Hydrogen is one of the future green energy sources that could resolve issues related to fossil fuels. The widespread use of hydrogen can be enabled by composite-overwrapped pressure vessels for storage. It offers advantages due to its low weight and improved mechanical performance. However, the safe storage of hydrogen requires continuous monitoring. Combining ultrasonic guided waves with interpretable machine learning provides a powerful tool for structural health monitoring. In this study, we developed a feature extraction approach based on a similarity method that enables interpretability in the proposed machine learning model for damage detection and localization in pressure vessels. Furthermore, a systematic optimization was performed to explore and tune the model’s parameters. This resulting model provides accurate damage localization and is capable of detecting and localizing damage on hydrogen pressure vessels with an average localization error of 2 cm and a classification accuracy of 96.5% when using quantized classification. In contrast, binarized classification yields a higher accuracy of 99.5%, but with a larger localization error of 6 cm.

Composite overwrapped pressure vessels are increasingly used for hydrogen storage because of their lightweight construction. Ensuring their structural integrity therefore becomes an important requirement for safe operation. Ultrasonic guided waves are well suited for this task because they are highly sensitive to structural changes in thin-walled pressure vessels. In this work, we developed a machine learning framework based on interpretable Best Daubechies Wavelet features and k-Nearest Neighbors novelty detection. The framework identifies a persistent transition in the UGW response during overpressurization that is indicative of a permanent structural change and occurs prior to burst failure. It was validated using measurements acquired from a real-world pressure vessel. For the a priori selected sensor pair 11–12, located in the highly stressed cylindrical section, the method achieved a balanced accuracy of 98.28% and a true negative rate of 100%. In addition, the proposed methodology identified the pressure level at which the persistent structural transition first became detectable and showed that this transition remained detectable after the vessel had returned to its normal operating pressure.

The paper discusses the development of a non-resonant shear-wave piezoelectric transducer array ring for the efficient generation of the fundamental torsional mode T(0,1) mode in pipes using dry coupling. In this, 3D finite element (FE) modelling is employed to design and optimise a tungsten-epoxy composite backing mass that suppresses ringing and maximises shear wave transmission. A novel 3D-spatial cosine transform-based technique is employed to simulate an inhomogeneous composite without discretely modelling individual tungsten particles. From the model, the optimum density of the composite backing mass is found to be 12650 kg/m3, which virtually eliminates ringing while preserving the bandwidth and centerfrequency. Sixteen optimised transducers are fabricated in-house and qualified by the laser Doppler vibrometer (LDV) technique. Q-factors of the transducer from the FE model and the LDV technique are in good agreement with the values of ~2.8 and 3.0, respectively. Further, contact mechanics calculation of contact width and contact area, formed by the spring-loaded transducer on a carbon steel pipe of an outer diameter of 88.9 mm, yields 0.08 mm and 1.3 mm2, respectively. The transducers are then integrated into a 3D printed, detachable, springloaded ring holder and dry-coupled to the pipe. The pipe experiments confirm a fairly clean T(0,1) mode excitation with negligible flexural contamination, a group velocity of 3200 m/s, attenuation of ~0.1 dB/m, and propagation over 100 m. Besides, it also detects a circumferential defect of depth 0.32 mm (10% wall thickness) and an axial defect of 1.6 mm depth (50% wall thickness), with good sensitivity.