Using Soft Computing Technologies for the Simulation of LCAC Dynamics

Abstract

Data acquired from experiments with a 1/6th scale, free-running model of an air-cushioned, amphibious vehicle (LCAC) in waves and calm water were used to train a recursive neural network (RNN). This network is used to simulate the six degree-of-freedom motion of the LCAC providing faster than real-time, time-domain predictions of the vehicle's dynamics as a function of the control signals given by the driver. Results are presented comparing the time-series predictions of the RNN simulation with experimental data. Two error measures are used to quantify the results, an average angle measure and a correlation coefficient, and they indicate good solutions in every case. The intent is to use this time domain simulation of LCAC to gain further insight into the vehicle's dynamics in calm water and irregular waves.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2011
Accession Number
ADA558410

Entities

People

  • David E. Hess
  • Thomas K. Fu
  • William E. Faller

Organizations

  • Naval Surface Warfare Center Carderock Division

Tags

Communities of Interest

  • Ground and Sea Platforms
  • Weapons Technologies

DTIC Thesaurus Topics

  • Accuracy
  • Dynamics
  • Engineering
  • Engineers
  • Errors
  • Experimental Data
  • Fans
  • Ground Effect Machines
  • Landing Craft
  • Military Research
  • Neural Networks
  • Ships
  • Simulations
  • Surface Warfare
  • Thrusters
  • Time Domain
  • Turbines

Readers

  • Computational Modeling and Simulation
  • Marine Hydrodynamics
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks