A Computer Vision Approach to Evaluate Powder Flowability for Metal Additive Manufacturing

Zhang, Jiahui; Habibnejad-korayem, Mahdi; Liu, Zhiying; Lyu, Tianyi; Sun, Qiang; Zou, Yu

doi:10.1007/s40192-021-00226-3

Cited by 11 publications

(4 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Discussionmentioning

confidence: 99%

“…Thus, it is critical to correlate as-received powder characteristics (e.g., particle size distribution, shape, morphology, flowability) with the critical velocity, deposition efficiency, porosity, and microstructure of as-produced parts. A few methodologies used for beam-based AM processes, both experimental, and machine learning methods can be employed for the cold spray process. Hybrid additive manufacturing: the combination of CSAM and other AM methods. Numerical simulations, such as FEM, can be employed for visualizing and understanding the dynamic process of cold-spraying and laser-based AM processes. , There are a large variety of processing parameters in the cold spray process, including gas type, temperature, and pressure, working distance, scanning speed, and spray angle.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Cold Spray Additive Manufacturing: Microstructure Evolution and Bonding Features

Zou

2021

Acc. Mater. Res.

Self Cite

View full text Add to dashboard Cite

Conspectus Most metal additive manufacturing (AM) methods involve the melting or sintering of feedstock powder or wire using an energy source (laser, electron beam, or electric arc). Solid-state AM, sometimes also known as non-beam-based AM, is a process in which the deposited material does not melt and is built up layer-by-layer, typically through severe plastic deformation. Initially considered to be a coating technique, by virtue of its high deposition rate, cold spray additive manufacturing (CSAM) is attractive as a solid-state AM technology. In the CSAM process, metal powder particles are impacted onto a substrate at a supersonic velocity and relatively low temperature. The CSAM process reduces or eliminates many problems associated with melting or beam-based AM methods, making the CSAM technically attractive for a wide range of applications, such as in the aerospace, automobile, marine, biomedical, machinery, and energy sectors. In this Account, the author briefly reviews the setup of a cold spray system and discusses the strengths and drawbacks of CSAM compared with thermal sprays and beam-based AM processes, as well as applications in relevant industries. The author summarizes the bonding mechanisms proposed for the cold spray process. The focus of this Account is to review the microstructure evolution of several typical model metals (copper, nickel, aluminum, and titanium) during the cold spray process. The author shows a large variety of microstructure characteristics (recrystallized grains, annealing twins, shear bands, submicron-sized grains, deformation twins, and nanometer-sized grains) in cold-sprayed copper, dynamic recrystallization of cold-sprayed nickel, and the formation of refined grains even below 10 nm in size in cold-sprayed aluminum. The magnitude of the stacking fault energy of as-sprayed materials considerably influences the microstructure after cold spray and postprocessing. Due to the relatively low thermal conductivity and ductility of titanium, cold spraying of titanium shows both a high deposition efficiency and relatively high porosity of as-sprayed parts, as well as a heterogeneous microstructure. Moreover, the Account introduces the postprocessing heat treatment and nanoindentation characterization of cold-sprayed materials. A fundamental understanding of microstructure evolution during and after the cold spray process is essential for optimal mechanical properties. Lastly, the author provides a perspective on applying old lessons and taking advantage of new techniques and materials, including powder characterization, hybrid additive manufacturing, machine learning for searching process windows, nanomechanical testing, and emerging alloys (high-entropy alloys, nanocrystalline alloys, and quasicrystals), to advance the research and applications of CSAM.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Cold Spray Additive Manufacturing: Microstructure Evolution and Bonding Features

Zou

2021

Acc. Mater. Res.

Self Cite

View full text Add to dashboard Cite

show abstract

“…This toolkit involves the application of an unsupervised machine-learning algorithm on a moderately sized training dataset of image patches to enable effective anomaly detection and in situ optimization [ 183 ]. Moreover, computer-vision approaches can be used for quality control of parts fabricated using AM [ 184 ], as well as to predict the powder flowability in metal AM [ 185 ]. Different ML algorithms, listed in Table 6 , can be implemented at various stages of AM guided by the adaptability of the predictive techniques.…”

Section: Computational Approachesmentioning

confidence: 99%

Advances and Challenges in Predictive Modeling for Additive Manufacturing of Dissimilar Metals and Complex Alloys

Adak,

Sreeramagiri,

Roy

et al. 2023

Materials

View full text Add to dashboard Cite

We present a scrutiny on the state of the art and applicability of predictive methods for additive manufacturing (AM) of metals, alloys, and compositionally complex metallic materials, to provide insights from the computational models for AM process optimization. Our work emphasizes the importance of manufacturing parameters on the thermal profiles evinced during processing, and the fundamental insights offered by the models used to simulate metal AM mechanisms. We discuss the methods and assumptions necessary for an educated tradeoff between the efficacy and accuracy of the computational approaches that incorporate multi-physics required to mimic the associated fluid flow phenomena as well as the resulting microstructures. Finally, the current challenges in the existing approaches are summarized and future scopes identified.

show abstract

“…Nevertheless, the relationship between powder flow, apparent density, spreadability and the morphological characteristics of individual particles remains difficult to establish quantitatively. Although particles can be imaged using a scanning electron microscope (SEM) and characterised by image analysis, a thorough quantitative analysis requires two key elements: first, a large number of images and second, utilisation of adequate shape and morphology descriptors [6]. In this regard, artificial intelligence (AI) represents disruptive approach to increase the reach and the potential of such image analysis approaches.…”

Section: Introductionmentioning

confidence: 99%

Rheological characterisation of water atomised tool steel powders developed for laser powder bed fusion by supervised and unsupervised machine learning

2023

View full text Add to dashboard Cite

Metal powders developed for additive manufacturing processes need to achieve specific flow characteristics to be considered suitable. However, for the relationship between powder flow and the morphological characteristics of individual particles can be difficult to establish. In this context, artificial intelligence appears to be the perfect tool to clarify the imprecision surrounding this type of interaction. The work summarised in this manuscript first uses a neural network architecture (Mask R-CNN) allowing the segmentation of individual wateratomised tool steel particles in micrographs acquired in scanning electron microscopy. The micrographs of individual particles or their shape descriptors are then processed using and comparing two different strategies, namely linear regression or unsupervised machine learning (ML), to corelate the information collected on individual particles with the rheological properties of powder specimens. The approach developed aims to acquire new knowledge regarding specific particle characteristics that are required to optimise powder flowability for laser powder-bed fusion.

show abstract

A Computer Vision Approach to Evaluate Powder Flowability for Metal Additive Manufacturing

Cited by 11 publications

References 45 publications

Cold Spray Additive Manufacturing: Microstructure Evolution and Bonding Features

Cold Spray Additive Manufacturing: Microstructure Evolution and Bonding Features

Advances and Challenges in Predictive Modeling for Additive Manufacturing of Dissimilar Metals and Complex Alloys

Rheological characterisation of water atomised tool steel powders developed for laser powder bed fusion by supervised and unsupervised machine learning

Contact Info

Product

Resources

About