Muutke küpsiste eelistusi

E-raamat: Artificial Neural Network-based Optimized Design of Reinforced Concrete Structures [Taylor & Francis e-raamat]

(Kyung Hee University, Republic of Korea)
  • Formaat: 564 pages, 290 Tables, color; 244 Line drawings, color; 244 Illustrations, color
  • Ilmumisaeg: 11-Jan-2023
  • Kirjastus: CRC Press
  • ISBN-13: 9781003314684
Teised raamatud teemal:
  • Taylor & Francis e-raamat
  • Hind: 244,66 €*
  • * hind, mis tagab piiramatu üheaegsete kasutajate arvuga ligipääsu piiramatuks ajaks
  • Tavahind: 349,51 €
  • Säästad 30%
Artificial Neural Network-based Optimized Design of Reinforced Concrete StructuresSuurem pilt
  • Formaat: 564 pages, 290 Tables, color; 244 Line drawings, color; 244 Illustrations, color
  • Ilmumisaeg: 11-Jan-2023
  • Kirjastus: CRC Press
  • ISBN-13: 9781003314684
Teised raamatud teemal:
Taylor & Francis e-raamatudRohkem infot Taylor & Francis e-raamatute kohta
Raamatu kodulehekülg: https://www.taylorfrancis.com/books/9781003314684
Artificial Neural Network-based Optimized Design of Reinforced Concrete Structures introduces AI-based Lagrange optimization techniques that can enable more rational engineering decisions for concrete structures while conforming to codes of practice. It shows how objective functions including cost, CO2 emissions, and structural weight of concrete structures are optimized either separately or simultaneously while satisfying constraining design conditions using an ANN-based Lagrange algorithm. Any design target can be adopted as an objective function. Many optimized design examples are verified by both conventional structural calculations and big datasets.





Uniquely applies the new powerful tools of AI to concrete structural design and optimization Multi-objective functions of concrete structures optimized either separately or simultaneously Design requirements imposed by codes are automatically satisfied by constraining conditions Heavily illustrated in color with practical design examples

The book suits undergraduate and graduate students who have an understanding of collegelevel calculus and will be especially beneficial to engineers and contractors who seek to optimize concrete structures.
Preface xiii
Author xv
1 Introduction to Lagrange optimization for engineering applications
1(26)
1.1 Significance of this chapter
1(1)
1.2 An optimality formulation based on equality constraints
2(4)
1.2.1 Formulation of Lagrange functions
2(1)
1.2.2 Formulation of gradient vectors
2(2)
1.2.3 Optimality conditions of objective functions constrained by equality functions based on gradient vectors; finding stationary points based on gradients vectors
4(1)
1.2.4 Optimizations of an objective function constrained by equality functions
5(1)
1.3 An optimality formulation based on inequality constraints
6(18)
1.3.1 KKT (Karush-Kuhn-Tucker Conditions) optimality conditions
6(2)
1.3.2 Formulation of KKT optimality conditions (active and inactive), their implications on economy and structural engineering
8(1)
1.3.3 Optimality examples with inequality conditions
9(1)
1.3.3.1 Example #1
9(5)
Summary
14(1)
1.3.3.2 Example #2
14(5)
1.3.3.3 Example #3
19(5)
1.4 How many KKT conditions (Kuhn and Tucker, 1951; Kuhn and Tucker, 2014) must be considered?
24(1)
1.5 Conclusions
25(2)
References
25(2)
2 Lagrange optimization using artificial neural network-based generalized functions
27(172)
2.1 Importance of an optimization for engineering designs
27(1)
2.1.1 Significance of ANN-based optimization
27(1)
2.1.2 Why ANN-based generalized functions?
28(1)
2.2 ANN-based Lagrange formulation constrained by inequality functions
28(1)
2.3 ANN-based generalizable objective and constraining functions
29(23)
2.3.1 A [ imitation of an analytical function-based objective and inequality functions
29(1)
2.3.2 Formulation of ANN-based Lagrange functions and KKT condition
29(1)
2.3.3 Formulation of ANN-based objective and inequality functions
30(2)
2.3.4 Linear approximation of a first derivative (Jacobi) of Lagrange functions
32(1)
2.3.4.1 Optimization based on linearized Lagrange functions based on first-order (Jacobian matrix δ £(x(k), λc(k), λv(k))4% using Newton-Raphson iteration
32(3)
2.3.4.2 Formulation of generalized Jacobian and Hessian matrices
35(4)
2.3.4.3 Formulation of KKT non-linear equations based on Newton-Raphson iteration
39(1)
2.3.5 Stationary points of Lagrange functions based on gradient vectors
39(1)
2.3.6 ANN-based generalized functions replacing analytical functions
40(1)
2.3.6.1 Formulation of Jacobian and Hessian matrices
40(2)
2.3.6.2 Formulation of Jacobian matrix based on ANN
42(3)
2.3.6.3 Formulation of universally generalizable Hessian matrix based on ANN
45(6)
2.3.6.4 Flow chart for Lagrange-based optimization
51(1)
2.3.6.5 Summary
52(1)
2.4 Examples of optimizing Lagrange functions using ANN-based objective and constraining functions with KKT conditions
52(147)
2.4.1 Purpose of examples
52(1)
2.4.2 Optimization of a fourth-order polynomial with KKT conditions
53(1)
2.4.2.1 Optimization of a fourth-order polynomial considering inequality constraints based on analytical objective and constraining functions
53(9)
2.4.2.2 ANN-based optimization of a fourth-order polynomial constrained by inequality functions
62(15)
2.4.2.3 Conclusions
77(1)
2.4.3 A design of a truss frame based on Lagrange optimization
78(1)
2.4.3.1 Lagrange optimization of a truss frame based on analytical objective and constraining functions
78(18)
2.4.3.2 Lagrange optimization of a truss frame based on ANN-based object and constraining functions
96(46)
2.4.3.3 Conclusions
142(2)
2.4.4 Maximizing flying distance of a projectile based on Lagrange optimization
144(1)
2.4.4.1 Analytical function-based Lagrange optimization
144(16)
2.4.4.2 ANN-based Lagrange optimization
160(38)
References
198(1)
3 Design of reinforced concrete columns using ANN-based Lagrange algorithm
199(110)
3.1 Introduction
199(2)
3.1.1 Overview of Lagrange multiplier method-based KKT conditions
199(1)
3.1.2 Optimization implemented in structural engineering
200(1)
3.1.3 Significance of the chapter
201(1)
3.2 ANN-based on Lagrange networks
201(23)
3.2.1 Obtaining minimum design parameters for reinforced concrete columns based on ACI318-19 and ACI318-19
202(1)
3.2.2 ANN-based functions including objective functions of RC columns
203(1)
3.2.2.1 Weight and bias matrices based on forward ANNs to derive objective functions
203(15)
3.2.2.2 Weight and bias matrices based on reverse ANNs to derive objective functions
218(1)
3.2.2.3 Jacobian and Hessian matrices derived based on ANNs
218(3)
3.2.2.4 Stationary points of Lagrange functions C(x, Xc, Xy) subject to constraining conditions based on Newton-Raphson iteration
221(3)
3.3 Optimization of column designs based on an Ann-based Lagrange algorithm
224(78)
3.3.1 Column design scenario minimizing CIc
225(1)
3.3.1.1 Formulation of Lagrange optimization based on forward network
225(14)
3.3.1.2 Formulation of Lagrange optimization based on a reverse network
239(8)
3.3.1.3 Verifications
247(8)
3.3.1.4 P-M diagram
255(1)
3.3.2 Column design scenario minimizing COz
255(1)
3.3.2.1 Formulation of forward network vs. reverse network
255(2)
3.3.2.2 Solving KKT nonlinear equations based on Newton-Raphson iteration
257(17)
3.3.2.3 Verifications
274(3)
3.3.2.4 P-M diagram
277(1)
3.3.3 Column design scenario minimizing weight
278(1)
3.3.3.1 Formulation of forward network vs. reverse network
278(1)
3.3.3.2 Solving KKT nonlinear equations based on Newton-Raphson method
279(19)
3.3.3.3 Verifications
298(1)
3.3.3.4 P-M diagram
299(2)
3.3.3.5 Influence of optimization on P-M diagrams
301(1)
3.4 Noticeable updates with ACI 318-19 compared with 318-14
302(2)
3.5 Conclusions
304(5)
References
306(3)
4 Optimization of a reinforced concrete beam design using ANN-based Lagrange algorithm
309(38)
4.1 Significance of the
Chapter
309(2)
4.1.1 Current research
309(1)
4.1.2 Motivations and objective
310(1)
4.1.3 Significance of the proposed methodology
310(1)
4.2 Optimization of a reinforced concrete beam designs based on ANNs
311(10)
4.2.1 Beam design scenarios
311(2)
4.2.2 Formulation of a Lagrange function for optimizing a reinforced concrete beam based on ANNs
313(1)
4.2.2.1 Derivation of ANN-based objective functions
313(3)
4.2.2.2 Derivation of ANN-based Lagrange functions
316(1)
4.2.2.3 Formulation of KKT conditions based on equality and inequality constraints
317(4)
4.3 Generation of Large Structural Datasets
321(5)
4.3.1 Input and output parameters selected for large datasets
321(1)
4.3.2 Random design ranges
321(1)
4.3.3 Network training based on parallel training method (PTM) training
322(1)
4.3.4 Training for forward Lagrange networks
322(1)
4.3.5 Training for rebar placements with multiple layers
323(3)
4.4 Network Verification
326(6)
4.4.1 Verification of design parameters based on a forward Lagrange network
326(4)
4.4.2 Verification of Selected parameters based on large datasets
330(1)
4.4.3 Cost savings based on Lagrange algorithm
331(1)
4.5 Design Charts Based on ANN-Based Lagrange Optimizations Minimizing CIb
332(6)
4.5.1 Optimization of the cost (CIJ for material and manufacture for design ductile beam sections based on design charts
331(4)
4.5.2 Use of design charts to design ductile beam sections
335(2)
4.5.3 Verification of optimization
337(1)
4.6 Use of ANN-Based Lagrange Networks to Investigate Changes between ACI 318-14 and ACI 318-19
338(3)
4.6.1 ACI 318-19
338(1)
4.6.1.1 Revised limit of tension-controlled sections
338(1)
4.6.1.2 Reduction in effective moment of inertia for ACI318-19
338(2)
4.6.2 The Comparisons between ACI 318-14 and ACI 318-19 Based on Conventional Structural Calculations
340(1)
4.6.3 Changes of Optimized Results between ACI 318-14 and ACI 318-19 Using ANNs
341(1)
4.7 Results and Discussions
341(2)
4.7.1 ANN-based formulation of objective functions
341(1)
4.7.2 Design charts obtained based on Lagrange networks optimizing cost (material and manufacture) of ductile doubly reinforced concrete beams
342(1)
4.7.3 Verifying optimized objective functions
343(1)
4.7.4 ANN-based structural designs beyond human efficiency
343(1)
4.8 Conclusions
343(4)
References
344(3)
5 ANN-based structural designs using Lagrange multipliers optimizing multiple objective functions
347(141)
5.1 Introduction
347(19)
5.1.1 Significance of optimizing multiple objective functions
347(1)
5.1.1.1 Previous studies
347(1)
5.1.1.2 Problem Descriptions and Motivations of the
Chapter
348(1)
5.1.1.3 Significance of optimizing UFOs
349(1)
5.1.1.4 Contents of
Chapter 5
350(1)
5.1.2 Review of Pareto frontier
350(4)
5.1.3 Criterion space and Pareto frontier
354(1)
5.1.4 Weighted sum method
355(1)
5.1.4.1 The first method - minimization of bi-objective functions based on a definition of nondominated points
356(2)
5.1.4.2 The second method - minimizing bi-objective functions (UFO) based on weighted sum method
358(4)
5.1.5 Normalized unified function of objectives implementing weighted sum method
362(1)
5.1.5.1 Normalized UFOs implementing weighted sum method
362(2)
5.1.5.2 Discussion on normalized objective and nonnormalized functions
364(2)
5.2 ANN-based Lagrange functions optimizing multiple objective functions
366(5)
5.2.1 Significance of considering UFO
366(1)
5.2.2 Unified function of objectives
367(1)
5.2.3 ANN-based Lagrange optimization algorithm of five steps based on UFO
368(3)
5.3 ANN-based Lagrange optimization design of RC circular columns having multiple objective
371(30)
5.3.1 Forward design of circular RC columns
372(1)
5.3.2 Optimization design scenarios
373(1)
5.3.3 Five steps to optimize circular RC column based on three-objective functions
373(11)
5.3.4 Discussions on an optimization based on three objective functions
384(1)
5.3.5 Verification to large datasets
384(1)
5.3.6 Generation of evenly spaced fractions
385(5)
5.3.7 Interpretation of data trend
390(1)
5.3.7.1 Relationships among three objective functions
390(1)
5.3.7.2 Exploring trend of large datasets
391(2)
5.3.8 Examples of optimal designs based on Pareto frontier
393(1)
5.3.8.1 Identifying design parameters for a designated fraction
393(5)
5.3.8.2 Optimized P-M diagram
398(1)
5.3.9 Decision-making based on Pareto frontier
399(2)
5.4 An ANN-based optimization of UFO for circular RC columns sustaining multiple loads
401(26)
5.4.1 Reusing components of weight matrices subject to one biaxial load pair (ANN-1LP) to derive weight matrices subject to multiple biaxial load pairs (ANN-nLP) load pairs
401(3)
5.4.1.1 Generalized ANN (Model-LPs) used to derive n load pairs (Tu MUii)
404(2)
5.4.1.2 Formulation of the Network subject to multi-load pairs
406(16)
5.4.2 An optimization of a circular RC column sustaining five load pairs based on three-objective functions
422(1)
5.4.2.1 Optimization design scenario
422(1)
5.4.2.2 Five steps to optimize a circular RC column sustaining five load pairs based on three-objective functions
422(4)
5.4.3 Verification of Pareto frontier based on large datasets
426(1)
5.5 ANN-based Lagrange optimization for UFO to design uniaxial rectangular RC columns sustaining multiple loads
427(11)
5.5.1 Optimization scenario based on a forward design
427(1)
5.5.2 Five-step optimization based on multiple objective functions
428(5)
5.5.3 Verification of Pareto frontier to large dataset
433(1)
5.5.4 Design parameters corresponding to three fractions of Pareto frontier
433(5)
5.6 ANN-based Lagrange optimization for UFO to design biaxial rectangular RC columns sustaining multiple loads
438(23)
5.6.1 Optimization scenario based on a forward design subject to multi-loads with small magnitude
438(1)
5.6.2 Five steps optimization based on multiple objective functions
439(6)
5.6.3 Verification of Pareto frontier based on large datasets
445(1)
5.6.4 Design parameters corresponding to three points of Pareto frontier
445(2)
5.6.5 An example of ANN-based Lagrange optimization design based on multi-objective functions for biaxial rectangular RC columns sustaining multiple loads with big magnitude
447(1)
5.6.5.1 Identifying design parameters for designated fractions based on two neural networks based on Tables 5.6.2.3 and 5.6.5.6
448(10)
5.6.5.2 Design accuracies based on the two neural networks based on Tables 5.6.2.3 and 5.6.5.6 for the two Pareto curves
458(3)
5.7 ANN-based Lagrange multi-objective optimization design of RC beams
461(23)
5.7.1 Design scenarios of doubly reinforced concrete beams
462(1)
5.7.1.1 Selection of design parameters based on design criteria of doubly reinforced concrete beams
462(2)
5.7.1.2 Selection of objective functions
464(1)
5.7.1.3 An optimization scenario
464(2)
5.7.2 Five steps to optimize a design of RC beams with which Clb, C02 and Wb are minimized
466(2)
5.7.2.1 Step 1-Deriving ANNs
468(3)
5.7.2.2 Step 2-Defining MOO problems
471(2)
5.7.2.3 Step 3-Optimization based on a single-objective function
473(1)
5.7.2.4 Step 4-Formulating UFO
473(1)
5.7.2.5 Step 5-Optimizing UFO
474(1)
5.7.3 Design parameters corresponding to various fractions on Pareto frontier
474(3)
5.7.4 Verification of Pareto frontier
477(3)
5.7.5 Decision-making based on the Pareto frontier
480(3)
5.7.6 Interpretation of data trend based on relationships among three objective functions
483(1)
5.8 Design recommendations and conclusions
484(4)
5.8.1 Design recommendations
484(1)
5.8.2 Conclusions
484(1)
References
485(3)
Acknowledgments 488(1)
Appendix A 489(22)
Appendix B 511(8)
Appendix C 519(18)
Appendix D 537(24)
Index 561
WonKee Hong is a professor of architectural engineering at Kyung Hee University, South Korea. He received his master's and PhD degrees from UCLA, and has worked for Englekirk and Hart, Inc. (USA), Nihhon Sekkei (Japan), and the Samsung Engineering and Construction Company (Korea). Dr. Hong has more than 35 years of professional experience in structural and construction engineering. He has been both an inventor and researcher in the field of modularized composite structures and is the author of more than 100 technical papers and over 100 patents in both Korea and The United States.
Püsilink: https://www.kriso.ee/db/9781003314684_pe.html
Märksõnad: