Atjaunināt sīkdatņu piekrišanu

E-grāmata: Soft Computing in Engineering

(University of Illinois at Urbana-Champaign, USA)
  • Formāts: 220 pages
  • Izdošanas datums: 11-May-2018
  • Izdevniecība: CRC Press Inc
  • ISBN-13: 9780429892820
Citas grāmatas par šo tēmu:
  • Formāts - EPUB+DRM
  • Cena: 57,60 €*
  • * ši ir gala cena, t.i., netiek piemērotas nekādas papildus atlaides
  • Ielikt grozā
  • Pievienot vēlmju sarakstam
  • Šī e-grāmata paredzēta tikai personīgai lietošanai. E-grāmatas nav iespējams atgriezt un nauda par iegādātajām e-grāmatām netiek atmaksāta.
Soft Computing in EngineeringPalielināt
  • Formāts: 220 pages
  • Izdošanas datums: 11-May-2018
  • Izdevniecība: CRC Press Inc
  • ISBN-13: 9780429892820
Citas grāmatas par šo tēmu:

DRM restrictions

  • Kopēšana (kopēt/ievietot):

    nav atļauts

  • Drukāšana:

    nav atļauts

  • Lietošana:

    Digitālo tiesību pārvaldība (Digital Rights Management (DRM))
    Izdevējs ir piegādājis šo grāmatu šifrētā veidā, kas nozīmē, ka jums ir jāinstalē bezmaksas programmatūra, lai to atbloķētu un lasītu. Lai lasītu šo e-grāmatu, jums ir jāizveido Adobe ID. Vairāk informācijas šeit. E-grāmatu var lasīt un lejupielādēt līdz 6 ierīcēm (vienam lietotājam ar vienu un to pašu Adobe ID).

    Nepieciešamā programmatūra
    Lai lasītu šo e-grāmatu mobilajā ierīcē (tālrunī vai planšetdatorā), jums būs jāinstalē šī bezmaksas lietotne: PocketBook Reader (iOS / Android)

    Lai lejupielādētu un lasītu šo e-grāmatu datorā vai Mac datorā, jums ir nepieciešamid Adobe Digital Editions (šī ir bezmaksas lietotne, kas īpaši izstrādāta e-grāmatām. Tā nav tas pats, kas Adobe Reader, kas, iespējams, jau ir jūsu datorā.)

    Jūs nevarat lasīt šo e-grāmatu, izmantojot Amazon Kindle.

Soft computing methods such as neural networks and genetic algorithms draw on the problem solving strategies of the natural world which differ fundamentally from the mathematically-based computing methods normally used in engineering. Human brains are highly effective computers with capabilities far beyond those of the most sophisticated electronic computers. The 'soft computing‘ methods they use can solve very difficult inverse problems based on reduction in disorder.

This book outlines these methods and applies them to a range of difficult engineering problems, including applications in computational mechanics, earthquake engineering, and engineering design. Most of these are difficult inverse problems – especially in engineering design – and are treated in depth.

Preface xi
Author xv
1 Soft computing
1(12)
1.1 Introduction
1(1)
1.2 Hard computing and soft computing methods
2(2)
1.3 Mathematically based engineering problem-solving methodology
4(1)
1.4 Problem-solving in nature
5(2)
1.5 Direct and inverse engineering problems
7(4)
1.6 Order and reduction in disorder
11(1)
1.7 Summary and discussion
11(2)
2 Neural networks
13(30)
2.1 Introduction
13(1)
2.2 Artificial neurons
13(4)
2.3 General remarks on neural networks
17(3)
2.3.1 Connecting artificial neurons in a neural network
18(2)
2.4 Perceptrons
20(4)
2.4.1 Linearly separable classification problems
21(1)
2.4.2 Nonlinearly separable classification problems
22(2)
2.5 Multilayer feedforward neural networks
24(3)
2.5.1 A Notation for multilayer feedforward neural networks
26(1)
2.6 Training of multilayer feedforward neural networks
27(7)
2.6.1 Supervised learning
27(1)
2.6.2 Backpropagation
28(2)
2.6.3 Discussion of backpropagation
30(1)
2.6.3.1 Updating of connection weights
30(2)
2.6.4 Training and retraining
32(2)
2.7 How many hidden layers?
34(1)
2.8 Adaptive neural network architecture
34(2)
2.9 Overtraining of neural networks
36(3)
2.10 Neural networks as dynamical systems; Hopfield nets
39(2)
2.11 Discussion
41(2)
3 Neural networks in computational mechanics
43(30)
3.1 Introduction
43(1)
3.2 Neural networks in modeling constitutive behavior of material
44(1)
3.3 Nested structure in engineering data
45(7)
3.3.1 Introduction
45(1)
3.3.2 Nested structure in training data
45(2)
3.3.3 Nested structure in constitutive behavior of materials
47(5)
3.4 Nested adaptive neural networks
52(2)
3.5 Path dependence and hysteresis in constitutive behavior of materials
54(2)
3.6 Case studies of application of nested adaptive neural networks in material modeling
56(8)
3.6.1 Uniaxial cyclic behavior of plain concrete
56(3)
3.6.2 Constitutive model of sand in triaxial state
59(5)
3.7 Modeling of hysteretic behavior of materials
64(1)
3.8 Acquisition of training data for neural network material models
65(2)
3.9 Nonlinear finite-element analysis with neural networks constitutive models
67(4)
3.10 Transition from mathematical models to information contained in data
71(2)
4 Inverse problems in engineering
73(30)
4.1 Forward and inverse problems
73(1)
4.2 Inverse problems in engineering
73(2)
4.3 Inverse problems in nature
75(2)
4.4 Neural networks in forward and inverse problems
77(1)
4.5 Illustrative example
78(7)
4.6 Role of precision, universality, and uniqueness
85(1)
4.6.1 Learning
85(1)
4.6.2 Learning from forward problems
85(1)
4.6.3 Learning from a set of forward problems
86(1)
4.7 Universal and locally admissible solutions
86(2)
4.8 Inverse problem of generating artificial earthquake accelerograms
88(8)
4.8.1 Preliminaries
88(1)
4.8.2 Problem definition
89(1)
4.8.3 Neural network approach
90(4)
4.8.4 Discussion
94(2)
4.9 Emulator neural networks and neurocontrollers
96(5)
4.10 Summary and discussion
101(2)
5 Autoprogressive algorithm and self-learning simulation
103(34)
5.1 Neural network models of components of a system
103(1)
5.2 Autoprogressive algorithm
104(3)
5.3 Autoprogressive algorithm in computational mechanics
107(6)
5.3.1 Neural network constitutive models of material behavior
107(1)
5.3.2 Training of neural network material models from structural tests
108(2)
5.3.2.1 FEA1
110(1)
5.3.2.2 FEA2
111(1)
5.3.2.3 Retraining phase of the autoprogressive algorithm
112(1)
5.3.2.4 Convergence of iterations
113(1)
5.3.2.5 Multiple load passes
113(1)
5.4 Illustrative example
113(5)
5.5 Autoprogressive algorithm applied to composite materials
118(4)
5.5.1 Laminated composite materials
118(1)
5.5.2 Test setup and specimen
119(1)
5.5.3 Finite-element model of the specimen
119(2)
5.5.4 Elastic pretraining
121(1)
5.5.5 Autoprogressive algorithm training
121(1)
5.6 Nonuniform material tests in geomechanics
122(5)
5.7 Autoprogressive training of rate-dependent material behavior
127(4)
5.8 Autoprogressive algorithm in biomedicine
131(1)
5.9 Modeling components of structural systems
132(1)
5.10 Hybrid mathematical-informational models
133(4)
6 Evolutionary models
137(22)
6.1 Introduction
137(2)
6.2 Evolution and adaptation
139(1)
6.3 Genetic algorithm
140(4)
6.3.1 Population of genetic codes
140(1)
6.3.2 Artificial environment and fitness
141(1)
6.3.3 Competitive rules of reproduction and recombination
141(1)
6.3.4 Random mutation
142(1)
6.3.5 Illustrative example
142(2)
6.4 Selection methods
144(1)
6.5 Shape optimization of a cantilever beam
145(9)
6.6 Dynamic neighborhood method for multimodal problems
154(3)
6.6.1 Himmelblau problem
155(2)
6.6.2 Concluding remarks on DNM
157(1)
6.7 Schema theorem
157(2)
7 Implicit redundant representation in genetic algorithm
159(18)
7.1 Introduction
159(2)
7.2 Autogenesis and redundancy in genetic algorithm
161(5)
7.2.1 String length and redundancy ratio
162(1)
7.2.2 Illustrative example
163(3)
7.3 Shape optimization of a cantilever beam using IRRGA
166(4)
7.4 IRRGA in nondestructive evaluation and condition monitoring
170(7)
7.4.1 Condition monitoring of a truss bridge
171(6)
8 Inverse problem of engineering design
177(22)
8.1 Introduction
177(2)
8.2 Structured and unstructured design problems
179(3)
8.3 Dynamic variable allocation and redundancy in genetic algorithm
182(2)
8.4 Unstructured design of a plane truss
184(7)
8.4.1 Problem definition
184(1)
8.4.2 String representation and structural synthesis
185(1)
8.4.3 Fitness function
186(2)
8.4.4 Evolution of a truss design
188(3)
8.5 IRRGA in unstructured design of a plane frame
191(6)
8.6 Summary and discussion
197(2)
References 199(4)
Index 203
Jamshid Ghaboussi is Emeritus Professor in Civil and Environmental Engineering at University of Illinois at Urbana-Champaign. He received his doctoral degree from University of California at Berkeley. He has over 40 years of teaching and research experience in computational mechanics and soft computing with applications in structural engineering, geo-mechanics and bio-medical engineering. He has published extensively in these areas and is the inventor in five patents, mainly in the application of soft computing and computational mechanics. He is the co-author of books Numerical Methods in Computational Mechanics (CRC Press) and Nonlinear Computational Solid Mechanics (CRC Press). In recent years he has been conducting research on complex systems and has co-authored a book on Understanding Systems: A Grand Challenge for 21st Century Engineering (World Scientific Publishing).
Biežāk uzdotie jautājumi par e-grāmatām Biežāk uzdotie jautājumi par e-grāmatām
Permanent link: https://www.kriso.lv/db/97804298928206e.html
Keywords: