| dc.description.abstract | Hydrogen could replace fossil fuels and mitigate the problem of global warming in the forthcoming years. However, pieces of equipment exposed to a hydrogen environment must cope with the damaging effect of this substance on metallic materials. Inspection procedures and maintenance activities are required to preserve the integrity of these technologies. In this light, risk-based approaches (RBI) aim to minimize the probability of systems failure prioritizing inspection and maintenance of high-risk components. The risk level of each piece of equipment is based on the damage factor and depends on the degrading mechanisms likely to occur. This methodology has never been adopted for equipment operating in a pure hydrogen environment. There are different recommended practices (i.e., API 580, API 581, DNVGL-RP-G101) and the standards (i.e., ASME PCC-3 and EN 16991) regarding RBI approach. However, the references to hydrogen embrittlement seem to be missing. In addition, a defined methodology to estimate the Damage Factor (DF) caused by pressurized hydrogen at ambient temperature is lacking. The aim of this work is to apply Machine Learning approach to predict the material embrittlement in presence of hydrogen as the first step for the estimation of the DF of equipment for hydrogen transportation and storage. The database for Machine Learning is determined by gathering data from the strain tests results carried out on metallic materials and reported in different resources. Then, the database is used to train three different machine learning models, whose performance has been evaluated and discussed. | |