We use cookies to enhance your experience. By continuing to browse this website, you agree to our use of cookies. More information.
An article from Polymer Testing magazine studies and compares the quality of several polymer composite materials manufactured using 3D printing technology, such as morphology and surface texture, mechanical properties, and thermal properties.
Research: Nano-particle-infused plastic products made by 3D printers guided by machine learning. Image source: Pixel B/Shutterstock.com
The manufactured polymer components require various qualities according to their purpose, some of which can be provided by using polymer filaments composed of different amounts of multiple materials.
A branch of additive manufacturing (AM), called 3D printing, is a cutting-edge technology that mixes materials to create products based on 3D model data.
Therefore, the waste generated by this process is relatively small. 3D printing technology is currently used in various applications, including the large-scale manufacturing of various items, and the amount of use will only increase.
This technology can now be used to manufacture objects with complex structures, lightweight materials, and customizable designs. In addition, 3D printing has the advantages of efficiency, sustainability, versatility and risk minimization.
One of the most important aspects of this technology involves choosing the right parameters because they have a great influence on the product, such as its shape, size, cooling rate, and thermal gradient. These qualities then affect the evolution of the microstructure, its characteristics and defects.
Machine learning can be used to establish the relationship between the process conditions, microstructure, component shape, composition, defects, and mechanical quality of a specific printed product. These connections may help reduce the number of trials required to produce high-quality output.
High-density polyethylene (HDPE) and polylactic acid (PLA) are the two most commonly used polymers in AM. PLA is used as the main material for many applications because it is sustainable, economical, biodegradable and has excellent properties.
Plastic recycling is a major issue facing the world; therefore, it would be very beneficial to incorporate recyclable plastic into the 3D printing process.
As the printing material is continuously fed into the liquefier, the temperature is maintained at a consistent level during fused filament manufacturing (FFF) deposition (a type of 3D printing).
Therefore, the molten polymer is ejected through the nozzle by the pressure reduction. Surface morphology, yield, geometric accuracy, mechanical properties, and cost are all affected by FFF variables.
Tensile, compressive impact or bending strength and printing direction are considered to be the most important process variables affecting FFF samples. In this study, the FFF method was used to prepare specimens; six different filaments were used to construct the sample layer.
a: ML prediction parameter optimization model of 3D printers in samples 1 and 2, b: ML prediction parameter optimization model of 3D printers in sample 3, c: ML prediction parameter optimization models of 3D printers in samples 4 and 5. Image source: Hossain, MI, etc.
3D printing technology can combine the excellent quality of printing projects that cannot be achieved by traditional production methods. Due to the unique production method of 3D printing, the quality of manufactured parts is greatly affected by design and process variables.
Machine learning (ML) has been used in many ways in additive manufacturing to enhance the entire development and manufacturing process. A data-based advanced design method for FFF and a framework for optimizing FFF component design have been developed.
The researchers estimated the nozzle temperature with the help of machine learning suggestions. ML technology is also used to calculate the print bed temperature and print speed; the same size is set for all samples.
The results show that the fluidity of the material directly affects the quality of the 3D print output. Only the proper nozzle temperature can ensure the required fluidity of the material.
In this work, PLA, HDPE and recycled filament materials are mixed with TiO2 nanoparticles and used to manufacture low-cost 3D printed objects by commercial melted filament manufacturing 3D printers and filament extruders.
The characteristic filaments are novel and use graphene to generate a waterproof coating, which can reduce any changes in the basic mechanical properties of the finished product. The outside of the 3D printed component can also be processed.
The main goal of this work is to find a way to achieve a more reliable and richer mechanical and physical quality in 3D printed items compared to traditional 3D printed items that are usually produced. The results and applications of this research can pave the way for the development of numerous industry-related programs.
Keep reading: Which nanoparticles are best for additive manufacturing and 3D printing applications?
Hossain, MI, Chowdhury, MA, Zahid, MS, Sakib-Uz-Zaman, C., Rahaman, ML, & Kowser, MA (2022) Development and analysis of nanoparticle-infused plastic products made by 3D printers guided by machine learning . Polymer testing, 106. Available from the following URL: https://www.sciencedirect.com/science/article/pii/S014294182100372X?via%3Dihub
Disclaimer: The views expressed here are those expressed by the author in a personal capacity, and do not necessarily represent the views of the owner and operator of this website, AZoM.com Limited T/A AZoNetwork. This disclaimer forms part of the terms and conditions of use of this website.
Hot sweat, Shahir. (December 5, 2021). Machine learning optimizes 3D printed products that recycle plastic. AZoNano. Retrieved from https://www.azonano.com/news.aspx?newsID=38306 on December 6, 2021.
Hot sweat, Shahir. “Machine learning optimizes 3D printed products from recycled plastics.” AZoNano. December 6, 2021. <https://www.azonano.com/news.aspx?newsID=38306>.
Hot sweat, Shahir. “Machine learning optimizes 3D printed products from recycled plastics.” AZoNano. https://www.azonano.com/news.aspx?newsID=38306. (Accessed on December 6, 2021).
Hot sweat, Shahir. 2021. Machine learning optimizes 3D printed products from recycled plastics. AZoNano, viewed on December 6, 2021, https://www.azonano.com/news.aspx?newsID=38306.
AZoNano talked to Dr. Jinian Yang about his participation in research on the benefits of flower-like nanoparticles on the performance of epoxy resins.
We discussed with Dr. John Miao that this research has changed our understanding of amorphous materials and what it means for the physical world around us.
We discussed NANO-LLPO with Dr. Dominik Rejman, a wound dressing based on nanomaterials that promotes healing and prevents infection.
The P-17 stylus profiler surface measurement system provides excellent measurement repeatability for consistent measurement of 2D and 3D topography.
The Profilm3D series provides affordable optical surface profilers that can generate high-quality surface profiles and true color images with unlimited depth of field.
Raith’s EBPG Plus is the ultimate product of high-resolution electron beam lithography. EBPG Plus is fast, reliable and high-throughput, ideal for all your lithography needs.
Post time: Dec-07-2021
