Application of artificial neural network in materials research Wei SHA Professor of Materials Science

Slides:



Advertisements
Similar presentations
Ryan Kraft, and Rajiv Asthana, University of Wisconsin-Stout
Advertisements

Jerzy DOBRODZIEJ, Jacek WOJUTYŃSKI, Jerzy RATAJSKI, Tomasz SUSZKO, Jerzy MICHALSKI INSTITUTE FOR SUSTAINABLE TECHNOLOGIES – NATIONAL RESEARCH INSTITUTE.
Artificial Neural Networks - Introduction -
Decision Support Systems
1 Part I Artificial Neural Networks Sofia Nikitaki.
Handwritten Character Recognition Using Artificial Neural Networks Shimie Atkins & Daniel Marco Supervisor: Johanan Erez Technion - Israel Institute of.
University of Cambridge Department of Materials Science and Metallurgy
Neural Networks
Radu Calin Dimitriu Modelling the Hot-Strength of Creep-Resistant Ferritic Steels and Relationship to Creep-Rupture.
Radial Basis Function Networks 표현아 Computer Science, KAIST.
University of Cambridge Stéphane Forsik 5 th June 2006 Neural network: A set of four case studies.
Statistical variation of material properties In practice, material properties are seldom homogenous, as they are sensitive to variations in parameter such.
Power Systems Application of Artificial Neural Networks. (ANN)  Introduction  Brief history.  Structure  How they work  Sample Simulations. (EasyNN)
VESTEL database realistic telephone speech corpus:  PRNOK5TR: 5810 utterances in the training set  PERFDV: 2502 utterances in testing set 1 (vocabulary.
Presenting: Itai Avron Supervisor: Chen Koren Characterization Presentation Spring 2005 Implementation of Artificial Intelligence System on FPGA.
1 Automated Feature Abstraction of the fMRI Signal using Neural Network Clustering Techniques Stefan Niculescu and Tom Mitchell Siemens Medical Solutions,
Training a Neural Network to Recognize Phage Major Capsid Proteins Author: Michael Arnoult, San Diego State University Mentors: Victor Seguritan, Anca.
Presenting: Itai Avron Supervisor: Chen Koren Mid Semester Presentation Spring 2005 Implementation of Artificial Intelligence System on FPGA.
An affordable creep-resistant nickel-base alloy for power plant Franck Tancret Harry Bhadeshia.
Efficient Generation of Electricity
Understanding Transformations in Copper Bearing Low Carbon Steels Teruhisa Okumura Department of Materials Science and Metallurgy University of Cambridge.
ADAPTIVE-MODEL-BASED OPTIMIZATION AND CONTROL OF AUTOMOTIVE PAINT SPRAY Jia Li and Yinlun Huang Department of Chemical Engineering and Materials Science.
Artificial Neural Network An artificial neural network (ANN), usually called neural network (NN), is a mathematical model or computational model that is.
THE EFFECT OF HEAT TREATMENT ON THE PROPERTIES OF ZIRCONIUM - CARBON STEEL BIMETAL PRODUCED BY EXPLOSION WELDING Mariusz Prażmowski 1), Henryk Paul 2),
Lehký, Keršner, Novák – Determination of concrete statistics using fracture test and inv. analysis based on FraMePID-3PB DETERMINATION OF STATISTICAL MATERIAL.
Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks.
Queen’s University Belfast Crest; Coat of Arms; Emblem.
Nanoscience: Mechanical Properties Olivier Nguon CHEM *7530/750 Feb 21st 2006.
IE 585 Introduction to Neural Networks. 2 Modeling Continuum Unarticulated Wisdom Articulated Qualitative Models Theoretic (First Principles) Models Empirical.
© Copyright 2004 ECE, UM-Rolla. All rights reserved A Brief Overview of Neural Networks By Rohit Dua, Samuel A. Mulder, Steve E. Watkins, and Donald C.
Self organizing maps 1 iCSC2014, Juan López González, University of Oviedo Self organizing maps A visualization technique with data dimension reduction.
Introduction to Artificial Neural Network Models Angshuman Saha Image Source: ww.physiol.ucl.ac.uk/fedwards/ ca1%20neuron.jpg.
RG1 University of Chemical Technology and Metallurgy Department of Materials Science Microstructure and Mechanical Properties of Austempered Ductile Cast.
Back-Propagation MLP Neural Network Optimizer ECE 539 Andrew Beckwith.
NEURAL NETWORKS FOR DATA MINING
Precipitation, microstructure and mechanical properties of maraging steels Wei SHA Professor of Materials Science
ARTIFICIAL NEURAL NETWORKS. Overview EdGeneral concepts Areej:Learning and Training Wesley:Limitations and optimization of ANNs Cora:Applications and.
Gap filling of eddy fluxes with artificial neural networks
Dünaamiliste süsteemide modelleerimine Identification for control in a non- linear system world Eduard Petlenkov, Automaatikainstituut, 2013.
03/04/2000LHC Vacuum Design Meeting Karine COUTURIER/EST-SM C17110 and C17410 coppers  Chemical composition (wt%) : copper = alloy balance Be Ni Co Fe.
NEURAL - FUZZY LOGIC FOR AUTOMATIC OBJECT RECOGNITION.
Queen’s University Belfast Crest; Coat of Arms; Emblem.
Soft Computing Lecture 8 Using of perceptron for image recognition and forecasting.
B. Titanium-based Alloys Titanium is hcp at room temperature – and transform to the bcc structure on heating to 883 o C. Alloying elements are added to.
A Simulated-annealing-based Approach for Simultaneous Parameter Optimization and Feature Selection of Back-Propagation Networks (BPN) Shih-Wei Lin, Tsung-Yuan.
 Based on observed functioning of human brain.  (Artificial Neural Networks (ANN)  Our view of neural networks is very simplistic.  We view a neural.
Next Generation Domain-Services in PL-Grid Infrastructure for Polish Science Górecki 1,2, Bachniak 1,2, Liput 2, Rauch 1,2, Kitowski 2,3, Pietrzyk 1,2.
Image Source: ww.physiol.ucl.ac.uk/fedwards/ ca1%20neuron.jpg
PROCESSES MODELING BY ARTIFICIAL NEURAL NETWORKS Tadej Kodelja, Igor Grešovnik i Robert Vertnik, Miha Kovačič, Bojan Senčič, Božidar Šarler Laboratory.
1 Neural Networks MUMT 611 Philippe Zaborowski April 2005.
Big data classification using neural network
, Prof. Dr. -Ing. Andreas Kern; Dipl. -Kffr. Esther Pfeiffer ; Dipl
J. Sargolzaei;A. Hedayati Moghaddam ;
COMPARISON OF WELD METAL PROPERTIES OF C-Mn MULTI-RUN WELDMENTS CONTAINING TITANIUM - AT DIFFERENT LEVELS OF NITROGEN Fig.2- The actual measured tensile.
NEURAL NETWORK APPROACHES FOR AUTOMOBILE MPG PREDICTION
NEURAL NETWORKS Lab 1 dr Zoran Ševarac FON, 2013.
Prof. Carolina Ruiz Department of Computer Science
Introduction to Deep Learning with Keras
Using Artificial Neural Networks and Support Vector Regression to Model the Lyapunov Exponent Adam Maus.
Eco 6380 Predictive Analytics For Economists Spring 2016
network of simple neuron-like computing elements
Introduction to Neural Networks And Their Applications - Basics
The use of Neural Networks to schedule flow-shop with dynamic job arrival ‘A Multi-Neural Network Learning for lot Sizing and Sequencing on a Flow-Shop’
Mechanical Properties of Metals
III. Introduction to Neural Networks And Their Applications - Basics
Gene Structure Prediction Using Neural Networks and Hidden Markov Models June 18, 권동섭 신수용 조동연.
Application of artificial neural network in materials research
A Data Partitioning Scheme for Spatial Regression
Using Clustering to Make Prediction Intervals For Neural Networks
Prof. Carolina Ruiz Department of Computer Science
Presentation transcript:

Application of artificial neural network in materials research Wei SHA Professor of Materials Science

The models Integrated Part III (pp ) “Application of neural- network models” pp

Composition-processing-temperature-mechanical properties TTT diagrams Fatigue life CCT diagrams Microhardness profile The models Graphical user interfaces of software for modelling

Basic principles of neural network modelling NatualArtificial Input Layer Hidden Layer Output Layer Neuron Neural Network The human brain contains – neurons

Basic principles of neural network modelling Steps Database collection Analysis and pre-processing of the data Design and training of the neural network Test of the trained network Using the trained NN for simulation and prediction

Database construction and analysis Distribution of the input dataset

Reading of file with database Normalisation of the data Creating neural network and defining training parameters Neural network training Post-training analyses for training and test subsets Use of the model Experimental verification Random redistribution of database Dividing to training and test subsets for inputs and corresponding outputs Loop for new random redistribution of the database Loops for new network architecture, training algorithm, transfer function and training parameters Algorithm of computer program Creation of neural network model

Number ×100 (%) HV Error EXP NNEXP - = Min = Max = Mean = STDEV = Algorithm of computer program Post-training validation of the software simulations

Algorithm of computer program Comparison between prediction and experiments

Use of the software Block diagram of software system Databases Computer program for training (learning) Trained artificial neural networks Graphical User Interfaces for use of the models Graphical User Interfaces for upgrade of the models Module for new data input Module for input of re- training parameters Module for materials selection

Use of the software Influence of alloy composition in  -TiAl, 1040 °C

Use of the software Microhardness profiles of titanium after nitriding

Use of the software Ti–15Mo–5Zr–3Al, nitrided in N 2 at 750 °C for 60 h (µm)

Use of the software Optimization of alloy composition and processing Optimisation Criteria Trained Neural Network Solution Loops for Heat Treatment Loops for Temperature Loops for Alloy Composition Find Alloy composition with max strength at 420°C Fix Heat treatment = Annealing T = 420°C Sn, Cr, Fe, Si, Nb, Mn = 0; O = 0.12 Vary Al, Mo, Zr, V Solution Al = 5.8; Mo = 7.3; Zr = 5.2; V = 0 Tensile strength (420°C) = 932 MPa; Yield strength = 665 MPa; Elongation = 10%; Modulus of elasticity = 94 GPa; Fatigue strength = 448 MPa; Fracture toughness = 101 MPa m 1/2