arXiv subjects

Henning Schwarz

Publications and source records attributed to Henning Schwarz.

4 recordsLinked to original sources

arXiv2026

Conditional Neural Field based Reduced Order Model for Dynamic Ditching Load Prediction

Grid-based neural networks such as convolutional autoencoders are widely used in dimension reduction-based surrogate models for computational fluid dynamics. In recent years, the use of coordinate-based approaches like conditional neural fields has emerged. Their independence of the spatial discretization is a beneficial feature for various applications in computational fluid dynamics. This paper discusses the spatio-temporal prediction of aircraft ditching loads using a conditional neural field approach. The model is evaluated using two datasets for the dynamic loads of the fuselage of a DLR-D150 aircraft, one of which relates to a single fixed spatial discretization and the other that includes data from different discretizations. When paired with a long short-term memory (LSTM) network in the latent space, the neural field-based model achieves a spatio-temporal prediction accuracy for the first data set that is close to that of grid-dependent convolutional autoencoder-based models, and with significantly less parameters. Results for the second data set demonstrate the ability of the neural field-based approach to reconstruct ditching loads accurately for heterogeneous spatial discretizations. This allows for flexible use of training datasets generated for different geometries and/or discretizations, as well as the use of the surrogate model to predict loads for different configurations.

physics.flu-dyn↗

arXiv2025

Data-driven pressure field prediction for ships in regular sea states

Merchant shipping is responsible for more than 90% of the global trade and has a significant environmental impact, accounting for over 2% of global greenhouse gas emissions. Therefore, fuel-saving measures are becoming increasingly important in reducing the ecological footprint and increasing the fuel efficiency of maritime transport. Routing optimization systems, which require a rapid prediction of ambient-dependent fuel consumption, represent an essential pillar here, e.g. to reduce added resistances due to seaways and/or wind. The paper aims to predict the added resistance due to seaways. In contrast to conventional methods the goal is achieved by surrogate modeling of the entire pressure fields. To this end, an online/offline-procedure is applied to an exemplarily free-floating container vessel. The online approach to be trained consists of two building blocks, namely a convolutional autoencoder (CAE)-based order reduction step and a neural network-based (NN) regression step that links the reduced space of the autoencoder with three control parameters that describe the sea state (wave height/steepness, encounter angle and wave length). Training data is obtained from time-averaged values for simulating instantaneous ship motion and pressure fields. During the offline phase, the combined CAE/NN is trained to capture the time-averaged pressure fields for a variety of sea-state conditions. During ship operation (online phase), the surrogate model predicts the three-dimensional pressure fields in response to sea state conditions, projects the pressure fields onto the ship hull, and integrates the corresponding resistances to guide the route. The evaluation of the method shows promising results for the different building blocks and the concept could therefore represent an attractive approach for cost-effective surrogate modeling of complex multiphase flow fields.

physics.flu-dyn↗

arXiv2025

Disentangled Latent Spaces for Reduced Order Models using Deterministic Autoencoders

Data-driven reduced-order models based on autoencoders generally lack interpretability compared to classical methods such as the proper orthogonal decomposition. More interpretability can be gained by disentangling the latent variables and analyzing the resulting modes. For this purpose, probabilistic $β$-variational autoencoders ($β$-VAEs) are frequently used in computational fluid dynamics and other simulation sciences. Using a benchmark periodic flow dataset, we show that competitive results can be achieved using non-probabilistic autoencoder approaches that either promote orthogonality or penalize correlation between latent variables. Compared to probabilistic autoencoders, these approaches offer more robustness with respect to the choice of hyperparameters entering the loss function. We further demonstrate the ability of a non-probabilistic approach to identify a reduced number of active latent variables by introducing a correlation penalty, a function also known from the use of $β$-VAE. The investigated probabilistic and non-probabilistic autoencoder models are finally used for the dimensionality reduction of aircraft ditching loads, which serves as an industrial application in this work.

cs.LG↗

arXiv2024

Machine Learning based Prediction of Ditching Loads

We present approaches to predict dynamic ditching loads on aircraft fuselages using machine learning. The employed learning procedure is structured into two parts, the reconstruction of the spatial loads using a convolutional autoencoder (CAE) and the transient evolution of these loads in a subsequent part. Different CAE strategies are assessed and combined with either long short-term memory (LSTM) networks or Koopman-operator based methods to predict the transient behaviour. The training data is compiled by an extension of the momentum method of von-Karman and Wagner and the rationale of the training approach is briefly summarised. The application included refers to a full-scale fuselage of a DLR-D150 aircraft for a range of horizontal and vertical approach velocities at 6° incidence. Results indicate a satisfactory level of predictive agreement for all four investigated surrogate models examined, with the combination of an LSTM and a deep decoder CAE showing the best performance.

cs.LG↗