Techno – Economic Analysis Constrained Machine Learning Predictions of Materials for High Pressure Hydrogen Compression

Published

April 30, 2018

Author(s)

Jason R. Hattrick-Simpers, Kamal Choudhary, Claudio Corgnale

Abstract

Here we present the results of using techno-economic analysis as constraints for machine learning guided studies of new metal hydride materials. Using existing databases for hydrogen storage alloys a regression model to predict the enthalpy of hydrogenation was generated with a mean absolute error of 8.56 kJ/mol and a mean relative error of 28%. Model predictions for new hydride materials were constrained by techno-economic analysis and used to identify 6110 potential alloys criteria required for hydrogen compressors. Additional constraints such as alloy cost and composition were used to reduce the number of possible alloys for experimental verification to less than 400. Finally, expert heuristics and a novel machine learning approach to approximating alloy stability was employed to select the Fe-Mn-Ti-X alloy system for future experimental studies.

Citation

Molecular Systems Design and Engineering

Pub Type

Journals

Download Paper

Local Download

Keywords

hydrogen storage, machine learning

Citation

Hattrick-Simpers, J. , Choudhary, K. and Corgnale, C. (2018), Techno – Economic Analysis Constrained Machine Learning Predictions of Materials for High Pressure Hydrogen Compression, Molecular Systems Design and Engineering, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=924879 (Accessed October 10, 2025)