Progress and Opportunities for Machine Learning in Materials and Processes of Additive Manufacturing.

In recent years, there has been widespread adoption of machine learning (ML) technologies to unravel intricate relationships among diverse parameters in various additive manufacturing (AM) techniques. These ML models excel at recognizing complex patterns from extensive, well-curated datasets, thereby unveiling latent knowledge crucial for informed decision-making during the AM process. The collaborative synergy between ML and AM holds the potential to revolutionize the design and production of AM-printed parts. This review delves into the challenges and opportunities emerging at the intersection of these two dynamic fields. It provides a comprehensive analysis of the publication landscape for ML-related research in the field of AM, explores common ML applications in AM research (such as quality control, process optimization, design optimization, microstructure analysis, and material formulation), and concludes by presenting an outlook that underscores the utilization of advanced ML models, the development of emerging sensors, and ML applications in emerging AM-related fields. Notably, ML has garnered increased attention in AM due to its superior performance across various AM-related applications. It is envisioned that the integration of ML into AM processes will significantly enhance 3D printing capabilities across diverse AM-related research areas.

Automated Service Height Fault Detection Using Computer Vision and Machine Learning for Badminton Matches.

In badminton, accurate service height detection is critical for ensuring fairness. We developed an automated service fault detection system that employed computer vision and machine learning, specifically utilizing the YOLOv5 object detection model. Comprising two cameras and a workstation, our system identifies elements, such as shuttlecocks, rackets, players, and players' shoes. We developed an algorithm that can pinpoint the shuttlecock hitting event to capture its height information. To assess the accuracy of the new system, we benchmarked the results against a high sample-rate motion capture system and conducted a comparative analysis with eight human judges that used a fixed height service tool in a backhand low service situation. Our findings revealed a substantial enhancement in accuracy compared with human judgement; the system outperformed human judges by 3.5 times, achieving a 58% accuracy rate for detecting service heights between 1.150 and 1.155 m, as opposed to a 16% accuracy rate for humans. The system we have developed offers a highly reliable solution, substantially enhancing the consistency and accuracy of service judgement calls in badminton matches and ensuring fairness in the sport. The system's development signifies a meaningful step towards leveraging technology for precision and integrity in sports officiation.

Understanding droplet jetting on varying substrate for biological applications.

In the inkjet printing process, the droplet experience two phases, namely the jetting and the impacting phases. In this review article, we aim to understand the physics of a jetted ink, which begins during the droplet formation process. Following which, we highlight the different impacts during which the droplet lands on varying substrates such as solid, liquid, and less commonly known viscoelastic material. Next, the article states important process-specific considerations in determining the success of inkjet bioprinted constructs. Techniques to reduce cell deformation throughout the inkjet printing process are highlighted. Modifying postimpact events, such as spreading, evaporation, and absorption, improves cell viability of printed droplet. Last, applications that leverage on the advantage of pixelation in inkjet printing technology have been shown for drug screening and cell-material interaction studies. It is noteworthy that inkjet bioprinting technology has been integrated with other processing technologies to improve the structural integrity and biofunctionality of bioprinted construct.

The Design and Development of Instrumented Toys for the Assessment of Infant Cognitive Flexibility.

The first years of an infant's life represent a sensitive period for neurodevelopment where one can see the emergence of nascent forms of executive function (EF), which are required to support complex cognition. Few tests exist for measuring EF during infancy, and the available tests require painstaking manual coding of infant behaviour. In modern clinical and research practice, human coders collect data on EF performance by manually labelling video recordings of infant behaviour during toy or social interaction. Besides being extremely time-consuming, video annotation is known to be rater-dependent and subjective. To address these issues, starting from existing cognitive flexibility research protocols, we developed a set of instrumented toys to serve as a new type of task instrumentation and data collection tool suitable for infant use. A commercially available device comprising a barometer and an inertial measurement unit (IMU) embedded in a 3D-printed lattice structure was used to detect when and how the infant interacts with the toy. The data collected using the instrumented toys provided a rich dataset that described the sequence of toy interaction and individual toy interaction patterns, from which EF-relevant aspects of infant cognition can be inferred. Such a tool could provide an objective, reliable, and scalable method of collecting early developmental data in socially interactive contexts.

Machine Learning for Bioelectronics on Wearable and Implantable Devices: Challenges and Potential.

Bioelectronics presents a promising future in the field of embedded and implantable electronics, providing a range of functional applications, from personal health monitoring to bioactuators. However, due to the intrinsic difficulties present in producing and optimizing bioelectronics, recent research has focused on utilizing machine learning (ML) to reliably mitigate such issues and aid in process development. This review focuses on the recent developments of integrating ML into bioelectronics, aiding in a multitude of areas, such as material development, fabrication process optimization, and system integration. First, discussing how ML has aided in the material development by identifying complex relationships between process input parameters and desired outputs, such as product design. Second, examine the advancements in ML to accurately optimize fabrication precision and stability for various 3D printing technologies. Third, provide an overview of how ML can greatly assist in the analysis of complex, nonlinear relationships in data obtained from bioelectronics. Lastly, a summary of the challenges present with utilizing ML with bioelectronics and any other developments in this field. Such advancements in the field of bioelectronics and ML could hopefully build a strong foundation for this research field, promoting smart optimization together with effective use of ML to further enhance the effectiveness of such applications. Impact statement The article serves to give insight about the use of the machine learning (ML) techniques in the field of bioelectronics, since bioelectronics and ML are two distinct fields. This article allows bioelectronics researcher to get to know the latest advancement in the ML field. On the other hand, the article provides an insight to the ML researchers about how ML techniques can be useful in bioelectronics applications.

Controlling Droplet Impact Velocity and Droplet Volume: Key Factors to Achieving High Cell Viability in Sub-Nanoliter Droplet-based Bioprinting.

Three-dimensional (3D) bioprinting systems serve as advanced manufacturing platform for the precise deposition of cells and biomaterials at pre-defined positions. Among the various bioprinting techniques, the drop-on-demand jetting approach facilitates deposition of pico/nanoliter droplets of cells and materials for study of cell-cell and cell-matrix interactions. Despite advances in the bioprinting systems, there is a poor understanding of how the viability of primary human cells within sub-nanoliter droplets is affected during the printing process. In this work, a thermal inkjet system is utilized to dispense sub-nanoliter cell-laden droplets, and two key factors - droplet impact velocity and droplet volume - are identified to have significant effect on the viability and proliferation of printed cells. An increase in the cell concentration results in slower impact velocity, which leads to higher viability of the printed cells and improves the printing outcome by mitigating droplet splashing. Furthermore, a minimum droplet volume of 20 nL per spot helps to mitigate evaporation-induced cell damage and maintain high viability of the printed cells within a printing duration of 2 min. Hence, controlling the droplet impact velocity and droplet volume in sub-nanoliter bioprinting is critical for viability and proliferation of printed human primary cells.

Tissue engineering and 3D printing of bioartificial pancreas for regenerative medicine in diabetes.

Diabetes is a severe chronic disease worldwide. In various types of diabetes, the pancreatic beta cells fail to secrete sufficient insulin, at some point, to regulate blood glucose levels. Therefore, the replacement of dysfunctional pancreas, islets of Langerhans, or even the insulin-secreting beta cells facilitates physiological regulation of blood glucose levels. However, the current lack of sufficient donor human islets for cell replacement therapy precludes a routine and absolute cure for most of the existing diabetes cases globally. It is envisioned that tissue engineering of a bioartificial pancreas will revolutionize regenerative medicine and the treatment of diabetes. In this review, we discuss the anatomy and physiology of the pancreas, and identify the clinical considerations for engineering a bioartificial pancreas. Subsequently, we dissect the bioengineering problem based on the design of the device, the biomaterial used, and the cells involved. Last but not least, we highlight current tissue engineering challenges and explore potential directions for future work.

Aerosol-Jet-Printed Preferentially Aligned Carbon Nanotube Twin-Lines for Printed Electronics.

The alignment of carbon nanotubes (CNTs) is of great importance for the fabrication of high-speed electronic devices such as a transistor as the electron mobilities can be greatly enhanced with aligned CNT architectures. Here, we report, for the first time, a methodology to obtain preferentially aligned CNT traces on a flexible polyimide substrate utilizing the high-resolution aerosol jet printing technique and evaporation-driven self-assembly process. A self-assembled twin-line of CNT ("coffee-ring" effect) is observed in the deposit patterns, and the field-emission scanning electron microscopy (FESEM) images reveal highly self-ordered CNT in the resulting CNT twin-line. Various aerosol jet parameters have been investigated to obtain printed tracks in the range of 30-80 µm and conductive tracks (single CNT twin-line width) in the range of 600-1500 nm. The smallest CNT twin-line obtained in this experiment is found to be approximately 16 µm using a suitable sheath-to-atomizer flow ratio. Image analysis of FESEM images confirms the formation of aligned CNT traces at the ink periphery. The effect of the line width on the degree of alignment of the CNT is studied and evaluated. The electrical resistance of the CNT trace is adjustable by controlling the number of print passes and print speed.

Sessile droplets containing carbon nanotubes: a study of evaporation dynamics and CNT alignment for printed electronics.

Carbon nanotubes (CNTs) are 1-dimensional (1D) and flexible nanomaterials with high electric conductivity and a high aspect ratio. These features make CNTs highly suitable materials for the fabrication of flexible electronics. CNTs can also be made into dispersions which can be used as the feedstock material for droplet-based 3D printing technologies, e.g., inkjet printing and aerosol jet printing to fabricate printed electronics. These printing techniques involve several physical processes including deposition of ink droplets on flexible polymeric substrates such as polyimides, evaporation of the solvent and formation of thin films of CNTs, all of which have not been thoroughly investigated. Besides, alignment of the CNTs in the resultant thin films dictates their electrical performance. In this work, we examine the effect of substrate temperature and CNT concentration on the evaporation dynamics and also the alignment in the deposition patterns. Evaporation-driven self-assembly of CNTs and their preferential alignment are observed. Image analysis and Raman spectroscopy are utilised to evaluate the degree of alignment of the CNT network. It is found that the contact line dynamics depends greatly on the CNT concentration. Besides, the substrate temperature plays a significant role in determining the order of the CNTs in the drying deposition pattern. Our findings show the possibility of controlling the film morphology and the degree of alignment of CNTs for printed electronics in the printing process.

Wearable Bandage-Based Strain Sensor for Home Healthcare: Combining 3D Aerosol Jet Printing and Laser Sintering.

Flexible and stretchable strain sensors are in great demand for many applications like wearables and home health. This work reports a strain sensor fabricated using aerosol jet printing technology on a commercially available bandage to be used as a low-cost wearable. Laser light is explored to sinter the silver nanoparticle ink on a low-temperature bandage substrate. The laser parameters, their effects on the microstructure of the film, and the resulting sensor performance are systematically investigated. The results showed that the sensor is stretchable and has good sensitivity and stability for 700 cycles of repeated bending.