A Survey of Neural Computing of Effective Properties of Random Composites
|
|
- Ashley Bryce Bryant
- 5 years ago
- Views:
Transcription
1 A Survey of Neural Computing of Effective Properties of Random Composites ABRAHAM I. BELTZER, VICTOR A. GOTLIB Holon Academic Institute of Technology POB 305, Holon 580 ISRAEL TADANOBU SATO Disaster Prevention Research Institute yoto University Gokasho, Uji, yoto 6 JAPAN Abstract: - The effective behavior of disordered heterogeneous materials, in general, is not amenable to exact analysis because the phase geometry may not be completely specified. Besides the bounds for the effective moduli, most reported results are essentially approximate, may contradict each other or even violate the bounds. With increasing number of phases, and therefore increasing uncertainty inherent in the very statement of the problem, the investigation of effective behavior becomes less amenable to analytical treatment, in particular, by methods of boundary-value problems of mathematical physics. The present paper discusses, in light of recent publications, a methodology for investigating the effective behavior of disordered composites with the help of neural networks as well as particular results obtained for effectively isotropic and macroscopically homogeneous two-phase materials. It appears that, after incorporating the bounds and proper training, simple neural networks may describe a wide variety of the effective behavior for two-phase composites, though in general more complicated networks appear necessary. ey-words: - neural network, random composite, effective behavior, elastic properties. Introduction The present paper deals with recent investigations into the effective behavior of disordered composites with the help of a neural network, which has become one of the main paradigms of engineering research. Artificial neural networks have proven useful in treating problems characterized by incomplete a priori given information and are difficult for exact analysis, in particular, by the methods borrowed from boundary-value problems of mathematical physics. This is typical of disordered materials and therefore neural networks, which are capable of discovering a hidden regularity, may constitute a useful tool for specifying their effective behavior. For details concerning the effective static behavior of composites the reader is referred, for example, to the works [] [6]. The effective behavior of disordered heterogeneous materials is not amenable to exact analysis because the phase geometry may not be completely specified. Besides the bounds for the effective moduli, most reported results are essentially approximate, may contradict each other or even violate the bounds. Resort to a particular shape of inclusion necessary in the frameworks of such methods as the composite sphere assemblage or self-consistent schemes seems to contradict to a basic assumption of arbitrary phase geometry, which should come into play through the volume concentration only. With increasing number of phases and therefore increasing uncertainty inherent in the very statement of the problem, the investigation of effective behavior becomes less amenable to analytical treatment, in particular, by methods of boundary-value problems of
2 mathematical physics. That is why applications of neural networks to this problem is useful. The publications on neural computing of the efective behavior of composite materials include a communication [7] and papers [8] and [9]. These deal with: (i the general methodology of application of neural networks to disordered heterogeneous materials; (ii particular results derived for the effective elastic moduli and for the effective scalar property, such as conductivity, of two-phase composites. The elastic response of isotropic composites is governed by two effective moduli. One therefore may consider a problem of specifying the bulk and Young s moduli, and E, respectively, of a twophase elastic isotropic material of arbitrary geometry. Another relevant issue is the problem of effective scalar properties, such as: thermal conductivity, electrical conductivity, dielectric constant, magnetic permeability, and diffusivity in the realm of disordered composites. Below we denote all these quantities by a scalar parameter k. In this case, the phenomena are described by similar mathematical expressions, the effective property being the coefficient in the relevant equation, which relates solenoidal and irrotational vector fields. For details of the similarity among the indicated phenomena the reader is referred to the reviews [] and [3]. The lower - and upper Hashin-Shtrikman bounds for the bulk modulus for such composites are [3] c - =, ( 3c 3 4G c =, ( 3c 3 4G where and are the bulk moduli of the phases, G and G their shear moduli, c and c their volume concentrations and <, G < G, c c =. Similarly, for the shear modulus, G, the bounds are c G- = G, (3 6c ( G G G 5G (3 4G G c = G, (4 6c( G ( G G 5G (3 4G These Hashin-Shtrikman bounds are the best possible as far as arbitrary geometry is concerned, and their disparity is sensitive to the shear moduli ratio, G /G, vanishing for G /G =. The latter case, for which the exact solution does exist, is known as Hill s solid [] and is naturally excluded from the present investigation. The main body of experiments available deals with the effective moduli and E rather then and G. The bounds for E follow from the well known relation E = E(, G and expressions ( - (4: E ± 9± G± = 3 G ± ±. (5 As far as effective scalar property k is concerned, the lower, k -, and upper, k, Hashin- Shtrikman bounds, which are also,the best possible as far as arbitrary geometry is concerned, are (see, for example, Ref. [3]: k = c k, (6 c k k 3k k = c k, (7 c k k 3k where k and k are the parameters of the phases, c and c their volume concentrations and k < k, c c. = Neural Networks First, consider the case of elastic behavior. It is assumed that (i the composite microstructure is not completely known and is specified in terms of,, G, G, c, (or c = - c only; and (ii the composite may be treated as effectively isotropic and macroscopically homogeneous. In the case of a scalar property, which is denoted by the generic notation k, the difference is that the microstructure description contains three parameters only, k, k and c.
3 3 Taking into account the bias and avoiding the overfitting, one may try a single-neuron network (perceptron with six inputs in case of the elastic behavior and with four inputs in case of the effective scalar behavior, such as electrical conductivity, for example. As to the transfer function, we note that the effective moduli depend on its arguments in a nonlinear manner and are bounded from below and above. A sigmoid transfer function - F ( n = tanh( n (8 may incorporate this fundamental behavior. Here F is the network output and n = w (9 0 w wg w3 w4g w5c is the total (weighted network input in case of the elastic response. Given the value of F, the bulk modulus follows as: F F = and the inverse transformation F ( = (0 ( relates -. and the network output - F. Similar expressions hold for Young s modulus E. Evidently, the weights and biases can be different for the cases of and E. For the effective scalar property, k, the total (weighted net input is 3 n = w u = w w k w θ w c, ( i= 0 i i 0 3 where w 0 is the bias, θ is the dimensionless input parameter, θ = ( k k k, 0 < θ. k is the normalized quantity k, (k > k scaled to the interval 0. < k according to the expressions k = k 0 p, = [ log0 k ] p, (3 where the square brackets denote the floorfunction. Another parameter k is scaled using the same value of p, i.e. k = p k 0. This methodology enables one to inherently incorporate the bounds, which are shown below to also facilitate a proper specification of the training set. Besides the bounds, the relevant information consists of experimental data, which are approximate because of the experimental scatter. Indeed, some experiments fall outside the bounds and must be excluded from considerations. Also, experiments with dilute mixtures or with the phases having slight mismatch of the shear moduli are of little interest, as the Hashin-Shtrikman bounds are sufficiently stringent in this case. For the case of the elastic response use has been made of experiments with sintered alumina, ceramics, tungsten carbide-cobalt alloy and ClCu aggregate for a wide interval of the volume concentrations. For the case of a scalar property use has been made of the electrical conductivity data for various compounds, such as Cu Sb -Sb, Pb-Mg Pb, Sn-Bi, Bi Pb-Bi, Cd-Pb, and the thermal conductivity data for a sandstone and for a firebrick. The data have been divided to a training set and a test set. It is essential that training set has been specified so as to include samples displaying the effect at hand to its maximal degree. It appears that data dealing with concentrated mixtures c c 0.5 and possibly large mismatch of the shear moduli are most informative, as the uncertainty left over by the bounds is maximal under these conditions. Because, as the present methodology suggests, the bounds are fed in the network separately for each particular composite prior to the weight optimization process, it seems possible to adopt small training sets, which are mainly placed in the region of maximal disparity between the bounds. At the same time, it is essential that the training samples would represent a possibly large variety of microstructure in agreement with the assumption (i made in the above. The training sets first consisted of three samples and then of four samples These samples have been so chosen as to comply with the above comments concerning specification of the training sets. The weights arrived at by the gradient descent method, which has been chosen to perform the training, are given for the above three cases in Table.
4 4 Tab.. The values of weigths E k w w (GPa - (GPa - w (GPa - (GPa - w (GPa - (GPa - w (GPa - (GPa - w moduli: = 30 GPa, G = GPa, = GPa, G = Gpa. The values, which correspond to the differential scheme and to the self-consistent method, have been computed according to expressions discussed in detail in [] and [0]. Fig. presents the results for a scalar property k.for the values k = 5 and k = 00. It is observed from Figs. and that the assumption of a particular inclusion shape, which is inhereht in the above analytical investigations and absent in the neural computing, may strongly affect the evaluation of effective modulus. 3 Analysis of Results The neural computation shows good agreement with the experimental data. This is particularly true for the network trained with four samples. The generalization capability of the networks seems fairly impressive, particularly, in view of their extreme simplicity and the small training sets. Going over to comparison of the neural computation with analytical techniques such as the self-consistent scheme and the differential method, we note that even though the results associated with these techniques employ the phase concentration c as the only phase geometry parameter, their derivation essentially assumes a particular phase geometry (spherical inclusions embedded in a homogeneous matrix. On the other hand, the above neural computation is solely based on the Hashin- Shtrikman bounds and experiments which incorporate a variety of microstructures in agreement with the assumption made. Therefore any comparison between these approaches should not be taken literally. This comparison would be more meaningful if the training and test sets consist only of the samples of spherical inclusions in a purely homogeneous matrix. Presently, to the best knowledge of these authors, the available experimental data of this type are too limited to allow for such a procedure. Nevertheless, it would be of interest to appreciate the difference between these analytical models and the neural computation in case of composite with a particularly large gap between the Hashin-Shtrikman bounds. For example, Fig. shows bulk modulus and the effective modulus E as functions of the volume concentration, c, for a composite with the following values of elastic Fig.. Effective bulk modulus, (GPa, and effective Young s modulus, E (GPa vs. volume concentration c : B Hashin-Shtrikman bounds, N neural network, D differential scheme, S self-consistent method.
5 5 If, contrary to the assumption (i of Section, the inclusion shape is known, the training set should be reformulated so as to include proper samples, say, disk-like inclusions. The Hashin-Shtrikman bounds still hold, though, in general, they may be replaced by more stringent bounds because of the specific geometry involved. This would allow for incorporating the effect of inclusion shape. Fig.. Effective scalar property, k, vs. volume concentration c : B Hashin-Shtrikman bounds, N neural network, S self-consistent method. Further, since the Hashin-Shtrikman bounds do not distinguish between phases in the form of matrix or particles, in order to investigate yet another effect of which component is the matrix phase and which is the inclusion phase, one should design two networks trained on two different sets. One of these sets should contain only the samples with much stiffer matrix phase and the second with much stiffer particles phase. Unfortunately, the experimental data presently available do not seem sufficient for such investigations. The simplicity of the results obtained herein and a possibility of their extension to more complicated cases in the frameworks of the modern paradigm of neural networks seems attractive. 4 Conclusions The uncertainty typical of disordered heterogeneous materials increases in case of multiphase and incompletely specified microstructure. This further complicates their analysis by the conventional methods borrowed from boundary-value problems of mathematical physics and neural networks may serve as a useful alternative. The bounds play an essential role in the present methodology of applications of neural networks to the effective behavior of disordered composites. Since the experimental data concerning dilute mixtures and/or slight mismatch of the parameters of the microstucture bear little information compared to the bounds, they may be put aside while specifying a training set. Then the bounds are fed in the neural network separately for each particular composite as an integral part of the training. The generalization capability of the designed networks appears substantial, particularly in view of their extreme simplicity and the small training sets employed. Though the simple perceptrons show a wide variety of the effective behavior for two-phase composites, in general a more complicated network appears necessary. It seems that neural networks, which incorporate the relevant bounds and are trained on small but properly selected experimental sets, may provide a useful insight into the effective behavior of heterogeneous materials. References [] Christensen, R.M., A Critical Evaluation for a Class of Micromechanics Models, Journal of Mechanics and Physics of Solids, Vol. 38, No. 3, 990, pp [] Hale, D.., The Physical Properties of Composite Materials, Journal of Material Science, Vol., 976, pp [3] Hashin, Z., Analysis of Composite Materials - A Survey, Journal of Applied Mechanics, Vol. 50, 983, pp [4] Willis, J.R., Variational and Related Methods for the Overall Properties of Composites. Advances in Applied Mechanics, Vol., 98, pp [5] Beltzer, A.I., The Effective Dynamic Response of Random Composites and Polycrystals - A Survey of the Causal Approach, Wave Motion, Vol., 989, pp. -9. [6] Nemat-Nasser, S., Hori, M., Micromechanics: overall properties of heterogeneous materials, North-Holland, Amsterdam, 993.
6 [7] Beltzer, A.I., Sato, T., A Neural Network Approach to Effective Response of Heterogeneous Materials, in: Proceedings of the International Conference Mesomechanics 98, Tel Aviv, 998, p. 38. [8] Gotlib V.A., Sato T., Beltzer A.I., Neural Computations of Effective Response of Random Composites, International Journal of Solids and Structures, Vol. 37, 000, pp [9] Gotlib V.A., Sato T., Beltzer A.I., Neural Computing of Effective Properties of Random Composite Materials, Computers and Structures, Vol. 79, No., 000, pp. -6. [0] Zimmerman, R.W., Elastic Moduli of a Solid Containing Spherical Inclusions, Mechanics of Materials, Vol., 99, pp
Module 7: Micromechanics Lecture 29: Background of Concentric Cylinder Assemblage Model. Introduction. The Lecture Contains
Introduction In this lecture we are going to introduce a new micromechanics model to determine the fibrous composite effective properties in terms of properties of its individual phases. In this model
More informationAnalysis of high loss viscoelastic composites
Analysis of high loss viscoelastic composites by C. P. Chen, Ph.D. and R. S. Lakes, Ph.D. Department of Engineering Physics Engineering Mechanics Program; Biomedical Engineering Department Materials Science
More informationEVALUATION OF EFFECTIVE MECHANICAL PROPERTIES OF COMPLEX MULTIPHASE MATERIALS WITH FINITE ELEMENT METHOD
U.P.B. Sci. Bull., Series D, Vol. 79, Iss. 3, 2017 ISSN 1454-2358 EVALUATION OF EFFECTIVE MECHANICAL PROPERTIES OF COMPLEX MULTIPHASE MATERIALS WITH FINITE ELEMENT METHOD Mohamed said BOUTAANI 1, Salah
More informationMICROSTRUCTURAL AND ELASTIC PROPERTIES OF SHORT FIBER REINFORCED COMPOSITES
MICROTRUCTURAL AND ELATIC PROPERTIE OF HORT FIBER REINFORCED COMPOITE V. Müller 1, T. Böhlke 1 1 Institute of Engineering Mechanics, Chair for Continuum Mechanics, Karlsruhe Institute of Technology (KIT)
More informationEffective medium theory for elastic composites
Effective medium theory for elastic composites James G. Berryman ABSTRACT The theoretical foundation of a variant on effective medium theories for elastic constants of composites is presented discussed.
More informationA GENERALIZED CROSS-PROPERTY RELATION BETWEEN THE ELASTIC MODULI AND CONDUCTIVITY OF ISOTROPIC POROUS MATERIALS WITH SPHEROIDAL PORES
journal webpage: www.ceramics-silikaty.cz Ceramics-Silikáty 61 (1, 74-80 (017 doi: 10.13168/cs.016.0063 A GENERALIZED CROSS-PROPERTY RELATION BETWEEN THE ELASTIC MODULI AND CONDUCTIVITY OF ISOTROPIC POROUS
More informationMcMAT 2007 Micromechanics of Materials Austin, Texas, June 3 7, 2007
McMAT 2007 Micromechanics of Materials Austin, Texas, June 3 7, 2007 RANDOM POLYCRYSTALS OF GRAINS WITH CRACKS: MODEL OF ELASTIC BEHAVIOR FOR FRACTURED SYSTEMS James G. Berryman Earth Sciences Division
More informationChapter 5. Effects of Photonic Crystal Band Gap on Rotation and Deformation of Hollow Te Rods in Triangular Lattice
Chapter 5 Effects of Photonic Crystal Band Gap on Rotation and Deformation of Hollow Te Rods in Triangular Lattice In chapter 3 and 4, we have demonstrated that the deformed rods, rotational rods and perturbation
More informationHomogenization methods for multi-phase elastic composites: Comparisons and benchmarks
TECHNISCHE MECHANIK, 3, 4, (), 374 386 submitted: October 6, 9 Homogenization methods for multi-phase elastic composites: Comparisons and benchmarks B. Klusemann, B. Svendsen Usually homogenization methods
More informationNumerical evaluation of effective material properties of randomly distributed short cylindrical fibre composites
Computational Materials Science 39 (2007) 198 204 www.elsevier.com/locate/commatsci Numerical evaluation of effective material properties of randomly distributed short cylindrical fibre composites S. Kari
More informationMATERIAL MECHANICS, SE2126 COMPUTER LAB 4 MICRO MECHANICS. E E v E E E E E v E E + + = m f f. f f
MATRIAL MCHANICS, S226 COMPUTR LAB 4 MICRO MCHANICS 2 2 2 f m f f m T m f m f f m v v + + = + PART A SPHRICAL PARTICL INCLUSION Consider a solid granular material, a so called particle composite, shown
More informationME 7502 Lecture 2 Effective Properties of Particulate and Unidirectional Composites
ME 75 Lecture Effective Properties of Particulate and Unidirectional Composites Concepts from Elasticit Theor Statistical Homogeneit, Representative Volume Element, Composite Material Effective Stress-
More informationApparent thermal conductivity of periodic two-dimensional composites
Computational Materials Science 25 (2002) 329 338 www.elsevier.com/locate/commatsci Apparent thermal conductivity of periodic two-dimensional composites M. Jiang a, I. Jasiuk b, *, M. Ostoja-Starzewski
More informationXI. NANOMECHANICS OF GRAPHENE
XI. NANOMECHANICS OF GRAPHENE Carbon is an element of extraordinary properties. The carbon-carbon bond possesses large magnitude cohesive strength through its covalent bonds. Elemental carbon appears in
More informationRoberta Sburlati. Department of Civil, Chemical and Environmental Engineering (DICCA) University of Genova, Via Montallegro 1, Genova, Italy
Effect of graded interphase on the coefficient of thermal expansion for composites with spherical inclusions Roberta Sburlati Department of Civil, Chemical and Environmental Engineering (DICCA University
More informationBounding of effective thermal conductivities of multiscale materials by essential and natural boundary conditions
PHYSICAL REVIEW B VOLUME 54, NUMBER 1 1 JULY 1996-I Bounding of effective thermal conductivities of multiscale materials by essential and natural boundary conditions M. Ostoja-Starzewski Institute of Paper
More informationNeural Networks. Nicholas Ruozzi University of Texas at Dallas
Neural Networks Nicholas Ruozzi University of Texas at Dallas Handwritten Digit Recognition Given a collection of handwritten digits and their corresponding labels, we d like to be able to correctly classify
More informationPattern Recognition Prof. P. S. Sastry Department of Electronics and Communication Engineering Indian Institute of Science, Bangalore
Pattern Recognition Prof. P. S. Sastry Department of Electronics and Communication Engineering Indian Institute of Science, Bangalore Lecture - 27 Multilayer Feedforward Neural networks with Sigmoidal
More informationViscoelastic Damping Characteristics of Indium-Tin/SiC Particulate Composites
Viscoelastic Damping Characteristics of Indium-Tin/SiC Particulate Composites HyungJoo Kim, Colby C. Swan Ctr. for Computer-Aided Design, Univ. of Iowa Roderic Lakes Engineering Physics, Univ. of Wisconsin
More informationNeural Networks and the Back-propagation Algorithm
Neural Networks and the Back-propagation Algorithm Francisco S. Melo In these notes, we provide a brief overview of the main concepts concerning neural networks and the back-propagation algorithm. We closely
More informationAnalysis of contact deformation between a coated flat plate and a sphere and its practical application
Computer Methods and Experimental Measurements for Surface Effects and Contact Mechanics VII 307 Analysis of contact deformation between a coated flat plate and a sphere and its practical application T.
More informationSupporting Information. Potential semiconducting and superconducting metastable Si 3 C. structures under pressure
Supporting Information Potential semiconducting and superconducting metastable Si 3 C structures under pressure Guoying Gao 1,3,* Xiaowei Liang, 1 Neil W. Ashcroft 2 and Roald Hoffmann 3,* 1 State Key
More informationIntroduction to Neural Networks
CUONG TUAN NGUYEN SEIJI HOTTA MASAKI NAKAGAWA Tokyo University of Agriculture and Technology Copyright by Nguyen, Hotta and Nakagawa 1 Pattern classification Which category of an input? Example: Character
More informationMathematics and Mechanics of Solids. A systematic study on homogenization and the utility of circular simplified RVE
athematics and echanics of Solids A systematic study on homogenization and the utility of circular simplified RVE Journal: athematics and echanics of Solids anuscript ID S--0 anuscript Type: Original anuscript
More informationSeismic velocity decrement ratios for regions of partial melt near the core-mantle boundary
Stanford Exploration Project, Report 02, October 25, 999, pages 87 20 Seismic velocity decrement ratios for regions of partial melt near the core-mantle boundary James G. Berryman keywords: poroelasticity,
More informationContinuum Modeling Techniques to Determine Mechanical Properties of Nanocomposites
International OPEN ACCESS Journal Of Modern Engineering Research (IJMER) Continuum Modeling Techniques to Determine Mechanical Properties of Nanocomposites Sonali Gholap 1, Dr. Dhananjay R. Panchagade
More informationAN INTRODUCTION TO NEURAL NETWORKS. Scott Kuindersma November 12, 2009
AN INTRODUCTION TO NEURAL NETWORKS Scott Kuindersma November 12, 2009 SUPERVISED LEARNING We are given some training data: We must learn a function If y is discrete, we call it classification If it is
More informationin materials/structural modellings and designs Liping Liu
Closed-form solutions and their applications in materials/structural modellings and designs Liping Liu University it of Houston Why composites and heterogeneous structures? A material has many different
More informationModified Maxwell-Garnett equation for the effective transport coefficients in inhomogeneous media
J. Phys. A: Math. Gen. 3 (998) 7227 7234. Printed in the UK PII: S0305-4470(98)93976-2 Modified Maxwell-Garnett equation for the effective transport coefficients in inhomogeneous media Juris Robert Kalnin
More informationVariational Asymptotic Method for Unit Cell Homogenization
Variational Asymptotic Method for Unit Cell Homogenization Wenbin Yu 1 and Tian Tang 2 1 Utah State University, Logan, Utah 84322-4130 Wenbin.Yu@usu.edu 2 Utah State University, Logan, Utah 84322-4130
More informationInternational Journal of Engineering Science
International Journal of Engineering Science 63 (2013) 1 9 Contents lists available at SciVerse ScienceDirect International Journal of Engineering Science journal homepage: www.elsevier.com/locate/ijengsci
More informationMachine Learning (CSE 446): Neural Networks
Machine Learning (CSE 446): Neural Networks Noah Smith c 2017 University of Washington nasmith@cs.washington.edu November 6, 2017 1 / 22 Admin No Wednesday office hours for Noah; no lecture Friday. 2 /
More informationMultilayer Neural Networks
Multilayer Neural Networks Multilayer Neural Networks Discriminant function flexibility NON-Linear But with sets of linear parameters at each layer Provably general function approximators for sufficient
More informationSTANDARD SAMPLE. Reduced section " Diameter. Diameter. 2" Gauge length. Radius
MATERIAL PROPERTIES TENSILE MEASUREMENT F l l 0 A 0 F STANDARD SAMPLE Reduced section 2 " 1 4 0.505" Diameter 3 4 " Diameter 2" Gauge length 3 8 " Radius TYPICAL APPARATUS Load cell Extensometer Specimen
More informationFHWA/IN/JTRP-97/4- o \ Final Report STRENGTH AND DURABILITY OF CONCRETE: EFFECTS OF CEMENT PASTE-AGGREGATE INTERFACES PARTI
Joint Transportation Research Program FHWA/IN/JTRP-97/4- o \ Final Report STRENGTH AND DURABILITY OF CONCRETE: EFFECTS OF CEMENT PASTE-AGGREGATE INTERFACES PARTI THEORETICAL STUDY ON INFLUENCE OF INTERFACIAL
More informationCellular solid structures with unbounded thermal expansion. Roderic Lakes. Journal of Materials Science Letters, 15, (1996).
1 Cellular solid structures with unbounded thermal expansion Roderic Lakes Journal of Materials Science Letters, 15, 475-477 (1996). Abstract Material microstructures are presented which can exhibit coefficients
More informationPorosity dependence of Elastic Modulii for Ceramic Materials
ISSN 394 3386 Volume 4, Issue 1 December 017 Porosity dependence of Elastic Modulii for Ceramic Materials R. K. Sharma a *, A.K.Upadhyay b & S. B. Sharma c a Department of Physics, B.S.A. College of Engg.
More informationSimple neuron model Components of simple neuron
Outline 1. Simple neuron model 2. Components of artificial neural networks 3. Common activation functions 4. MATLAB representation of neural network. Single neuron model Simple neuron model Components
More informationENTROPY OF MELTING AND STRUCTURAL CONDITION OF A MELT 12,, S. PROKHORENKO 2 V. PROKHORENKO. Rzeszów University, Poland Rzeszów 2
22/6 ARCHIWUM ODLEWNICTWA Rok 2002, Rocznik 2, Nr 6 Archives of Foundry Year 2002, Volume 2, Book 6 PAN - Katowice PL ISSN 1642-5308 ENTROPY OF MELTING AND STRUCTURAL CONDITION OF A MELT V. PROKHORENKO
More informationCHAPTER 4 MODELING OF MECHANICAL PROPERTIES OF POLYMER COMPOSITES
CHAPTER 4 MODELING OF MECHANICAL PROPERTIES OF POLYMER COMPOSITES 4. Introduction Fillers added to polymer matrices as additives are generally intended for decreasing the cost (by increase in bulk) of
More informationApplication of Artificial Neural Networks in Evaluation and Identification of Electrical Loss in Transformers According to the Energy Consumption
Application of Artificial Neural Networks in Evaluation and Identification of Electrical Loss in Transformers According to the Energy Consumption ANDRÉ NUNES DE SOUZA, JOSÉ ALFREDO C. ULSON, IVAN NUNES
More informationA micromechanical model for effective elastic properties of particulate composites with imperfect interfacial bonds
International Journal of Solids and Structures 42 (2005) 4179 4191 www.elsevier.com/locate/ijsolstr A micromechanical model for effective elastic properties of particulate composites with imperfect interfacial
More informationMechanics of Materials and Structures
Journal of Mechanics of Materials and Structures A VARIATIONAL ASYMPTOTIC MICROMECHANICS MODEL FOR PREDICTING CONDUCTIVITIES OF COMPOSITE MATERIALS Tian Tang and Wenbin Yu Volume, Nº 9 November 007 mathematical
More informationComposite materials: mechanical properties
Composite materials: mechanical properties A computational lattice model describing scale effects @ nano-scale Luciano Colombo In collaboration with: Pier Luca Palla and Stefano Giordano Department of
More informationTHE ROCK PHYSICS HANDBOOK
THE ROCK PHYSICS HANDBOOK TOOLS FOR SEISMIC ANALYSIS IN POROUS MEDIA Gary Mavko Tapan Mukerji Jack Dvorkin Stanford University Stanford University Stanford University CAMBRIDGE UNIVERSITY PRESS CONTENTS
More informationStatistical continuum mechanics analysis of an elastic two-isotropic-phase composite material
Composites: Part B 31 (2000) 39 46 www.elsevier.com/locate/compositesb Statistical continuum mechanics analysis of an elastic two-isotropic-phase composite material S. Lin, H. Garmestani* Mechanical Engineering
More informationIntroduction to Machine Learning Spring 2018 Note Neural Networks
CS 189 Introduction to Machine Learning Spring 2018 Note 14 1 Neural Networks Neural networks are a class of compositional function approximators. They come in a variety of shapes and sizes. In this class,
More informationFig. 1. Circular fiber and interphase between the fiber and the matrix.
Finite element unit cell model based on ABAQUS for fiber reinforced composites Tian Tang Composites Manufacturing & Simulation Center, Purdue University West Lafayette, IN 47906 1. Problem Statement In
More informationArtificial Neural Networks
Introduction ANN in Action Final Observations Application: Poverty Detection Artificial Neural Networks Alvaro J. Riascos Villegas University of los Andes and Quantil July 6 2018 Artificial Neural Networks
More informationSPSS, University of Texas at Arlington. Topics in Machine Learning-EE 5359 Neural Networks
Topics in Machine Learning-EE 5359 Neural Networks 1 The Perceptron Output: A perceptron is a function that maps D-dimensional vectors to real numbers. For notational convenience, we add a zero-th dimension
More informationNeural Networks and Ensemble Methods for Classification
Neural Networks and Ensemble Methods for Classification NEURAL NETWORKS 2 Neural Networks A neural network is a set of connected input/output units (neurons) where each connection has a weight associated
More informationCSC321 Lecture 5: Multilayer Perceptrons
CSC321 Lecture 5: Multilayer Perceptrons Roger Grosse Roger Grosse CSC321 Lecture 5: Multilayer Perceptrons 1 / 21 Overview Recall the simple neuron-like unit: y output output bias i'th weight w 1 w2 w3
More informationFinite Element of Composite Materials with Partial Debonding along Boundary. Kohei HIGUCHI, Tetsuo IWAKUMA
Vol. 8 (2005 8 ) Finite Element of Composite aterials with Partial Debonding along Boundary Kohei HIGUCHI, Tetsuo IWAKUA JFE PhD 980-8579 6-6-06 Damages in composite materials are mostly governed by interfacial
More informationHomogenization of Cemented Soil Stiffness and Application to the Study of Arching Effects between
Title: Homogenization of Cemented Soil Stiffness and Application to the Study of Arching Effects between Jet-Grouted Columns Authors: Chloé ARSON, Assistant Professor, School of Civil and Environmental
More informationA Constitutive Framework for the Numerical Analysis of Organic Soils and Directionally Dependent Materials
Dublin, October 2010 A Constitutive Framework for the Numerical Analysis of Organic Soils and Directionally Dependent Materials FracMan Technology Group Dr Mark Cottrell Presentation Outline Some Physical
More informationPHASE VELOCITY AND ATTENUATION OF SH WAVES IN A FIBER-
PHASE VELOCITY AND ATTENUATION OF SH WAVES IN A FIBER- REINFORCED COMPOSITE Ruey-Bin Yang and Ajit K. Mal Department of Mechanical, Aerospace and Nuclear Engineering University of California, Los Angeles,
More informationModule 7: Micromechanics Lecture 34: Self Consistent, Mori -Tanaka and Halpin -Tsai Models. Introduction. The Lecture Contains. Self Consistent Method
Introduction In this lecture we will introduce some more micromechanical methods to predict the effective properties of the composite. Here we will introduce expressions for the effective properties without
More informationAn Exact Result for the Macroscopic Response of Particle-Reinforced Neo-Hookean Solids
Oscar Lopez-Pamies Department of Mechanical Engineering, State University of New York, Stony Brook, NY 9- e-mail: oscar.lopez-pamies@sunysb.edu An Exact Result for the Macroscopic Response of Particle-Reinforced
More informationOpen-hole compressive strength prediction of CFRP composite laminates
Open-hole compressive strength prediction of CFRP composite laminates O. İnal 1, A. Ataş 2,* 1 Department of Mechanical Engineering, Balikesir University, Balikesir, 10145, Turkey, inal@balikesir.edu.tr
More informationMicrostructural Randomness and Scaling in Mechanics of Materials. Martin Ostoja-Starzewski. University of Illinois at Urbana-Champaign
Microstructural Randomness and Scaling in Mechanics of Materials Martin Ostoja-Starzewski University of Illinois at Urbana-Champaign Contents Preface ix 1. Randomness versus determinism ix 2. Randomness
More informationReading Group on Deep Learning Session 1
Reading Group on Deep Learning Session 1 Stephane Lathuiliere & Pablo Mesejo 2 June 2016 1/31 Contents Introduction to Artificial Neural Networks to understand, and to be able to efficiently use, the popular
More informationLearning from Data: Multi-layer Perceptrons
Learning from Data: Multi-layer Perceptrons Amos Storkey, School of Informatics University of Edinburgh Semester, 24 LfD 24 Layered Neural Networks Background Single Neurons Relationship to logistic regression.
More informationEnhancement of magnetoelectric coupling in multiferroic composites via FEM simulation
Enhancement of magnetoelectric coupling in multiferroic composites via FEM simulation *Artjom Avakian 1), Andreas Ricoeur 2) 1), 2) Institute of Mechanics, University of Kassel, Kassel 34125, Germany 1)
More informationPattern Classification
Pattern Classification All materials in these slides were taen from Pattern Classification (2nd ed) by R. O. Duda,, P. E. Hart and D. G. Stor, John Wiley & Sons, 2000 with the permission of the authors
More informationData Mining Part 5. Prediction
Data Mining Part 5. Prediction 5.5. Spring 2010 Instructor: Dr. Masoud Yaghini Outline How the Brain Works Artificial Neural Networks Simple Computing Elements Feed-Forward Networks Perceptrons (Single-layer,
More informationMultilayer Neural Networks
Multilayer Neural Networks Introduction Goal: Classify objects by learning nonlinearity There are many problems for which linear discriminants are insufficient for minimum error In previous methods, the
More informationLECTURE # - NEURAL COMPUTATION, Feb 04, Linear Regression. x 1 θ 1 output... θ M x M. Assumes a functional form
LECTURE # - EURAL COPUTATIO, Feb 4, 4 Linear Regression Assumes a functional form f (, θ) = θ θ θ K θ (Eq) where = (,, ) are the attributes and θ = (θ, θ, θ ) are the function parameters Eample: f (, θ)
More informationIntroduction Neural Networks - Architecture Network Training Small Example - ZIP Codes Summary. Neural Networks - I. Henrik I Christensen
Neural Networks - I Henrik I Christensen Robotics & Intelligent Machines @ GT Georgia Institute of Technology, Atlanta, GA 30332-0280 hic@cc.gatech.edu Henrik I Christensen (RIM@GT) Neural Networks 1 /
More informationJuan E. Santos a,b,c, Gabriela B. Savioli a and Robiel Martínez Corredor c a
Juan E. Santos a,b,c, Gabriela B. Savioli a and Robiel Martínez Corredor c a Universidad de Buenos Aires, Fac. Ing., IGPUBA, ARGENTINA b Department of Mathematics, Purdue University, USA c Universidad
More informationFeedforward Neural Nets and Backpropagation
Feedforward Neural Nets and Backpropagation Julie Nutini University of British Columbia MLRG September 28 th, 2016 1 / 23 Supervised Learning Roadmap Supervised Learning: Assume that we are given the features
More informationThree-dimensional thermoelastic deformations of a functionally graded elliptic plate
JCOMB Composites: Part B () 9 6 www.elsevier.com/locate/compositesb Three-dimensional thermoelastic deformations of a functionally graded elliptic plate Z.-Q. Cheng a, R.C. Batra b, * a Department of Modern
More informationA direct evaluation of the Fabric Tensor in anisotropic porous media
A direct evaluation of the Fabric Tensor in anisotropic porous media Maria Cristina Pernice 1, Luciano Nunziante 1, Massimiliano Fraldi 1,2 1 Department of Structural Engineering, University of Naples
More informationReification of Boolean Logic
526 U1180 neural networks 1 Chapter 1 Reification of Boolean Logic The modern era of neural networks began with the pioneer work of McCulloch and Pitts (1943). McCulloch was a psychiatrist and neuroanatomist;
More informationFLEXURAL AND TORSIONAL RESONANCES OF CERAMIC TILES VIA IMPULSE EXCITATION OF VIBRATION
FLEXURAL AND TORSIONAL RESONANCES OF CERAMIC TILES VIA IMPULSE EXCITATION OF VIBRATION A. A. Wereszczak,' R. H. Kraft? and J. J. Swab Metals and Ceramics Research Branch U. S. Army Research Laboratory
More informationA multiscale approach for composite materials as multifield continua
Materials Science Forum Vols. 539-543 (27) pp. 2551-2556 online at http://www.scientific.net (27) Trans Tech Publications, Switzerland A multiscale approach for composite materials as multifield continua
More informationArtifical Neural Networks
Neural Networks Artifical Neural Networks Neural Networks Biological Neural Networks.................................. Artificial Neural Networks................................... 3 ANN Structure...........................................
More informationPracticals 5 : Perceptron
Université Paul Sabatier M2 SE Data Mining Practicals 5 : Perceptron Framework The aim of this last session is to introduce the basics of neural networks theory through the special case of the perceptron.
More informationVelocity porosity relationships: Predictive velocity model for cemented sands composed of multiple mineral phases
Geophysical Prospecting,,, 9 7 Velocity porosity relationships: Predictive velocity model for cemented sands composed of multiple mineral phases Mark A. Knackstedt,, Christoph H. Arns and W. Val Pinczewski
More informationCSE 352 (AI) LECTURE NOTES Professor Anita Wasilewska. NEURAL NETWORKS Learning
CSE 352 (AI) LECTURE NOTES Professor Anita Wasilewska NEURAL NETWORKS Learning Neural Networks Classifier Short Presentation INPUT: classification data, i.e. it contains an classification (class) attribute.
More informationPREDICTION THE JOMINY CURVES BY MEANS OF NEURAL NETWORKS
Tomislav Filetin, Dubravko Majetić, Irena Žmak Faculty of Mechanical Engineering and Naval Architecture, University of Zagreb, Croatia PREDICTION THE JOMINY CURVES BY MEANS OF NEURAL NETWORKS ABSTRACT:
More informationELECTROMAGNETIC-RESONANCE-ULTRASOUND MICROSCOPY (ERUM) FOR QUANTITATIVE EVALUATION OF LOCALIZED ELASTIC CONSTANTS OF SOLIDS
ELECTROMAGNETIC-RESONANCE-ULTRASOUND MICROSCOPY (ERUM) FOR QUANTITATIVE EVALUATION OF LOCALIZED ELASTIC CONSTANTS OF SOLIDS J. Tian, H.Ogi, T. Tada and M. Hirao Graduate School of Engineering Science,
More informationDesign of porous phononic crystals with combined band gaps
Design of porous phononic crystals with combined band gaps Y.F. Li¹, X.Huang, and S. Zhou Centre for Innovative Structures and Materials, School of Engineering, RMIT University, Australia Presenting author:
More informationA differential scheme for elastic properties of rocks with dry or saturated cracks
Geophys. J. Int. (2002, 597 6 A differential scheme for elastic properties of rocks with dry or saturated cracks James G. Berryman, Steven R. Pride 2 and Herbert F. Wang 3 University of California, Lawrence
More informationDeep Learning & Artificial Intelligence WS 2018/2019
Deep Learning & Artificial Intelligence WS 2018/2019 Linear Regression Model Model Error Function: Squared Error Has no special meaning except it makes gradients look nicer Prediction Ground truth / target
More informationStiffness Predictions for Unidirectional Short-Fiber Composites: Review and Evaluation
Stiffness Predictions for Unidirectional Short-Fiber Composites: Review and Evaluation Charles L. Tucker III Department of Mechanical and Industrial Engineering University of Illinois at Urbana-Champaign
More informationCMSC 421: Neural Computation. Applications of Neural Networks
CMSC 42: Neural Computation definition synonyms neural networks artificial neural networks neural modeling connectionist models parallel distributed processing AI perspective Applications of Neural Networks
More informationA Logarithmic Neural Network Architecture for Unbounded Non-Linear Function Approximation
1 Introduction A Logarithmic Neural Network Architecture for Unbounded Non-Linear Function Approximation J Wesley Hines Nuclear Engineering Department The University of Tennessee Knoxville, Tennessee,
More informationPredicting Elastic Properties of Unidirectional SU8/ZnO Nanocomposites using COMSOL Multiphysics
Predicting Elastic Properties of Unidirectional SU8/ZnO Nanocomposites using COMSOL Multiphysics Neelam Mishra 1, and Kaushik Das *1 1 School of Minerals Metallurgical and Materials Engineering, Indian
More informationVariational bounds for anisotropic elastic multiphase composites with different shapes of inclusions
Arch Appl Mech DOI 1.17/s419-8-246-1 ORIGINAL R. Rodríguez-Ramos R. Guinovart-Díaz J. Bravo-Castillero F. J. Sabina H. Berger S. Kari U. Gabbert Variational bounds for anisotropic elastic multiphase composites
More informationIntegral equations for crack systems in a slightly heterogeneous elastic medium
Boundary Elements and Other Mesh Reduction Methods XXXII 65 Integral equations for crack systems in a slightly heterogeneous elastic medium A. N. Galybin & S. M. Aizikovich Wessex Institute of Technology,
More informationVelocity-porosity relationships, 1: Accurate velocity model for clean consolidated sandstones
GEOPHYSICS, VOL. 68, NO. 6 (NOVEMBER-DECEMBER 2003); P. 1822 1834, 16 FIGS., 1 TABLE. 10.1190/1.1635035 Velocity-porosity relationships, 1: Accurate velocity model for clean consolidated sandstones Mark
More information4. Multilayer Perceptrons
4. Multilayer Perceptrons This is a supervised error-correction learning algorithm. 1 4.1 Introduction A multilayer feedforward network consists of an input layer, one or more hidden layers, and an output
More informationA simple plane-strain solution for functionally graded multilayered isotropic cylinders
Structural Engineering and Mechanics, Vol. 24, o. 6 (2006) 000-000 1 A simple plane-strain solution for functionally graded multilayered isotropic cylinders E. Pan Department of Civil Engineering, The
More informationFUNDAMENTAL CONCEPTS IN MEASUREMENT & EXPERIMENTATION
FUNDAMENTAL CONCEPTS IN MEASUREMENT & EXPERIMENTATION What is Measurement? In general, it is the acquisition of information. Classification of information leads to two different types of measurements:
More informationNeural Networks, Computation Graphs. CMSC 470 Marine Carpuat
Neural Networks, Computation Graphs CMSC 470 Marine Carpuat Binary Classification with a Multi-layer Perceptron φ A = 1 φ site = 1 φ located = 1 φ Maizuru = 1 φ, = 2 φ in = 1 φ Kyoto = 1 φ priest = 0 φ
More informationFigure 1. P wave speed, Vp, S wave speed, Vs, and density, ρ, for the different layers of Ostrander s gas sand model shown in SI units.
Ambiguity in Resolving the Elastic Parameters of Gas Sands from Wide-Angle AVO Andrew J. Calvert - Simon Fraser University and David F. Aldridge - Sandia National Laboratories Summary We investigate the
More informationStatistical Machine Learning from Data
January 17, 2006 Samy Bengio Statistical Machine Learning from Data 1 Statistical Machine Learning from Data Other Artificial Neural Networks Samy Bengio IDIAP Research Institute, Martigny, Switzerland,
More informationLawrence Berkeley National Laboratory
Lawrence Berkeley National Laboratory Peer Reviewed Title: Fracture permeability and seismic wave scattering--poroelastic linear-slip interface model for heterogeneous fractures Author: Nakagawa, S. Publication
More informationChapter 9: The Perceptron
Chapter 9: The Perceptron 9.1 INTRODUCTION At this point in the book, we have completed all of the exercises that we are going to do with the James program. These exercises have shown that distributed
More informationComputational Analysis for Composites
Computational Analysis for Composites Professor Johann Sienz and Dr. Tony Murmu Swansea University July, 011 The topics covered include: OUTLINE Overview of composites and their applications Micromechanics
More information