Distinguished Lecture in Materials (Virtual) | Applications of and advances in Boron Nitride Nanotubes and Additively Manufactured Ceramic Matrix Composites

Featuring Ryan Holtschneider, Lead Data Scientist at Epic Advanced Materials
Hosted by: Aaron Stebner (ME)

Microsoft Teams meeting Link: Click here to join the meeting
Meeting ID: 226 087 057 817 |Passcode: i3ijAQ
Call in: 1- 470-705-2566|Phone Conference ID: 908 820 928#

Epic Advanced Materials is an AI-driven, interdisciplinary nanomaterials company focused on bringing nanomaterials and data driven material science to the mainstream. Epic's first case study on the application of data driven methods to the material science lifecycle is using AI to supercharge and automate the optimization and quality control of the EPIC synthesis process, the world's highest yield and highest quality BNNT synthesis process (boron nitride nanotube).

Boron Nitride Nanotubes have a number of amazing qualities such as high mechanical stiffness and specific strength, low density (lightweight), excellent chemical stability and low reactivity, extremely high oxidation temperature (~950˚C), easy disbursement in liquid metals and polymers, High thermal conductivity( up to 1000 W/m*k), neutron absorbing and radiation shielding, electrically insulating, piezoelectric, high transparency, hydrophobic, high hydrogen storage capacity and biocompatibility. This makes them an excellent material to improve metallic or ceramic composite parts for defense, aerospace, and energy applications which can be additively manufactured, aid in drug delivery, reinforce and improve the thermal properties of polymers, use in extreme environment sensors, use in desalination membranes, use in a radiation shielding coating and much more.

To automatically analyze and quantify our material quality we have built out a deep learning pipeline to train models to analyze material characterization outputs in the form of images such as TEM (transmission electron microscopy). To optimize the quality of our materials we use the output of our analysis models as feedback for another ML model that recommends near process parameters to try in experiments to improve our materials or to obtain certain qualities.

Nanoarmor is a materials development company focused on creating additively manufactured high temperature ceramic matrix composites using polymer derived ceramics which can also be reinforced with BNNTs. Additively manufacturing of ceramics significantly improves their processability and facilitates custom shapes at low costs and short production times and additive manufacturing synthesis of carbides maintains strength to weight ratio, char, and compressive strength. Ultra-high temperature ceramics such as ZrC, B4C, Si3N and TiB2 have high melting temperatures of 2,000-3,500C, high thermal conductivity and superior ablation resistance. By reinforcing UHTCs with metals, fibers or nanomaterials resulting CMCs overcome embrittlement and thermal shock limitations of conventional ceramics. Nanoarmor’s UHTCMCs have low shrinkage post sintering and can be sintered at low temperatures (<1450 C). Nanoarmor’s UHTCs can be used for leading edges for hypersonic flight, turbines for gas turbines, nuclear reactors, spacecraft components, high temperature heat exchangers, heat sinks in electronic systems, and more.

Biography of Presenter
Ryan Holtschneider is the Lead Data Scientist at Epic Advanced Materials, an interdisciplinary nanomaterials company using data driven methods to accelerate nanomaterial optimization and application development. Ryan Holtschneider has a master’s degree in applied mathematics, a bachelor’s degree in physics and professional experience in engineering and data science. He has built machine learning and computer vision tools to optimize testing, simulation and hardware to model correlation for advanced manufacturing processes at Northrop Grumman. Ryan joined Epic from Parsons where he researched applications of computer vision and machine learning to radar signal processing. Ryan is currently developing machine learning based solutions to optimize nanomaterials, evaluate their quality and integrate them with other material systems.