Combined Experimental and Modeling Study of Microwave-Assisted Methane Dehydroaromatization Process
ACS Fall Meeting 2022, Chicago, IL, August 21-25, 2022
Bai, Xinwei↗
Engineering topics
Musho, Terence
Publications and source records attributed to Musho, Terence.
Cooperative Research and Development Agreement between National Energy Technology Laboratory and West Virginia University Research Corporation (Abstract)
The National Energy Technology Laboratory (NETL) and West Virginia University Research Corporation (Participant) will collaborate on the testing of a 3D printed sparger in a temperature and pressure chamber, for the purpose of supporting the “American-Made Geothermal Prize” competition, designed to catalyze manufacturing innovation in the American geothermal industry by harnessing the rapid advances additive manufacturing can provide in improving design, fabrication, and functionality, which is accomplished through a series of prize competitions and the development of a diverse and powerful support network that leverages national laboratories, energy incubators, and other resources from across the United States. The intent is to connect competitor teams with national laboratories that can help accelerate the development of innovative solutions and products. Teams who have won the Set!, Go!, Make! Contests are eligible to utilize vouchers at national laboratories to advance their ideas.
15 GEOTHERMAL ENERGY↗
Autonomous design of new chemical reactions using a variational autoencoder
Artificial intelligence based chemistry models are a promising method of exploring chemical reaction design spaces. However, training datasets based on experimental synthesis are typically reported only for the optimal synthesis reactions. This leads to an inherited bias in the model predictions. Therefore, robust datasets that span the entirety of the solution space are necessary to remove inherited bias and permit complete training of the space. In this study, an artificial intelligence model based on a Variational AutoEncoder (VAE) has been developed and investigated to synthetically generate continuous datasets. The approach involves sampling the latent space to generate new chemical reactions. This developed technique is demonstrated by generating over 7,000,000 new reactions from a training dataset containing only 7,000 reactions. The generated reactions include molecular species that are larger and more diverse than the training set.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗