For the ongoing energy transition, high pressure hydrogen is a highly relevant energy carrier. In order to provide a practical and robust hydrogen infrastructure, a vast variety of components needs to be developed to ensure a save hydrogen storage and transport. Dimensioning of these parts with respect to their structural durability requires new dimensioning schemes and guidelines to be developed which account for material specific damage mechanisms under hydrogen environment. An ideal basis represents the well-established FKM guideline issued by the German Research Association Mechanical Engineering (FKM). The guideline is applicable for a wide range of mechanical engineering components and is particularly popular for small and medium enterprises (SME). Within our research project, the dimensioning scheme based on the FKM guideline is applied for exemplary structural parts in hydrogen environment. Based on literature data and experiments conducted within the project, a dimensioning scheme is developed specifically for a sample component. In our presentation, we analyze existing dimensioning codes and material data under hydrogen environment and discuss how the FKM approach needs to be adapted to consider the hydrogen effects on material and component strength.

In order to provide a robust hydrogen infrastructure for the ongoing energy transition, many components need to be developed to ensure a save hydrogen storage and transport. Strength assessment of these parts requires new guidelines to be developed. An ideal basis represents the well-established FKM guideline issued by the German Research Association Mechanical Engineering (FKM). In our work, the FKM guideline is applied for demonstrator parts in hydrogen environment. We analyze the applicability based on the demonstrator use case and discuss how the FKM approach needs to be adapted in the future to consider hydrogen effects on a general basis.

Machine learning approaches gain more and more importance for fatigue assessment of materials and industrial parts. In this work an extensive database of more than 22.000 single fatigue test and 1100 fatigue test series (SN-curves) of different steels are used to build a generalized approach for the fatigue prediction based on machine learning (ML). For this, different strategies are used: First, the fatigue assessment based on SN-curves, where the SN-curve parameters (slope, characteristic fatigue strength, …) were determined by ML and used for the fatigue life prediction; and second, the fatigue life prediction based on specimens, where the characteristics of single specimen of the fatigue tests series (stress amplitude, number of load cycles, …) are used. Different ML approaches (artificial neural networks, random forest, …) approaches are used. A higher accuracy of the fatigue life prediction by ML is shown for the SN-curve approach. Also, a recommendation is given by the results of this work how data should be arranged, and which characteristics (or parameter) should be used for the fatigue assessment of steels by ML.