techniquesto assess the effects of dry and wet deposition modes on thesubstrate-deposited aerosol particles' mixing states. Glucose and NaClbinary mixtures that form core–shell particle morphologies were studied asmodel systems, and the mixing states were quantified by measuring the OVF ofindividual particles using AFM and compared to the ensemble measured byHPLC. Dry-deposited single-particle OVF data positively deviated from thebulk HPLC data by up to 60 %, which was attributed to significantspreading of the NaCl core upon impaction with the solid substrate. This ledto underestimation of the core volume. This problem was circumvented by (a) performing wet deposition and thus bypassing the effects of the solid corespreading upon impaction and (b) performing a hydration–dehydration cycle ondry-deposited particles to restructure the deformed NaCl core. Bothapproaches produced single-particle OVF values that converge well with thebulk and expected OVF values, validating the methodology. These findingsillustrate the importance of awareness in how conventional particledeposition methods may significantly alter the impacted particlemorphologies and their mixing states. 

   more » « less
5. Phase-Field Modeling of Wetting and Balling Dynamics in Powder Bed Fusion Process

   https://doi.org/https://doi.org/10.1063/5.0046771  

   Li, L.; Li, J.-Q.; Fan, T.-H. (April 2021, Physics of fluids)

   null (Ed.)

   In a powder bed fusion additive manufacturing (AM) process, the balling effect has a significant impact on the surface quality of the printing parts. Surface wetting helps the bonding between powder and substrate and the inter-particle fusion, whereas the balling effect forms large spheroidal beads around the laser beam and causes voids, discontinuities, and poor surface roughness during the printing process. To better understand the transient dynamics, a theoretical model with a simplified 2D configuration is developed to investigate the underlying fluid flow and heat transfer, phase transition, and interfacial instability along with the laser heating. We demonstrate that the degree of wetting and fast solidification counter-balance the balling effect, and the Rayleigh-Plateau flow instability plays an important role for cases with relatively low substrate wettability and high scanning rate. 

   more » « less