Reviews on Machine Learning Approaches for Process Optimization in Noncontact Direct Ink Writing

Abstract

Recently, machine learning has gained considerable attention in noncontact direct ink writing because of its novel process modeling and optimization techniques. Unlike conventional fabrication approaches, noncontact direct ink writing is an emerging 3D printing technology for directly fabricating low-cost and customized device applications. Despite possessing many advantages, the achieved electrical performance of produced microelectronics is still limited by the printing quality of the noncontact ink writing process. Therefore, there has been increasing interest in the machine learning for process optimization in the noncontact direct ink writing. Compared with traditional approaches, despite machine learning-based strategies having great potential for efficient process optimization, they are still limited to optimize a specific aspect of the printing process in the noncontact direct ink writing. Therefore, a systematic process optimization approach that integrates the advantages of state-of-the-art machine learning techniques is in demand to fully optimize the overall printing quality. In this paper, we systematically discuss the printing principles, key influencing factors, and main limitations of the noncontact direct ink writing technologies based on inkjet printing (IJP) and aerosol jet printing (AJP). The requirements for process optimization of the noncontact direct ink writing are classified into four main aspects. Then, traditional methods and the state-of-the-art machine learning-based strategies adopted in IJP and AJP for process optimization are reviewed and compared with pros and cons. Finally, to further develop a systematic machine learning approach for the process optimization, we highlight the major limitations, challenges, and future directions of the current machine learning applications.

Study on Chemical Graft Structure Modification and Mechanical Properties of Photocured Polyimide

“…The curing depth of light curing is mainly related to the photosensitivity of resin. At present, most researchers use the Jacobs equation to describe the curing depth: 3 , 6 , 11 , 14 , 46 …”

“…The preponderance of arbitrary shape control makes 3D printing widely used in various applications. Material jetting, material extrusion, vat photopolymerization, and powder bed fusion are the unique methods of AM, of which developments so far have emerged in stereolithography (SL), digital light processing (DLP), 1 two-photon lithography (TPP), 2 direct ink writing (DIW), 3 continuous liquid interface printing (CLIP), 4 fused wire manufacturing (FFF), 5 inkjet printing, and polymer powder layer fusion technologies. 6 , 7 These technologies can be seen in particular in some comments, which will not be described in detail here.…”

“…The preponderance of arbitrary shape control makes 3D printing widely used in various applications. Material jetting, material extrusion, vat photopolymerization, and powder bed fusion are the unique methods of AM, of which developments so far have emerged in stereolithography (SL), digital light processing (DLP), two-photon lithography (TPP), direct ink writing (DIW), continuous liquid interface printing (CLIP), fused wire manufacturing (FFF), inkjet printing, and polymer powder layer fusion technologies. , These technologies can be seen in particular in some comments, which will not be described in detail here. As a method of additive manufacturing, photocuring has the advantages of being able to be molded at room temperature and having excellent geometric versatility on the strength of maintaining rapid prototyping in additive manufacturing, which also makes it have a wide range of application potential in automotive, biomedical, aerospace, and other fields .…”

Shape memory elastomers: A review of synthesis, design, advanced manufacturing, and emerging applications

“…191 In this regard, ML is suitable for advanced modeling and inverse design due to offering several advantages, for example, automated identification of patterns and trends, continuous development, and handling multi-dimensional and diverse data. 192,193 Currently, ML is utilized in many industries, such as financial services, health care, government, oil and gas, transportation, and material science.…”

“…The inputs can be used to predict the desired outputs through a hypothesized mathematical model that is learned by processing the available data and maximizing a problem‐dependent performance criterion 191 . In this regard, ML is suitable for advanced modeling and inverse design due to offering several advantages, for example, automated identification of patterns and trends, continuous development, and handling multi‐dimensional and diverse data 192,193 . Currently, ML is utilized in many industries, such as financial services, health care, government, oil and gas, transportation, and material science.…”