arXiv subjects

Pyei Phyo Lin

Publications and source records attributed to Pyei Phyo Lin.

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

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↗

arXiv2023

Assessing the Suitability of the Langevin Equation for Analyzing Measured Data Through Downsampling

The measured time series from complex systems are renowned for their intricate stochastic behavior, characterized by random fluctuations stemming from external influences and nonlinear interactions. These fluctuations take diverse forms, ranging from continuous trajectories reminiscent of Brownian motion to noncontinuous trajectories featuring jump events. The Langevin equation serves as a powerful tool for generating stochasticity and capturing the complex behavior of measured data with continuous stochastic characteristics. However, the traditional modeling framework of the Langevin equation falls short when it comes to capturing the presence of abrupt changes, particularly jumps, in trajectories that exhibit non-continuity. Such non-continuous changes pose a significant challenge for general processes and have profound implications for risk management. Moreover, the discrete nature of observed physical phenomena, measured with a finite sample rate, adds another layer of complexity. In such cases, data points often appear as a series of discontinuous jumps, even when the underlying trajectory is continuous. In this study, we present an analytical framework that goes beyond the limitations of the Langevin equation. Our approach effectively distinguishes between diffusive or Brownian-type trajectories and trajectories with jumps. By employing downsampling techniques, where we artificially lower the sample rate, we derive a set of measures and criteria to analyze the data and differentiate between diffusive and non-diffusive behaviors. To further demonstrate its versatility and practical applicability, we have applied our proposed method to real-world data in various scientific fields, turbulence, optical tweezers for trapped particles, neuroscience, renewable energy, and market price analysis.

cond-mat.stat-mech↗

arXiv2023

Discontinuous Jump Behavior of the Energy Conversion in Wind Energy Systems

The power conversion process of a wind turbine can be characterized by a stochastic differential equation (SDE) of the power output conditioned to certain fixed wind speeds. An analogous approach can also be applied to the mechanical loads on a wind turbine, such as generator torque. The constructed SDE consists of the deterministic and stochastic terms, the latter corresponding to the highly fluctuating behavior of the wind turbine. Here we show how advanced stochastic analysis of the noise contribution can be used to show different operating modes of the conversion process of a wind turbine. The parameters of the SDE, known as Kramers-Moyal (KM) coefficients, are estimated directly from the measurement data. Clear evidence is found that both, continuous diffusion noise and discontinuous jump noise are present. The difference in the noise contributions indicates different operational regions. In particular, we observe that the jump character or discontinuity in power production has a significant contribution in the regions where the control system switches strategies. We find that there is a high increase in jump amplitude near the transition to the rated region, and the switching strategies cannot result in a smooth transition. The proposed analysis provides new insights to the control strategies of the wind turbine.

eess.SY↗