Unlocking the Full Potential of Additive Manufacturing: A Closer Look at the NSF Grant for Developing an Efficient Predictive Model

Researcher Parisa Khodabakhshi, an assistant professor of Mechanical Engineering and Mechanics at Lehigh University's P.C. Rossin College of Engineering and Applied Science, has received a $350,000 grant from the National Science Foundation to develop a computationally efficient model that accurately predicts how additive manufacturing process parameters influence the solidification microstructure and determine the properties of the final part. This project focuses on optimizing the manufacturing of additively manufactured parts, which are crucial in industries where confidence in manufacturing is paramount, such as aerospace, automotive, and healthcare. Khodabakhshi's approach uses a scientific machine learning framework that blends data-driven machine learning algorithms with physical laws to develop a physics-based, data-driven reduced-order model for predicting microstructure evolution in binary alloy solidification.

Key Takeaways:

• The NSF grant focuses on developing a computationally efficient model for predicting microstructure evolution in binary alloy solidification, which will help optimize the manufacturing of additively manufactured parts.
• The project will utilize a scientific machine learning framework that embeds physics into the problem, making it a significant departure from conventional machine learning methods.
• The University's Assistant Professor of Mechanical Engineering and Mechanics, Parisa Khodabakhshi, will lead the project, which aims to develop a reduced-order model that can accurately predict the solidification microstructure and the resulting properties of the final part.
• The project will benefit industries such as aerospace, automotive, and healthcare, where confidence in manufacturing is paramount, by providing a more efficient and accurate method for manufacturing additively manufactured parts.
• The team's approach will blend data-driven machine learning algorithms with physical laws to develop a predictive model that can be used to optimize the manufacturing process.

Statistics:

• The National Science Foundation grant awarded to Parisa Khodabakhshi is valued at $350,000.
• The three-year project aims to develop a computationally efficient model for predicting microstructure evolution in binary alloy solidification.
• The project will utilize a scientific machine learning framework that blends data-driven machine learning algorithms with physical laws.
• The model will be developed to optimize the manufacturing of additively manufactured parts, which are crucial in industries such as aerospace, automotive, and healthcare.

Sources:

• Parisa Khodabakhshi, an assistant professor of Mechanical Engineering and Mechanics at Lehigh University's P.C. Rossin College of Engineering and Applied Science, as stated in the VerticalNews article.
• National Science Foundation (NSF), the grant provider for Parisa Khodabakhshi's project, as stated in the VerticalNews article.
• VerticalNews, the publication source for the article, as stated in the copyright information.