scholarly journals Learning functionals via LSTM neural networks for predicting vessel dynamics in extreme sea states

2021 ◽  
Vol 477 (2245) ◽  
pp. 20190897
Author(s):  
J. del Águila Ferrandis ◽  
M. S. Triantafyllou ◽  
C. Chryssostomidis ◽  
G. E. Karniadakis
Keyword(s):  
Neural Networks ◽  
Cfd Simulations ◽  
Sea State ◽  
Wave Elevation ◽  
Engineering Problems ◽  
Testing Error ◽  
Simulation Paradigm ◽  
Computational Resources ◽  
State 1 ◽  
Recurrent Type

Predicting motions of vessels in extreme sea states represents one of the most challenging problems in naval hydrodynamics. It involves computing complex nonlinear wave-body interactions, hence taxing heavily computational resources. Here, we put forward a new simulation paradigm by training recurrent type neural networks (RNNs) that take as input the stochastic wave elevation at a certain sea state and output the main vessel motions, e.g. pitch, heave and roll. We first compare the performance of standard RNNs versus GRU and LSTM neural networks (NNs) and show that LSTM NNs lead to the best performance. We then examine the testing error of two representative vessels, a catamaran in sea state 1 and a battleship in sea state 8. We demonstrate that good accuracy is achieved for both cases in predicting the vessel motions for unseen wave elevations. We train the NNs with expensive CFD simulations offline , but upon training, the prediction of the vessel dynamics online can be obtained at a fraction of a second. This work is motivated by the universal approximation theorem for functionals (Chen & Chen, 1993. IEEE Trans. Neural Netw. 4 , 910–918 ( doi:10.1109/72.286886 )), and it is the first implementation of such theory to realistic engineering problems.

scholarly journals Efficient Binarized Convolutional Layers for Visual Inspection Applications on Resource-Limited FPGAs and ASICs

Electronics ◽  
2021 ◽  
Vol 10 (13) ◽  
pp. 1511
Author(s):  
Taylor Simons ◽  
Dah-Jye Lee
Keyword(s):  
Neural Networks ◽  
Visual Inspection ◽  
Deep Neural Networks ◽  
Computational Cost ◽  
Quality Inspection ◽  
Agricultural Produce ◽  
Resource Limited ◽  
Inspection Tasks ◽  
Computational Resources ◽  
Small Models

There has been a recent surge in publications related to binarized neural networks (BNNs), which use binary values to represent both the weights and activations in deep neural networks (DNNs). Due to the bitwise nature of BNNs, there have been many efforts to implement BNNs on ASICs and FPGAs. While BNNs are excellent candidates for these kinds of resource-limited systems, most implementations still require very large FPGAs or CPU-FPGA co-processing systems. Our work focuses on reducing the computational cost of BNNs even further, making them more efficient to implement on FPGAs. We target embedded visual inspection tasks, like quality inspection sorting on manufactured parts and agricultural produce sorting. We propose a new binarized convolutional layer, called the neural jet features layer, that learns well-known classic computer vision kernels that are efficient to calculate as a group. We show that on visual inspection tasks, neural jet features perform comparably to standard BNN convolutional layers while using less computational resources. We also show that neural jet features tend to be more stable than BNN convolution layers when training small models.

Prediction of slip in cable-drum systems using structured neural networks

2013 ◽  
Vol 228 (3) ◽  
pp. 441-456 ◽  
Author(s):  
Ergin Kilic ◽  
Melik Dolen
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Size ◽  
Network Architectures ◽  
Network Development ◽  
Low Velocity ◽  
Error Band ◽  
Artificial Neural ◽  
Recurrent Type ◽  
Selection Of

This study focuses on the slip prediction in a cable-drum system using artificial neural networks for the prospect of developing linear motion sensing scheme for such mechanisms. Both feed-forward and recurrent-type artificial neural network architectures are considered to capture the slip dynamics of cable-drum mechanisms. In the article, the network development is presented in a progressive (step-by-step) fashion for the purpose of not only making the design process transparent to the readers but also highlighting the corresponding challenges associated with the design phase (i.e. selection of architecture, network size, training process parameters, etc.). Prediction performances of the devised networks are evaluated rigorously via an experimental study. Finally, a structured neural network, which embodies the network with the best prediction performance, is further developed to overcome the drift observed at low velocity. The study illustrates that the resulting structured neural network could predict the slip in the mechanism within an error band of 100 µm when an absolute reference is utilized.

Nonlinear Ship Loads: Stochastic Models for Extreme Response

1998 ◽  
Vol 42 (01) ◽  
pp. 46-55
Author(s):  
Rune Torhaug ◽  
Steven R. Winterstein ◽  
Arne Braathen
Keyword(s):  
Time Domain ◽  
Stochastic Models ◽  
Stochastic Analysis ◽  
Short Wave ◽  
Response Analysis ◽  
Correct Result ◽  
Sea State ◽  
Extreme Response ◽  
Computational Resources ◽  
The Cost

In this study we focus on stochastic analysis methods for selective simulations, and we consider the extreme midspan moment of a fast-moving ship subjected to random Gaussian waves. We concentrate on analysis within a stationary sea state and our purpose is to accurately estimate hourly maximum ship response (compared with the correct result per hour) within a sea state with as little computational resources as possible. We consider how the use of a limited number of short simulations with "critical wave episodes" (short wave segments which are likely candidates to produce extreme response in the simulated hour-long history) reduces the cost of nonlinear time-domain ship response analysis.

Artificial Neural Networks (ANNs) and Solution of Civil Engineering Problems

2020 ◽  
pp. 13-38
Author(s):  
Melda Yucel ◽  
Sinan Melih Nigdeli ◽  
Gebrail Bekdaş
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Structural Properties ◽  
Structural Design ◽  
Civil Engineering ◽  
Back Propagation ◽  
Training Algorithm ◽  
Design Problems ◽  
Engineering Problems ◽  
Artificial Neural

This chapter reveals the advantages of artificial neural networks (ANNs) by means of prediction success and effects on solutions for various problems. With this aim, initially, multilayer ANNs and their structural properties are explained. Then, feed-forward ANNs and a type of training algorithm called back-propagation, which was benefited for these type networks, are presented. Different structural design problems from civil engineering are optimized, and handled intended for obtaining prediction results thanks to usage of ANNs.

scholarly journals On the Assessment of Numerical Wave Makers in CFD Simulations

2019 ◽  
Vol 7 (2) ◽  
pp. 47 ◽  
Author(s):  
Christian Windt ◽  
Josh Davidson ◽  
Pál Schmitt ◽  
John Ringwood
Keyword(s):  
Test Cases ◽  
Cfd Simulations ◽  
Wave Tank ◽  
Free Surface Waves ◽  
Offshore Engineering ◽  
Engineering Problems ◽  
Computational Fluid Dynamics Cfd ◽  
Single Method ◽  
Wave Maker ◽  
Numerical Wave

A fully non-linear numerical wave tank (NWT), based on Computational Fluid Dynamics (CFD), provides a useful tool for the analysis of coastal and offshore engineering problems. To generate and absorb free surface waves within a NWT, a variety of numerical wave maker (NWM) methodologies have been suggested in the literature. Therefore, when setting up a CFD-based NWT, the user is faced with the task of selecting the most appropriate NWM, which should be driven by a rigorous assessment of the available methods. To provide a consistent framework for the quantitative assessment of different NWMs, this paper presents a suite of metrics and methodologies, considering three key performance parameters: accuracy, computational requirements and available features. An illustrative example is presented to exemplify the proposed evaluation metrics, applied to the main NWMs available for the open source CFD software, OpenFOAM. The considered NWMs are found to reproduce waves with an accuracy comparable to real wave makers in physical wave tank experiments. However, the paper shows that significant differences are found between the various NWMs, and no single method performed best in all aspects of the assessment across the different test cases.

Intercomparison of Seastate and Zerocrossing Parameters From the WACSIS Field Experiment and Interpretation Using Video Evidence

2002 ◽  
Author(s):  
Stephen F. Barstow ◽  
Harald E. Krogstad ◽  
Lasse Lo̸nseth ◽  
Jan Petter Mathisen ◽  
Gunnar Mo̸rk ◽  
...  
Keyword(s):  
Time Series ◽  
The Netherlands ◽  
Field Experiment ◽  
Time Series Data ◽  
Series Data ◽  
Sea State ◽  
Single Wave ◽  
Video Recordings ◽  
Wave Parameters ◽  
Wave Elevation

During the WACSIS field experiment, wave elevation time series data were collected over the period December 1997 to May 1998 on and near the Meetpost Nordwijk platform off the coast of the Netherlands from an EMI laser, a Saab radar, a Baylor Wave Staff, a Vlissingen step gauge, a Marex radar and a Directional Waverider. This paper reports and interprets, with the help of simultaneous dual video recordings of the ocean surface, an intercomparison of both single wave and sea state wave parameters.

Ship As a Wave Buoy: Using Simulated Data to Train Neural Networks for Real Time Estimation of Relative Wave Direction

2019 ◽  
Author(s):  
Bart Mak ◽  
Bülent Düz
Keyword(s):  
Neural Networks ◽  
Real Time ◽  
General Model ◽  
Simulated Data ◽  
Time Estimation ◽  
Measured Data ◽  
Wave Direction ◽  
Sea State ◽  
Digital Twin ◽  
Extended Training

Abstract Being able to give real time on-board advice, without depending on extensive sets of measured data, is the ultimate goal of the digital twin concept. Ideally, the models used in a digital twin only rely on current in-service data, although they have been built using simulated and possibly some measured data. Working with just the 6-DOF motions of a ship, can the local sea state reliably be estimated using the digital twin concept? Does a general model exist to do so, without the need to measure or simulate the particular ship? In this paper, we discuss how simulations of an advancing ship, subjected to various sea states, can be used to estimate the relative wave direction from in-service motion measurements of the corresponding ship. Various types of neural networks are used and evaluated with simulated data and measured data. In order to study the generalization power of the neural networks, a range of ships has been simulated, with varying lengths, drafts and geometries. Neural networks have been trained on selections of the ships in this extended training set and evaluated on the remaining ships. Results show that the developed neural networks give a remarkable performance in simulation data. Furthermore, generalization over geometry is very good, opening the door to train a general model for estimating sea state characteristics. Using the same model for in-service measurements does not perform well enough yet and further research is required. The paper will include discussion on possible causes for this performance gap and some promising ideas for future work.

Sign in / Sign up

Export Citation Format

Share Document