Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Adjoint-based shape optimization of a ship hull using a Conditional Variational Autoencoder (CVAE) assisted propulsion surrogate model

Moloud Arian Maram, Georgios Bletsos, Thanh Tung Nguyen, Ahmed Hassan, Michael Palm, Thomas Rung

TL;DR

A machine learning-assisted optimization framework that employs a Conditional Variational Autoencoder-based surrogate model of the propulsion system that replicates the time-averaged flow field induced by a Voith Schneider Propeller and replaces the geometrically and time-resolved propeller with a data-driven approximation is proposed.

Abstract

Adjoint-based shape optimization of ship hulls is a powerful tool for addressing high-dimensional design problems in naval architecture, particularly in minimizing the ship resistance. However, its application to vessels that employ complex propulsion systems introduces significant challenges. They arise from the need for transient simulations extending over long periods of time with small time steps and from the reverse temporal propagation of the primal and adjoint solutions. These challenges place considerable demands on the required storage and computing power, which significantly hamper the use of adjoint methods in the industry. To address this issue, we propose a machine learning-assisted optimization framework that employs a Conditional Variational Autoencoder-based surrogate model of the propulsion system. The surrogate model replicates the time-averaged flow field induced by a Voith Schneider Propeller and replaces the geometrically and time-resolved propeller with a data-driven approximation. Primal flow verification examples demonstrate that the surrogate model achieves significant computational savings while maintaining the necessary accuracy of the resolved propeller. Optimization studies show that ignoring the propulsion system can yield designs that perform worse than the initial shape. In contrast, the proposed method produces shapes that achieve more than an 8\% reduction in resistance.

Adjoint-based shape optimization of a ship hull using a Conditional Variational Autoencoder (CVAE) assisted propulsion surrogate model

TL;DR

A machine learning-assisted optimization framework that employs a Conditional Variational Autoencoder-based surrogate model of the propulsion system that replicates the time-averaged flow field induced by a Voith Schneider Propeller and replaces the geometrically and time-resolved propeller with a data-driven approximation is proposed.

Abstract

Adjoint-based shape optimization of ship hulls is a powerful tool for addressing high-dimensional design problems in naval architecture, particularly in minimizing the ship resistance. However, its application to vessels that employ complex propulsion systems introduces significant challenges. They arise from the need for transient simulations extending over long periods of time with small time steps and from the reverse temporal propagation of the primal and adjoint solutions. These challenges place considerable demands on the required storage and computing power, which significantly hamper the use of adjoint methods in the industry. To address this issue, we propose a machine learning-assisted optimization framework that employs a Conditional Variational Autoencoder-based surrogate model of the propulsion system. The surrogate model replicates the time-averaged flow field induced by a Voith Schneider Propeller and replaces the geometrically and time-resolved propeller with a data-driven approximation. Primal flow verification examples demonstrate that the surrogate model achieves significant computational savings while maintaining the necessary accuracy of the resolved propeller. Optimization studies show that ignoring the propulsion system can yield designs that perform worse than the initial shape. In contrast, the proposed method produces shapes that achieve more than an 8\% reduction in resistance.
Paper Structure (21 sections, 13 equations, 19 figures, 3 tables, 1 algorithm)

This paper contains 21 sections, 13 equations, 19 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Suggested Optimization Approach
  3. Autoencoder Surrogate Model
  4. Configuration of the Conditional Variational Autoencoder
  5. Learning Rate
  6. CFD-based Methodology
  7. Governing Equations
  8. Computational Domain and Numerical Mesh
  9. Structure of Parameter Data
  10. Meta-Grid
  11. Integration of offline CFD results into surrogate model
  12. Integration of surrogate model into CFD software
  13. Verification and Validation
  14. Validation of the Surrogate Model
  15. Verification of Propulsion Model Integration into CFD
  16. ...and 6 more sections

Figures (19)

  • Figure 1: Service Operation Vessel equipped with a Voith Schneider Propeller and exemplary mesh components.
  • Figure 2: Basic autoencoder scheme.
  • Figure 3: Architecture of the CVAE model used to reconstruct the velocity field.
  • Figure 4: Architecture of self-attention mechanism (top) and basic residual block (bottom).
  • Figure 5: Computational domain and boundary conditions
  • ...and 14 more figures