A5076331500- Ocean Waves and Remote Sensing
- Oceanographic and Atmospheric Processes
- Meteorological Phenomena and Simulations
- Underwater Acoustics Research
- Tropical and Extratropical Cyclones Research
- Non-Destructive Testing Techniques
- Infrastructure Maintenance and Monitoring
- Energy Load and Power Forecasting
- Time Series Analysis and Forecasting
- Acoustic Wave Phenomena Research
- Soil Moisture and Remote Sensing
- Machine Fault Diagnosis Techniques
- Advanced Fiber Optic Sensors
- Vehicle Noise and Vibration Control
- Ship Hydrodynamics and Maneuverability
Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)
2024
Universität Hamburg
2021-2023
Hamburg University of Technology
2021-2023
Measurements of acoustic properties sound absorbing materials in impedance tubes show poor reproducibility, which was demonstrated round robin tests. The tube measurements are standardized but lack precise definitions the actual measurement setup, specimen preparation, and other factors that introduce uncertainty practice. In this paper, machine learning models identify those mostly affect absorption coefficient from a large data set more than 3000 spectra measured one tube. specimens...
Abstract This paper explores the applicability of machine learning techniques for generation tailored wave sequences. For this purpose, a fully convolutional neural network was implemented relating target sequence at location in time domain to respective board. The synthetic training and validation data were acquired by applying high-order spectral (HOS) method. HOS method is very accurate modeling non-linear propagation its numerical efficiency allows large sets. featured groups short...
Abstract This paper explores the applicability of machine learning techniques for generation tailored wave sequences. For this purpose, a fully convolutional neural network was implemented relating target sequence at location in time domain to respective control signal board. The database generated by means extensive tank tests. experimental campaign focused on very steep groups including breaking which cannot be covered simplified methods. performed small with an automated approach...
Accurate short-term prediction of phase-resolved water wave conditions is crucial for decision-making in ocean engineering. However, the initialization remote-sensing-based models first requires a reconstruction surfaces from sparse measurements like radar. Existing methods either rely on computationally intensive optimization procedures or simplistic modeling assumptions that compromise real-time capability accuracy entire process. We therefore address these issues by proposing novel...
Deterministic phase-resolved prediction of the evolution surface gravity waves in water is challenging due to their complex spatio-temporal dynamics. Physics-based methods varying complexity are available, but conflicting objectives numerical efficiency and accuracy impede real-time wave prediction. Data-driven may be able overcome this challenge by using training data generated methods. This work explores potential a machine learning (ML) approach based on fully convolutional...
Accurate short-term predictions of phase-resolved water wave conditions are crucial for decision-making in ocean engineering. However, the initialization remote-sensing-based prediction models first requires a reconstruction surfaces from sparse measurements like radar. Existing methods either rely on computationally intensive optimization procedures or simplistic modelling assumptions that compromise real-time capability accuracy subsequent process. We therefore address these issues by...
Machine learning (ML) techniques allow for finding hidden patterns and signatures in data. Currently, these methods are gaining increased interest engineering general vibroacoustics particular. Although ML successfully applied, it is hardly understood how black box-type make their decisions. Explainable machine aims at overcoming this issue by deepening the understanding of decision-making process through perturbation-based model diagnosis. This paper introduces reviews recent explainability...