Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Applied Neural Network-Based Active Control for Vortex-Induced Vibrations Suppression in a Two-Degree-of-Freedom Cylinder

Soha Ilbeigi, Ashkan Bagherzadeh, Alireza Sharifi

TL;DR

The paper tackles VIV suppression in a 2DOF cylinder by integrating a model-based active control framework with neural network-based uncertainty estimation. By coupling URANS fluid dynamics with a Newtonian structural model and employing FEL-inspired learning (with Simple and Composite variants), the authors achieve substantial vibration attenuation and demonstrate controllability. Composite Learning offers faster convergence, smoother control, and higher suppression accuracy, both with and without uncertainty, outperforming a conventional SMC baseline. The work advances robust VIV control through real-time uncertainty compensation and rigorous stability analysis, with strong implications for the durability and efficiency of cylindrical structures in fluid environments.

Abstract

Vortex-Induced Vibrations (VIVs) of cylindrical structures present significant challenges in various engineering applications, including marine risers, tall buildings, and renewable energy systems. Hence, it is vital to control Vortex-Induced Vibrations of cylindrical structures. For this purpose, in this study a novel approach is introduced to VIV control, based on a model-based active control strategy integrated with a Neural Network (NN) in the presence of uncertainty modeling. The proposed method utilizes a closed-loop control system, where feedback from the system's dynamic state is used to generate adaptive control commands, enabling the system to respond to changing flow conditions and nonlinearities. Then, the controllability analysis is conducted to assess the efficiency of the control strategy in mitigating VIV. Two control approaches are implemented: simple learning and composite learning. Both strategies significantly enhance vibration suppression, achieving up to 99% reduction in vibrations despite uncertainties in the system. The results demonstrate the potential of the proposed method to enhance the efficiency, stability, and lifespan of structures subject to VIV.

Applied Neural Network-Based Active Control for Vortex-Induced Vibrations Suppression in a Two-Degree-of-Freedom Cylinder

TL;DR

The paper tackles VIV suppression in a 2DOF cylinder by integrating a model-based active control framework with neural network-based uncertainty estimation. By coupling URANS fluid dynamics with a Newtonian structural model and employing FEL-inspired learning (with Simple and Composite variants), the authors achieve substantial vibration attenuation and demonstrate controllability. Composite Learning offers faster convergence, smoother control, and higher suppression accuracy, both with and without uncertainty, outperforming a conventional SMC baseline. The work advances robust VIV control through real-time uncertainty compensation and rigorous stability analysis, with strong implications for the durability and efficiency of cylindrical structures in fluid environments.

Abstract

Vortex-Induced Vibrations (VIVs) of cylindrical structures present significant challenges in various engineering applications, including marine risers, tall buildings, and renewable energy systems. Hence, it is vital to control Vortex-Induced Vibrations of cylindrical structures. For this purpose, in this study a novel approach is introduced to VIV control, based on a model-based active control strategy integrated with a Neural Network (NN) in the presence of uncertainty modeling. The proposed method utilizes a closed-loop control system, where feedback from the system's dynamic state is used to generate adaptive control commands, enabling the system to respond to changing flow conditions and nonlinearities. Then, the controllability analysis is conducted to assess the efficiency of the control strategy in mitigating VIV. Two control approaches are implemented: simple learning and composite learning. Both strategies significantly enhance vibration suppression, achieving up to 99% reduction in vibrations despite uncertainties in the system. The results demonstrate the potential of the proposed method to enhance the efficiency, stability, and lifespan of structures subject to VIV.

Paper Structure

This paper contains 21 sections, 1 theorem, 31 equations, 16 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Problem Definition
  3. Modeling of the Cylinder Dynamics
  4. Fluid Model
  5. Structural Model
  6. Uncertainty Estimation
  7. Neural Network Structure
  8. Hidden Layer and Activation Function
  9. Output Layer and Approximation
  10. Universal Approximation and Convergence
  11. Formulation of Controller Design
  12. Dynamical System
  13. Nonlinear Controllability Analysis
  14. Simple Learning Method
  15. Composite Learning Method
  16. ...and 6 more sections

Key Result

Lemma 1

(Lie Bracket Criterion for Controllability) Consider a nonlinear dynamic system represented by where $x \in \mathbb{R}^n$ is the state vector, $u \in \mathbb{R}^m$ is the control input vector, and $\mathbf{f(x)}$ and $\mathbf{g(x)}$ are smooth vector fields on $\mathbb{R}^n$. Define the controllability matrix $M$ as where $[\cdot, \cdot]$ denotes the Lie bracket of two vector fields. The system

Figures (16)

  • Figure 1: Structure of the NN-VIV Suppression simulation method
  • Figure 2: Structural model within the fluid solution domain
  • Figure 3: Computational domain of fluid model
  • Figure 4: Structure of the proposed neural network
  • Figure 5: Comparison of fluid domain results for both fixed and free case
  • ...and 11 more figures

Theorems & Definitions (1)

  • Lemma 1