1 Using ANN to solve the Navier Stoke Equations Motivation: Solving the complete Navier Stokes equations using direct numerical simulation is computationally.

Slides:



Advertisements
Similar presentations
Artificial Neural Networks
Advertisements

Multi-Layer Perceptron (MLP)
Beyond Linear Separability
Partial Differential Equations
ECE 8443 – Pattern Recognition EE 3512 – Signals: Continuous and Discrete Objectives: Response to a Sinusoidal Input Frequency Analysis of an RC Circuit.
Artificial Intelligence 13. Multi-Layer ANNs Course V231 Department of Computing Imperial College © Simon Colton.
Multilayer Perceptrons 1. Overview  Recap of neural network theory  The multi-layered perceptron  Back-propagation  Introduction to training  Uses.
Neural Networks  A neural network is a network of simulated neurons that can be used to recognize instances of patterns. NNs learn by searching through.
CSCI 347 / CS 4206: Data Mining Module 07: Implementations Topic 03: Linear Models.
Mehran University of Engineering and Technology, Jamshoro Department of Electronic Engineering Neural Networks Feedforward Networks By Dr. Mukhtiar Ali.
Kostas Kontogiannis E&CE
Artificial Neural Networks
Artificial Neural Networks
Simple Neural Nets For Pattern Classification
Prénom Nom Document Analysis: Artificial Neural Networks Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
September 30, 2010Neural Networks Lecture 8: Backpropagation Learning 1 Sigmoidal Neurons In backpropagation networks, we typically choose  = 1 and 
Prénom Nom Document Analysis: Artificial Neural Networks Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
September 23, 2010Neural Networks Lecture 6: Perceptron Learning 1 Refresher: Perceptron Training Algorithm Algorithm Perceptron; Start with a randomly.
October 14, 2010Neural Networks Lecture 12: Backpropagation Examples 1 Example I: Predicting the Weather We decide (or experimentally determine) to use.
Face Recognition Using Neural Networks Presented By: Hadis Mohseni Leila Taghavi Atefeh Mirsafian.
Traffic Sign Recognition Using Artificial Neural Network Radi Bekker
Optimization of thermal processes2007/2008 Optimization of thermal processes Maciej Marek Czestochowa University of Technology Institute of Thermal Machinery.
Dr. Hala Moushir Ebied Faculty of Computers & Information Sciences
A Genetic Algorithms Approach to Feature Subset Selection Problem by Hasan Doğu TAŞKIRAN CS 550 – Machine Learning Workshop Department of Computer Engineering.
Biointelligence Laboratory, Seoul National University
1 Predicting and Understanding the Breakdown of Linear Flow Models P. Stuart, I. Hunter, R. Chevallaz-Perrier, G. Habenicht 19 March 2009.
Classification Part 3: Artificial Neural Networks
Evolving a Sigma-Pi Network as a Network Simulator by Justin Basilico.
1 Tips for solving Project 1 Reactor SO 3 SO 2 +O 2.
Introduction to Artificial Neural Network Models Angshuman Saha Image Source: ww.physiol.ucl.ac.uk/fedwards/ ca1%20neuron.jpg.
Artificial Intelligence Techniques Multilayer Perceptrons.
1 Pattern Recognition: Statistical and Neural Lonnie C. Ludeman Lecture 21 Oct 28, 2005 Nanjing University of Science & Technology.
A note about gradient descent: Consider the function f(x)=(x-x 0 ) 2 Its derivative is: By gradient descent. x0x0 + -
CS344: Introduction to Artificial Intelligence (associated lab: CS386) Pushpak Bhattacharyya CSE Dept., IIT Bombay Lecture 31: Feedforward N/W; sigmoid.
1 Pattern Recognition: Statistical and Neural Lonnie C. Ludeman Lecture 24 Nov 2, 2005 Nanjing University of Science & Technology.
CFD Refinement By: Brian Cowley. Overview 1.Background on CFD 2.How it works 3.CFD research group on campus for which problem exists o Our current techniques.
Non-Bayes classifiers. Linear discriminants, neural networks.
Akram Bitar and Larry Manevitz Department of Computer Science
Title: SHAPE OPTIMIZATION OF AXISYMMETRIC CAVITATOR IN PARTIALY CAVITATING FLOW Department of Mechanical Engineering Ferdowsi University of Mashhad Presented.
CS621 : Artificial Intelligence
Inverse Kinematics for Robotics using Neural Networks. Authors: Sreenivas Tejomurtula., Subhash Kak
Neural Networks - Berrin Yanıkoğlu1 Applications and Examples From Mitchell Chp. 4.
1 Lecture 6 Neural Network Training. 2 Neural Network Training Network training is basic to establishing the functional relationship between the inputs.
AI & Machine Learning Libraries By Logan Kearsley.
Slide 6- 1 What you’ll learn about Differential Equations Slope Fields Euler’s Method … and why Differential equations have been a prime motivation for.
Image Source: ww.physiol.ucl.ac.uk/fedwards/ ca1%20neuron.jpg
5/10/00 Integration of Advanced Automotive Simulation Methods Using ANN 1 Integration of Advanced Automotive Simulation Methods Using Artificial Neural.
C - IT Acumens. COMIT Acumens. COM. To demonstrate the use of Neural Networks in the field of Character and Pattern Recognition by simulating a neural.
Nonlinear balanced model residualization via neural networks Juergen Hahn.
Meta-controlled Boltzmann Machine toward Accelerating the Computation Tran Duc Minh (*), Junzo Watada (**) (*) Institute Of Information Technology-Viet.
Intro. ANN & Fuzzy Systems Lecture 11. MLP (III): Back-Propagation.
Advanced Numerical Techniques Mccormack Technique CFD Dr. Ugur GUVEN.
Neural networks.
One-layer neural networks Approximation problems
Soft Computing Applied to Finite Element Tasks
Announcements HW4 due today (11:59pm) HW5 out today (due 11/17 11:59pm)
Neural Networks A neural network is a network of simulated neurons that can be used to recognize instances of patterns. NNs learn by searching through.
Structure learning with deep autoencoders
AIAA OBSERVATIONS ON CFD SIMULATION UNCERTAINITIES
of the Artificial Neural Networks.
network of simple neuron-like computing elements
Driven Lid Partially Filled Porous Cavity - Single Domain Approach
Coordinate Transformation in 3D Final Project Presentation
Neural networks (1) Traditional multi-layer perceptrons
Artificial Intelligence 10. Neural Networks
Ensembles An ensemble is a set of classifiers whose combined results give the final decision. test feature vector classifier 1 classifier 2 classifier.
August 8, 2006 Danny Budik, Itamar Elhanany Machine Intelligence Lab
Pattern Recognition: Statistical and Neural
Akram Bitar and Larry Manevitz Department of Computer Science
Presentation transcript:

1 Using ANN to solve the Navier Stoke Equations Motivation: Solving the complete Navier Stokes equations using direct numerical simulation is computationally very expensive. A simple three dimensional gas jet might take over one year of CPU time to simulate. Approach: Use of ANN to solve these equations is demonstrated using the driven lid cavity problem. (code: drivencavity.m)

2 Driven lid cavity problem Plate Cavity Reynolds no.=70

3 Steady state predictions CFD solution uses the vorticity-streamfunction approach to solve the NS equations. For a particular reynolds number there is only one unique solution. The quantity to be predicted was the streamfunction since all other quantities such as velocity can be derived directly from it: - Where u and v are the x and y velocity components. An MLP using the back propagation algorithm was used to predict the streamfunction at the 64 grid points with just the Reynolds number as input. Predictions with less than 1 percent error were obtained with just one hidden layer containing three neurons samples were used to train the network.

4 Transient predictions The steady state predictions are not general.i.e. they can be used only at a particular Reynolds number. To be a useful tool the the network was used to solve for the streamfunction in the code. This is the same as solving a set of partial differential equations. The code iterates globally for vorticity and locally for the streamfunction. The streamfunction is solved for, using the Gauss-Siedel method. For this case the code makes 78,997 local iterations for the streamfunction within 300 global iterations for vorticity.

5 Neural Net Predictions Percentage error for streamfunction at each grid point

6 Can we use this model directly? This network had 64 vorticity inputs, 64 streamfunction outputs and 3 hidden layers with 10 neurons each samples were used to train and 300 samples to test. If we use this network directly, the final solution will not converge even if there is 1% error. However we can try to replace the initial iterations by the network and restore the initial numerical method at a later time.

7 Replacing the initial iterations We can let the code skip any number of initial iterations. The solution will always converge as long as we let the original numerical scheme take over at the end. But if we use the neural net for too many iterations, the errors will get stacked up and the numerical scheme will have to do extra iterations to correct the solution. However it was observed that the solution always converges to the one unique solution no matter how long we use the neural network Therefore it becomes an optimization issue; till what point should we use the network and at what point should we changeover?

8 Results and conclusions At the optimum point, computation time reduces by 76.3%

9 Results and conclusions This approach is safe. The unique physical solution is always obtained as long as the original numerical scheme is allowed to kick in at any point. Even if we do not find the optimum point and specify an arbitrary high number of neural net iterations, the plot shows a striking 72% reduction of computational time. The neural net developed to solve this set of PDE’s can be used in general in any code using the same governing equations. This technique has potential to be used in direct numerical simulation, the main limiting factor of which is computational time.