Turbulence Prediction Using Non-Linear Phase Space Analysis

Authors

Jeremy Quijano, University of South AlabamaFollow

Files

Description

Our research presents a novel approach for turbulence prediction in computational fluid dynamics (CFD) simulations using a non-linear phase space analysis (NLPSA) and threshold algorithm. NLPSA has been utilized in medical applications to predict seizures, as well as in cybersecurity to detect malicious control and utilization of computing systems. NLPSA uses time-series data to learn the normal operating state of the system, then sets a threshold to predict when the system becomes abnormal. Turbulence prediction is similar, such that a fluid system changes from normal to abnormal. Turbulence prediction methods currently utilize machine learning tools, such as convolutional neural networks (CNN), which use images created from CFD simulation data. Typical CNN methods require datasets with high resolution to ensure accuracy in their predictions. However, these high-resolution images require increased computational cost to run the prediction models. To combat this, the proposed method uses an NLPSA and threshold algorithm that takes direct time-series data as input to predict when or if a system becomes abnormal. We will compare this approach with traditional CNN prediction models to test accuracy and feasibility. The main advantages to using NLPSA are the reduced computing cost and the ability to use data directly from the CFD simulation, rather than needing to interpolate and extrapolate images as with a CNN. We expect the proposed NLPSA method to extend the understanding and study of turbulence prediction by providing a new and novel approach.

Publication Date

3-2025

Department

Computer Science

City

Mobile

Disciplines

OS and Networks | Other Computer Sciences | Programming Languages and Compilers | Systems Architecture

Recommended Citation

Quijano, Jeremy, "Turbulence Prediction Using Non-Linear Phase Space Analysis" (2025). Shelby Hall Graduate Research Forum Posters. 1.
https://jagworks.southalabama.edu/southalabama-shgrf-posters/1