Physics-added neural networks: An image-based deep learning for material printing system

Kwon, Soon-Wook; Kim, Jun Seong; Lee, Hee Min; Lee, Joon Sang

doi:10.1016/j.addma.2023.103668

Cited by 5 publications

(3 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This research provides a promising approach for designing optimized control algorithms and implementing closed-loop control systems, thereby contributing to improved jet stability and the expedited application of electrohydrodynamic direct-writing (EDW) technology, as shown in Figure 6 a. Soon Wook Kwon [ 41 ] improved the predictive accuracy of the material printing process by introducing physical constraints into neural networks, as shown in Figure 6 b. Huang et al [ 50 ] studied the evolution behavior and process dynamics of ink droplets in the inkjet printing process using unsupervised learning methods. By using video data instead of images to study droplet evolution during inkjet printing, the experimental results demonstrated the high accuracy of the proposed method in predicting droplet evolution and understanding the dynamics of the inkjet printing process, as shown in Figure 6 c. Segura [ 67 ] studied the evolution of droplet behavior with different materials and process parameters through tensor time-series analysis of experimental data.…”

Section: Control Methods For Droplet Printingmentioning

confidence: 99%

“…( b ) Snapshots of temperature contour of inkjet process simulation result. Reproduced with permission from [ 41 ], published by Elsevier, 2023. ( c ) Preceding predictive results of frame sequences from the video of the droplet formation process.…”

Section: Figurementioning

confidence: 99%

Section: Printing Quality Modelingmentioning

confidence: 99%

See 2 more Smart Citations

Review of Droplet Printing Technologies for Flexible Electronic Devices: Materials, Control, and Applications

Jiang,

Chen,

Mei

et al. 2024

Micromachines

View full text Add to dashboard Cite

Flexible devices have extensive applications in areas including wearable sensors, healthcare, smart packaging, energy, automotive and aerospace sectors, and other related fields. Droplet printing technology can be utilized to print flexible electronic components with micro/nanostructures on various scales, exhibiting good compatibility and wide material applicability for device production. This paper provides a comprehensive review of the current research status of droplet printing technologies and their applications across various domains, aiming to offer a valuable reference for researchers in related areas.

show abstract

Section: Control Methods For Droplet Printingmentioning

confidence: 99%

Section: Figurementioning

confidence: 99%

Section: Printing Quality Modelingmentioning

confidence: 99%

See 1 more Smart Citation

Review of Droplet Printing Technologies for Flexible Electronic Devices: Materials, Control, and Applications

Jiang,

Chen,

Mei

et al. 2024

Micromachines

View full text Add to dashboard Cite

show abstract

Image-based identification of optical quality and functional properties in inkjet-printed electronics using machine learning

Polomoshnov,

Reichert,

Rettenberger

et al. 2024

J Intell Manuf

View full text Add to dashboard Cite

We propose a novel image-analysis based machine-learning approach to the fully-automated identification of the optical quality, of functional properties, and of manufacturing parameters in the field of 2D inkjet-printed test structures of conductive traces. To this end, a customizable modular concept to simultaneously identify or predict dissimilar properties of printed functional structures based on images is described and examined. An application domain of the concept in the printing production process is outlined. To examine performance, we develop a dataset of over 5000 test structures containing images and physical characteristics, which are manufactured using commercially available materials. Functional test structures are fabricated via a single-nozzle vector-based inkjet-printing system and thermally sintered. Physical characterization of electrical conductance, image capturing, and evaluation of the optical quality of the test structures is done by an automatic in-house built measurement station. Conceptionally, the design of a convolutional neural network is described to identify the optical quality and physical characteristics based only on acquired images. A mathematical apparatus that allows assessment of the identification accuracy is developed and described. The impact of printing resolution, of emerging defects in the geometry of printed structures, and of image quality and color space on the identification accuracy is analyzed. Quality groups related to the printing resolution that affect identification accuracy are determined. Supplementarily, we introduce not yet reported classification of processes related to the fabrication of printed functional structures, adopted from the process analytical technology.

show abstract

Machine learning in polymer additive manufacturing: a review

Nikooharf,

Shirinbayan,

Arabkoohi

et al. 2024

Int J Mater Form

View full text Add to dashboard Cite

Additive manufacturing (AM) has emerged as a commonly utilized technique in the manufacturing process of a wide range of materials. Recent advances in AM technology provide precise control over processing parameters, enabling the creation of complex geometries and enhancing the quality of the final product. Moreover, Machine Learning (ML) has become widely used to make systems work better by using materials and processes more intelligently and controlling their resulting properties. In industrial settings, implementing ML not only reduces the lead time of manufacturing processes but also enhances the quality and properties of produced parts through optimization of process parameters. Also, ML techniques have facilitated the advancement of cyber manufacturing in AM systems, thereby revolutionizing Industry 4.0. The current review explores the application of ML techniques across different aspects of AM including material and technology selection, optimization and control of process parameters, defect detection, and evaluation of properties results in the printed objects, as well as integration with Industry 4.0 paradigms. The progressive phases of utilizing ML in the context of AM, including data gathering, data preparation, feature engineering, model selection, training, and validation, have been discussed. Finally, certain challenges associated with the use of ML in the AM and some of the best-practice solutions have been presented.

show abstract

Physics-added neural networks: An image-based deep learning for material printing system

Cited by 5 publications

References 37 publications

Review of Droplet Printing Technologies for Flexible Electronic Devices: Materials, Control, and Applications

Review of Droplet Printing Technologies for Flexible Electronic Devices: Materials, Control, and Applications

Image-based identification of optical quality and functional properties in inkjet-printed electronics using machine learning

Machine learning in polymer additive manufacturing: a review

Contact Info

Product

Resources

About