This study focuses on the development of a machine learning (ML) model to elaborate on predictions of structural damage in submerged structures due to ocean states and subsequently compares it to a real-life case of a 6-month experiment with a benthic lander bearing a multitude of sensors. The ML model uses wave parameters such as height, period and direction as input layers, which describe the ocean conditions, and strains in selected points of the lander structure as output layers. To streamline the dataset generation, a simplified approach was adopted, integrating analytical formulations based on Morison equations and numerical simulations through the Finite Element Method (FEM) of the designed lander. Subsequent validation involved Fluid–Structure Interaction (FSI) simulations, using a 2D Computational Fluid Dynamics (CFD)-based numerical wave tank of the entire ocean depth to access velocity profiles, and a restricted 3D CFD model incorporating the lander structure. A case study was conducted to empirically validate the simulated ML model, with the design and deployment of a benthic lander at 30 m depth. The lander was monitored using electrical and optical strain gauges. The strains measured during the testing period will provide empirical validation and may be used for extensive training of a more reliable model.

This study explores the fatigue properties of EN AW-6082-T6 aluminum alloy in the gigacycle range (106–109 cycles), using ultrasonic resonance fatigue testing at 20 kHz in a push–pull mode with a symmetric load cycle (R = −1). A custom-built ultrasonic fatigue machine, developed at TU-Varna, comprising a generator, ultrasonic train (including a high-power transducer, booster, custom-made sonotrode, and specimen), monitoring, data logging systems, and an air-cooling capability, was used for the experiments conducted. A Bezier curve sonotrode, with an amplification ratio of 1:6, was designed and produced for the test. Hourglass-shaped specimens were designed on the base of the dynamic Young’s modulus E = 71.3 GPa, determined through the impulse resonance method (ASTM E1876-01), and validated with FEM analysis for resonance length and stress amplitude. The fatigue testing revealed a fatigue strength reduction of approximately 60 MPa between 106 and 109 cycles. The percentile of failure curves based on a Cactillo–Canteli model fits well with the experimental data and gives a fatigue limit at 109 cycles σl = 104 MPa and “endurance strength” σw = 84 MPa. Surface crack initiation was consistently observed with predominately cleavage transgranular fractures in the fatigue zone. The present research highlights the utility of ultrasonic testing for examining fatigue behavior in the gigacycle regime.

The aim of this paper is the study of the storage of hydrogen in the liquid state, LH2, with a focus on the thermal gains for cylindrical and spherical tank geometries. A given tank volume was assumed; three geometries for such a tank were taken, similar to the most common tanks for LH2 storage: cylindrical (vertical and horizontal) and spherical. An integrated refrigeration system was considered for LH2 stored at a temperature around 22 K and at a pressure around 3 bar. Then, the energy expenditure by the refrigeration system to maintain LH2 in the liquid state was determined and compared with the value of the energy contained in the LH2, in order to compare such a storage method to other hydrogen storage methods, namely compressed hydrogen, in the gaseous state. The most important conclusion was that spherical tanks had lower thermal gains than tanks with other geometries.