Journal of Asian Architecture and Building Engineering

ISSN: (Print) (Online) Journal homepage: https://www.tandfonline.com/loi/tabe20

An AI-based auto-design for optimizing RC frames

using the ANN-based Hong–Lagrange algorithm

Won-Kee Hong & Tien Dat Pham

To cite this article: Won-Kee Hong & Tien Dat Pham (2023) An AI-based auto-design for
optimizing RC frames using the ANN-based Hong–Lagrange algorithm, Journal of Asian
Architecture and Building Engineering, 22:5, 2876-2888, DOI: 10.1080/13467581.2022.2163174

To link to this article: https://doi.org/10.1080/13467581.2022.2163174

© 2023 The Author(s). Published by Informa

UK Limited, trading as Taylor & Francis
Group on behalf of the Architectural
Institute of Japan, Architectural Institute of
Korea and Architectural Society of China.

Published online: 08 Jan 2023.

Submit your article to this journal

Article views: 381

View related articles

View Crossmark data

Citing articles: 1 View citing articles

Full Terms & Conditions of access and use can be found at

https://www.tandfonline.com/action/journalInformation?journalCode=tabe20
JOURNAL OF ASIAN ARCHITECTURE AND BUILDING ENGINEERING
2023, VOL. 22, NO. 5, 2876–2888
https://doi.org/10.1080/13467581.2022.2163174

BUILDING STRUCTURES AND MATERIALS

An AI-based auto-design for optimizing RC frames using the ANN-based Hong–

Lagrange algorithm
Won-Kee Hong and Tien Dat Pham
Department of Architectural Engineering, Kyung Hee University, Yongin, Republic of Korea

ABSTRACT ARTICLE HISTORY

Artificial neural networks (ANNs)-based objective functions such as costs and weights of Received 9 September 2022
reinforced concrete (RC) frames with four-by-four bays and four floors are optimized simulta­ Accepted 15 December 2022
neously based on big datasets of 330,000 designs according to ACI 318-19, whereas corre­ KEYWORDS
sponding design parameters, which minimize objective functions, are also obtained. The ANN-based Hong–Lagrange
Pareto frontier verified by big datasets shows reductions up to 44.983% and 33.111% in algorithm of RC frames;
costs and weights, respectively, compared with probable designs based on averages of 688 Pareto frontier of RC frames;
(0.1%) best designs among 688,000 samples. Optimized designs’ meeting requirements big datasets of RC frames;
imposed by codes and architects are achieved using the ANN-based Hong–Lagrange algorithm KKT solutions of RC frames;
in which complex analytical objective functions are replaced by ANN-based objective func­ weight fraction of MOO
tions. ANN is formulated to provide 32 forward outputs based on 18 forward inputs to minimize problems
or maximize objective functions, such as costs and weights as a function of 18 input para­
meters. When good training qualities are achieved, objective functions with equality and
inequality constraints are implemented in the proposed method, which determines optimal
design parameters for building with accuracies and robustness equivalent to derivation-based
approaches, which are hard to obtain using metaheuristic methods. The proposed AI-based
auto-designs perform optimization where design variables are produced automatically while
optimizing design targets.

1. Introduction due to seismic actions. The MOO problem, then, was

solved using a ε-constraint method, providing a Pareto
1.1. Literature review
set of optimal building designs. Paya-Zaforteza et al.
Building optimization is always an ultimate goal of struc­ (2009) presented a method based on a similated anneal­
tural engineers. However, it is difficult to explicitly derive ing algorithm, optimizing CO2 emissions and costs of
analytical objective functions to optimize complex rein­ buildings designed based on the Spanish code. Results
forced concrete (RC) frames that meet all code require­ indicated a close relationship between two objective
ments simultaneously. This is a complex task, especially, functions where environmental and economical efficien­
when multiple constraining conditions are to be imposed. cies of a design minimizing CO2 emissions were relatively
Zou et al. (2007) formulated the life-cycle costs of similar to those obtained from a design with optimized
a building as a multi-objective optimization (MOO) pro­ costs. On the other hand, Yeo and Potra (2015) reported
blem consisting of material costs and expected damages a difference of 5% to 10% between CO2 emissions of

CONTACT Won-Kee Hong [email protected] Room 104-1, Engineering building, Kyung Hee University Global Campus 1732, Deogyeong-daero,
Giheung-gu, Yongin-si, Gyeonggi-do 17104, Republic of Korea
This article has been republished with minor changes. These changes do not impact the academic content of the article.
© 2023 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group on behalf of the Architectural Institute of Japan, Architectural Institute of Korea and
Architectural Society of China.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits
unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. The terms on which this article has been published allow the posting
of the Accepted Manuscript in a repository by the author(s) or with their consent.
 JOURNAL OF ASIAN ARCHITECTURE AND BUILDING ENGINEERING 2877

a design minimizing CO2 emissions and those of the offering optimized designs based on ANNs-based
cheapest design. Camp and Huq (2013) implemented Lagrange optimization that are not available currently.
the Big Bang-Big Crunch algorithm in Accuracies were verified by conventional structural
reducing CO2 emissions and costs of RC frames, resulting designs, resulting in the basis for data-centric engineer­
in improvements compared with genetic and annealing ing which is not based on structural mechanics.
algorithms. The study by Sharafi, Hadi, and Teh (2012)
applied a colony optimization algorithm in minimizing
1.2. Research significance
a cost of a 3D RC frame, resulting in a further cost reduc­
tion of 4.8% compared with a study by Sahab, Ashour, Derivation-based approaches are unable to efficiently
and Toropov (2005) which combined an exhaustive optimize large structure designs because optimizations
search algorithm, a genetic algorithm, and a Hook and and sensitivity analysis are complex due to various
Jeeves method.Esfandiari et al. (2018 – 2017) introduced requirements imposed by codes and a large number of
an algorithm that combined multi-criterion decision- input and output variables. Metaheuristic methods such
making and particle swarm optimizations, accelerating as genetic algorithms, similated annealing algorithms,
convergences in finding optimal solutions for 3D RC and colony optimization algorithms are widely applied,
frames subjected to lateral seismic forces. Bai, Jin, and as discussed in the literature review. However, there are
Ou (2020) maximized seismic resistance of RC structures debates about their accuracies and robustness, for exam­
by an iterative analysis-and-redesign scheme, substan­ ple, results provided by genetic algorithms can be
tially reducing story drifts while slightly increasing mate­ unstable and converge to the local minima because
rial costs. Hysteresis behaviors of structures are predicted procedures initializations, crossover, and mutations heav­
based on Bouc–Wen models in studies by Sirotti et al. ily rely on randomness (Blum and Roli 2003). Achieving
(2021), Pelliciari et al. (2020, 2018). optimal solutions, hence, in day-to-day engineering prac­
The majority of previous studies evaded complexities tices is still challenging even if numerous research has
of explicit objective functions in structural designs by been proposed in the field. The present study offers
using metaheuristic methods such as genetic algorithm, a novel algorithm that systematically and conveniently
pattern search algorithm, and colony optimization algo­ optimizes building frames, bridging state-of-the-art artifi­
rithm. Examples of artificial neural networks (ANNs)- cial intelligence (AI) technologies and practical
based structural designs were found in studies by engineering.
Srinivas and Ramanjaneyulu (2007), Shin et al. (2020), This study uses an ANN-based Hong–Lagrange algo­
Asteris et al. (2016), and García-Segura, Yepes, and rithm with constraints imposed by codes and architects
Frangopol (2017). Behaviors of bridge decks were pre­ to holistically optimize RC frames, recognizing that it is
dicted by ANNs, and designs are optimized using difficult to explicitly derive analytical objective functions
genetic algorithms, in the study of Srinivas and when optimizing complex RC frames that meet all code
Ramanjaneyulu (2007). Hazards of seismically deficient requirements simultaneously. The approach provided in
RC frames were assessed and mitigated using ANNs by this study optimizes RC frames based on ANN-based
Shin et al. (2020), aiding retrofit designs in buildings. objective functions, solving non-linear optimization pro­
Asteris et al. (2016) predicted fundamental periods of blems under strict constraints imposed by design codes
infilled RC structures using ANNs, showing good accura­ and interests of engineers. The use of ANN-based objec­
cies when verified by analytical investigations. tive functions eliminates complex derivations of explicit
García-Segura, Yepes, and Frangopol (2017) conducted mathematical formulations which hinders applications of
an optimization of post-tensioned concrete road optimizations for practical designs.
bridges using ANNs, minimizing total expected costs This study considers RC frames where the ANN-
while achieving required levels of safety and durability. based auto-designs for optimizing RC frames are
However, the implementation of ANNs in optimizations developed based on the ANN-based Hong–Lagrange
of RC frames were not common even though ANNs have algorithm. Additional structural systems such as dual
been successfully used in in many areas such as medical, frames, steel RC frames, and prestressed frames are
auto pilot, financial, etc. The present study provided under development. AI-based auto-designs proposed
a novel procedure to calculate design parameters in this study perform design optimization while opti­
while minimizing both single and multi-objective func­ mizing design targets. Design parameters are pro­
tions for structural frames using the ANN-based Hong– duced automatically, whereas it is challenging to
Lagrange algorithm. ANN-based Hong–Lagrange algo­ achieve auto-designs by conventional approaches.
rithm was successfully implemented in optimizing beam
and column designs in the studies of Hong and Nguyen
1.3. ANN-based Hong–Lagrange algorithm
(2021) and Hong, Nguyen, and Nguyen (2021). It was
anticipated that the optimizations for beams, columns, Villarrubia et al. (2018) proposed a method of approx­
and frames can assist human engineers in enhancing imating objective functions by ANNs and minimizing
design accuracies and reducing their labor while constrained ANN-based objective functions by
2878 W.-K. HONG AND T. D. PHAM

Figure 1. A graphical illustration of ANN-based Hong–Lagrange algorithm.

Figure 2. Four steps of ANN-based Hong–Lagrange algorithm from generating big datasets to identifying Pareto frontiers.

Lagrange functions and Karush–Kuhn–Tucker (KKT) samples, producing optimized design parameters as
conditions. Theoretically, this method can provide shown in Figure 1. Complex analytical objective func­
accuracy and robustness equivalent to derivative- tions are replaced by ANN-based objective functions
based methods while eliminating complex derivation while multiple constraining conditions are imposed by
processes when good training is achieved. The ANN- equality and inequality constraints in Lagrange func­
based Hong–Lagrange algorithm illustrated in Figure 1 tions (Lagrange 1804).
is developed referring to the method proposed by Optimization consists of four steps as follows as
Villarrubia et al. (2018), where ANN-based Lagrange shown in Figure 2.
optimizations are expanded to structural problems, Step 1: Any structural-based software including
implanting constraints imposed by architecture and MIDAS or ETABS can be used to model frames.
codes in Lagrange functions. This study performs Graphical interfaces of MIDAS and ETABS are utilized
a holistic optimization of RC frames based on the ANN- so frames can be modeled accurately and conveniently
based Hong–Lagrange algorithm, where ANN-based even though there are geometrical irregularities.
objective functions such as cost (CI) and weight (W) Information including frame geometry, frame supports,
of RC frames derived as a function of input parameters end-conditions of members, loading, story data, and
which are, then, minimized based on 330,000 data structural groups are established using graphical tools
 JOURNAL OF ASIAN ARCHITECTURE AND BUILDING ENGINEERING 2879

of MIDAS or ETAB as shown in descriptions from 1 to 6 in while optimizing multiple objective functions
Step 1.1 of Figure 2. In Step 1.1, graphical interfaces of simultaneously.
structural-based software (MIDAS or ETABS) are utilized The present study performs a data generating, train­
to establish frame models. However, MIDAS or ETABS ing, and optimizing algorithms using MATLAB Deep
only serve as modelers, whereas models are not inves­ Learning Toolbox (MathWorks 2022a), MATLAB
tigated by MIDAS or ETABS. The model is exported to Parallel Computing Toolbox (MathWorks 2022a),
external files such as MGT files by MIDAS. These MGT MATLAB Statistics and Machine Learning Toolbox
files are imported in the ABBA (AI-Based Build Analysis (MathWorks 2022a), MATLAB Global Optimization
and design) frame generator in Step 1.2 to generate big Toolbox (MathWorks 2022a), MATLAB Optimization
data samples. The ABBA frame generator is a MATLAB- Toolbox (MathWorks 2022a), and MATLAB R2022a
based software. In this step, wind load parameters, seis­ (MathWorks 2022a). The purpose of each toolbox is
mic load parameters, load combinations, material prop­ described in Table 1. Steps 3.1 and 4 are developed
erties, ranges of section sizes, and rebar ratios are based on Villarrubia et al. (2018), and Step 3.2 is
assigned to the ABBA frame generator. In each data developed based on Zadeh (1963).
set, the generator randomly selects member sizes and The present study includes five sections. Section 1
rebars ratios based on ranges predefined by users to shows novelties and advantages of the proposed algo­
calculate output parameters including safety factors of rithm compared with available methods. Section 2
members, story drifts, long-term deflections, etc. introduces configurations of example buildings, data
required for frame designs. generations, and design constraints. Section 3 explains
Step 2: ANNs are trained based on big datasets gen­ formulations of objective functions based on weight
erated in Step 1 using MATLAB Deep Learning Toolbox and bias matrices of ANNs. Section 4 presents opti­
(MathWorks 2022a). MATLAB Deep Learning Toolbox is mized designs obtained from the ANN-based Hong–
a built-in application in the MATLAB platform where Lagrange algorithm. Lastly, Section 5 summarizes the
ANNs with different numbers of layers and neurons can research with discussions and recommendations.
be trained on big datasets. The toolbox produces regres­
sion models based on training, where weight and bias
matrices are extracted to generalize functions including 2. Frame investigations
objective and constraining functions. The generalized
2.1. Building configurations
functions are used to formulate Jacobi and Hessian
matrices of Lagrange functions. Stationary points for A four-by-four bay with four-story frame optimized in
Language functions are, then, identified using Newton– this study is shown in Figure 3, where the frame is
Raphson iteration (Upton and Cook 2014) in the SQP divided into two groups for beam and column designs.
algorithm (MathWorks 2022a). The floor height and beam span are 4 and 8 m, respec­
Step 3: ABBA-Frame optimization codes are developed tively. An example of optimizing RC frames is carried
to optimize frame designs based on single objective out to demonstrate the effectiveness of the ANN-
functions in Step 3.1. Design requirements are imposed based Hong–Lagrange algorithm. However, the algo­
by equalities and inequalities according to codes and rithm is not limited to any frame configurations, but it
architectural requirements. For example, all safety factors is possible for all frame layouts as long as these layouts
are greater than 1 and short-term deflections of beams can be modeled by either MIDAS or ETAB. Figure 3(a)
should be less than 1/360 of a span length. An objective shows a layout of beams and columns, while Figure 3
function for Lagrange optimization can be any design (b) illustrates slabs as dead loads. It is noted that
target, such as frame cost, CO2 emissions, and weight of weights and stiffnesses of slabs are considered in
the frame. In Step 3.2, a Unified Function of Objectives dynamic investigations even though slab weights are
(UFO) is established based on tradeoff ratios according to excluded in design tables. Weights of slabs are consid­
weighted sum methods (Zadeh 1963). ered for dead loads to calculate structure masses,
Step 4: The Lagrange optimization is implemented whereas frames are investigated with rigid diaphragms
in UFO to determine optimized design parameters at each floor, taking into account stiffnesses of slabs.

Table 1. Purposes of toolboxes used in the ANN-based Hong–Lagrange algorithms.

Toolbox Purpose
MATLAB R2022a (MathWorks 2022a) A platform to develop codes
MATLAB Parallel Computing Toolbox (MathWorks 2022a) A toolbox for performing calculations parallelly on all CPUs, enhancing
speeds of data generations and design optimizations
MATLAB Statistics and Machine Learning Toolbox (MathWorks 2022a) A toolbox for normalizing big datasets before training
MATLAB Deep Learning Toolbox (MathWorks 2022a) A toolbox for training ANN models from big datasets
MATLAB Global Optimization Toolbox (MathWorks 2022a) Toolboxes for determining solutions for constrained optimization problem
MATLAB Optimization Toolbox (MathWorks 2022a)
2880 W.-K. HONG AND T. D. PHAM

Figure 3. Illustration of an RC frame under optimization: (a) Beam and column layouts of an RC frame under optimization, (b) RC
frame under optimization with slabs considered as dead loads, (c) A frame model in MIDAS.

Weights presented in design tables only represent the horizontal loads are presented in Table 2. Wind load
total weight of beams and columns which are parameters include basic wind speed, topographic fac­
optimized in the present study. Frame geometries, tor (Kzt ), exposure class, and enclosing condition,
loading, support conditions, end-conditions of mem­ whereas seismic load parameters include spectral
bers, and member grouping are modeled by MIDAS as response acceleration parameter at short periods
shown in Figure 3(c). Parameters defining vertical and (Ss = 0.55 g), deflection amplification factor:

Figure 4. Five steps to optimize multiple objective functions simultaneously by the ANN-based Hong–Lagrange algorithm
(MathWorks 2022a).
 JOURNAL OF ASIAN ARCHITECTURE AND BUILDING ENGINEERING 2881

Figure 5. The Pareto frontier when minimizing CI and W, comparing optimized designs points with big datasets.

Table 2. Loads and material properties of an RC frame under optimizations.

Vertical loads
Live load ¼ 6kN=m2
Self-weight of 200 mm-thickness slab ¼ 4:8kN=m2
Finishing layer ¼ 1:2kN=m2
Wind load parameters
Basic wind speed Topographic factor (Kzt ) Exposure class Enclosing condition
26 m/s 1 C Enclosed frame
Seismic load parameters
Spectral response Deflection amplification factor: Coefficients for calculating approximated fundamental
acceleration parameter at short Cd ¼ 2:5 periods: Ct ¼ 0:0466 and x ¼ 0:9
periods: Ss = 0.55 g
Spectral response Response modification coefficient: R ¼ 3 Gravity acceleration: 9:81m=s2
acceleration parameter at a
period of 1 s: S1 ¼ 0:22 g
Long-period transition period: TL ¼ 8 s The importance factor: Ie ¼ 1 Site class: D
Overstrength factor: Damping ratio: 5%
Ω0 ¼ 3
Material properties
Concrete Rebar Stirrup
Strength (MPa) 40 600 500
Elastic modulus (GPa) 29.75 200 200
Thermal coefficient 9.9E-6 1E-5 1E-5
Poisson’s ratio 0.2 0.3 0.3
Unit weight (kN/m3) 25 78.5 78.5
Unit price (Korean Won – KRW/m3) 94E3 8.5E6 8.3E6
Unit CO2 emission (T-CO2/m3) 0.168 19.73 19.73
Unit energy consumption (MJ/m3) 2.4E3 25E4 25E4

(Cd ¼ 2:5), coefficients for calculating approximated study are also defined in Table 2, where material prices
fundamental periods ðCt ¼ 0:0466Þ; spectral response as Korean Won per cubic meters (KRW/m3) are taken
acceleration parameter at a period of 1 s (S1 ¼ 0:22 g), according to Korean markets in 2021. Units CO2 emis­
response modification coefficient (R ¼ 3), and gravity sions and energy consumptions are calculated accord­
acceleration (9:81 =s). Material properties used in this ing to studies of (Hong et al. (2010) and Kuk Kim et al.

Table 3. Load combinations considered in the present study.

Dead load Live load Wind load Seismic load
Service combinations 1 1 0 0
1 0 0.6 0
1 0.75 0 0.525
Strength combinations 1.2 1.6 0.8 0
0.9 0 1.6 0
1.275 1 0 1
A combination for calculating masses in dynamic analyses 1 0.25 0 0
2882 W.-K. HONG AND T. D. PHAM

(2013), respectively. It is noted that unit values of costs, combinations shown in Table 3 which influences the
weights, CO2 emissions, and energy consumptions are design significantly.
not fixed, and they can be changed easily before gen­ Optimized objective functions for cost index and
erating big datasets. a total weight of frames are calculated in Parameters
47 and 49 of Table 4, respectively. The objective func­
tions of costs and weights in frames are calculated
2.2. Data generations based on concrete volumes, rebar ratios, and stirrups
A frame generator is developed, referring to open-source areas in beams and columns. Costs and weights from
software LESM (Fernando Martha et al. 2022). The ABBA slabs are excluded from objective functions; however,
generator produces 330,000 data samples of an RC frame weights and stiffness of slabs are considered by the
(Figure 3) according to ACI 318-19 (Building Code ABBA frame generator in dynamic investigations.
Requirements for Structural Concrete (ACI 318-19) Ranges of big datasets are shown in Table 4 where
Commentary on, & Building Code Requirements for ranges of output parameters are obtained for preas­
Structural Concrete (ACI 318R-19) 2019) and ASCE 7-16 signed ranges of input parameters. There are many
(Loads and Structures 2017) as presented in Table 4. Each more parameters calculated during bigdata genera­
data sample includes 18 forward input parameters and 32 tions, such as an upper limit fundamental period (Cu Ta )
forward output parameters. The present example uses for determining base shear, base shears, wind pressures,
three service load combinations and three strength load section strengths, etc. However, they are not printed on

Table 4. Ranges of big data, (a) Forward design input parameters in 330,000 samples (18 varied inputs), (b) Forward design output
parameters for big data (32 output parameters).
No. Parameters Range
Column Group 1 1 HC1 Size (mm) (assuming square columns) 400–1000
2 ρX C1 Rebar ratio in X-direction 0.01–0.04
3 ρY C1 Rebar ratio in Y-direction 0.01–0.04
Column Group 2 4 HC2 Size (mm) (assuming square columns) 400–1000
5 ρX C2 Rebar ratio in X-direction 0.01–0.04
6 ρY C2 Rebar ratio in Y-direction 0.01–0.04
Beam Group 1 7 BB1 Section width (mm) 200–1000
8 HB1 Section height (mm) 400–1000
9 ρts B1 Top rebar ratio at beam end 0.001–0.025
10 ρtm B1 Top rebar ratio at mid-span 0.001–0.025
11 ρbs B1 Bottom rebar ratio at beam end 0.001–0.025
12 ρbm B1 Bottom rebar ratio at mid-span 0.001–0.025
Beam Group 2 13 BB1 Section width (mm) 200–1000
14 HB1 Section height (mm) 400–1000
15 ρts B1 Top rebar ratio at beam end 0.001–0.025
16 ρtm B1 Top rebar ratio at mid-span 0.001–0.025
17 ρbs B1 Bottom rebar ratio at beam end 0.001–0.025
18 ρbm B1 Bottom rebar ratio at mid-span 0.001–0.025
Column safety factors 19 SFC1 S1 Column Group 1 on Story 1 0.097–4.924 330,000
20 SFC1 S2 Column Group 1 on Story 2 0.134–6.815 330,000
21 SFC2 S3 Column Group 2 on Story 3 0.121–8.238 330,000
22 SFC2 S4 Column Group 2 on Story 4 0.149–10.400 330,000
Beam Group 1 on Story 1 23 SFB1 S1 Safety factor 0.049–3.799 330,000
24 Δs B1 S1 Short-term deflection (mm) 0.282–20 F250,000
25 ΔL B1 S1 Long-term deflection (mm) 0.489–34.999 F250,000
26 σ s B1 S1 Rebar stress under service loads 6.773–599.9 F250,000
Beam Group 1 on Story 2 27 SFB1 S2 Safety factor 0.05–3.596 330,000
28 Δs B1 S2 Short-term deflection (mm) 0.282–20 F250,000
29 ΔL B1 S2 Long-term deflection (mm) 0.522–34.999 F250,000
30 σ s B1 S2 Rebar stress under service loads 6.956–599.9 F250,000
Beam Group 2 on Story 3 31 SFB2 S3 Safety factor 0.046–3.751 330,000
32 Δs B2 S3 Short-term deflection (mm) 0.276–20 F250,000
33 ΔL B2 S3 Long-term deflection (mm) 0.505–35 F250,000
34 σ s B2 S3 Rebar stress under service loads 7.668–599.899 F250,000
Beam Group 2 on Story 4 35 SFB2 S4 Safety factor 0.045–3.581 330,000
36 Δs B2 S4 Short-term deflection (mm) 0.345–20 F250,000
37 ΔL B2 S4 Long-term deflection (mm) 0.623– 35 F250,000
38 σ s B2 S4 Rebar stress under service loads 7.016–599.899 F250,000
Rebar strain when concrete strain reaches 0.003 39 εsp B1 Rebar strain of Beam Group 1 at supports 0.002–0.079 330,000
40 εsm B1 Rebar strain of Beam Group 1 at mid-span 0.002–0.077 330,000
41 εsp B2 Rebar strain of Beam Group 2 at supports 0.002–0.081 330,000
42 εsm B2 Rebar strain of Beam Group 2 at mid-span 0.002–0.083 330,000
Dynamic analyses 43 T Fundamental period (s) 0.195–2.361 330,000
44 Dmax Maximum wind deformations (mm) 0.275–11.961 330,000
45 Driftmax Maximum story drift ratio of all stories 0.002–0.06 330,000
46 θ Stability coefficient 0.005–0.222 330,000
Effective indexes 47 CI Cost indexðKoreanWon KRW Þ 39,962,969–565,522,773 330,000
48 CO2 CO2 emission ðT CO2 Þ 82–1251 330,000
49 W Total weight of beams and columns ðkNÞ 4296–37,570 330,000
50 Energy consumption 1,103,363–16,222,172 330,000
 JOURNAL OF ASIAN ARCHITECTURE AND BUILDING ENGINEERING 2883

Table 5. Equality and inequality constraints.

(a) Inequalities imposed on forward input parameters related to column configurations
V1: HC1 ≤ 1000 mm V6 : ρY C1 � 0:039 V11 : ρY C2 � 0:01 1
V2 : HC1 � 400 mm V7 : HC2 � 1000 mm V12 : ρY C2 � 0:039
V3 : ρX C1 � 0:01 1 V8 : HC2 � 400 mm V13 : HC2 � HC1
V4 : ρX C1 � 0:039 V9 : ρX C2 � 0:01 1 V14 : ρX C2 � ρX C1
V5 : ρY C1 � 0:01 1 V10 : ρX C2 � 0:0 39 V15 : ρY C2 � ρY C1
(b) Inequalities imposed on forward input parameters related to beam configurations
V16 : BB1 � 1000 mm V26 : ρtm B1 � 0:015 V36 : ρts B2 � 0:0 15
V17 : BB1 � 250 mm V27 : ρtm B1 � 0:0025 V37 : ρts B2 � 0:0025
V18 : HB1 � 1000 mm V28 : ρbm B1 � 0:015 V38 : ρbs B2 � 0:015
V19 : HB1 � 400 mm V29 : ρbm B1 � 0:0025 V39 : ρbs B2 � 0:0025
V20 : BB1 � HB1 V30 : BB2 � 1000 mm V40 : ρtm B2 � 0:015
V21 : BB1 � 0:3HB1 V31 : BB2 � 250 mm V41 : ρtm B2 � 0:0025
V22 : ρts B1 � 0:0 15 V32 : HB2 � 1000 mm V42 : ρbm B2 � 0:015
V23 : ρts B1 � 0:0025 V33 : HB2 � 400 mm V43 : ρbm B2 � 0:0025
V24 : ρbs B1 � 0:015 V34 : BB2 � HB2
V25 : ρbs B1 � 0:0025 V35 : BB2 � 0:3HB2
(c) Inequalities imposed on forward output parameters related to safety factors
V44 : SFC1 S1 � 1 V46 : SFC2 S3 � 1 V48 : SFB1 S1 � 1 50 : SFB2 S3 � 1
V45 : SFC1 S2 � 1 V47 : SFC2 S4 � 1 V49 : SFB1 S2 � 1 V51 : SFB2 S4 � 1
(d) Inequalities imposed on forward output parameters related to rebar strains
V52 : εsp B1 � 0:006 V53 : εsm B1 � 0:006 V54 : εsp B2 � 0:006 V55 : εsm B2 � 0:006
(e) Inequalities imposed on forward output parameters related to deflections
Short-term deflection Long-term deflection
V56 : Δs B1 S1 � L360 ¼ 22:22 mm V60 : ΔL B1 S1 � L240 ¼ 33:33 mm
V57 : Δs B1 S2 � L360 ¼ 22:22 mm V61 : ΔL B1 S2 � L240 ¼ 33:33 mm
V58 : Δs B2 S3 � L360 ¼ 22:22 mm V62 : ΔL B2 S3 � L240 ¼ 33:33 mm
V59 : Δs B2 S4 � L360 ¼ 22:22 mm V63 : ΔL B2 S4 � L240 ¼ 33:33 mm
(f) Inequalities imposed on forward output parameters related to rebar stresses under service loads
V64 : σs B1 S1 � 23fy ¼ 400 MPa V66 : σs B2 S3 � 23fy ¼ 400 MPa
V65 : σs B1 S2 � 23fy ¼ 400 MPa V67 : σs B2 S4 � 23fy ¼ 400 MPa
(g) Inequalities imposed on forward output parameters related to lateral deformations
V68 : Driftmax � 0:015 V69 : θ � 0:2 V70 : Dmax � H500 ¼ 32 mm

an output-side of the big datasets because they are not training if a safety factor of 1 is desired in optimal
constrained by any code-based requirements. It is noted designs. Constructability of a frame is considered in
that F250,000 data samples are obtained by filtering Inequalities from V13 to V15 where sizes and rebars of
from 330,000 big data samples. Some data such as the upper column groups are constrained to be smaller
deflections and stresses calculated when unfactored than or equal to those of the lower column group.
moments exceed nominal capacities of sections are Inequalities from V44 to V47 in Table 5(c) constrain
removed. Other parameters, such as safety factors or column and beam safety factors in all four stories
story drifts, are generated correctly in all cases. (from Stories 1 to 4) to be ≥1, ensuring safeties of
optimized designs. Inequalities V52 to V55 in Table 5
(d) constrain beam rebar strains to be ≥0.006 when
2.3. Design requirements as inequality concrete strains reach 0.003, avoiding brittle failure in
constraints beams according to Section 9.3.3.1 of ACI 318=19
Table 5 presents 70 inequalities imposed during an (Building Code Requirements for Structural Concrete
optimizations of RC frames. A number of inequalities (ACI 318-19) Commentary on, & Building Code
is greater than that of forward input parameters Requirements for Structural Concrete (ACI 318R-19)
because multiple inequalities are applied to one para­ 2019). Inequalities from V56 to V63 in Table 5(e) con­
meter. For example, Inequalities V1 and V13 shown in strain beam immediate deflections to be smaller than
L
Table 5(a) are applied to HC1 (size of columns in or equal to 360 and beam long-term deflections to be
L
Column Group 1). In Tables 5(a, b), Inequalities from smaller than or equal to 240 according to Table 24.2.2
V1 to V43 are imposed on 18 forward input parameters in ACI 318-19 (Building Code Requirements for
when optimizing designs. Ranges for 14 forward input Structural Concrete (ACI 318-19) Commentary on, &
parameters out of 18 forward input parameters indi­ Building Code Requirements for Structural Concrete
cated in 26 inequalities from V3 to V6 , from V9 to V12 , (ACI 318R-19) 2019), guaranteeing the serviceability
V17 , from V22 to V29 , V31 , and from V36 to V43 are taken of optimized frames. Inequalities from V64 to V67 in
slightly narrower than ranges of big datasets to avoid Table 5(f) constrain rebar tensile stresses under service
sparse data at the edge range of the big datasets. It is loads to be smaller than or equal to according to
noted that big datasets should be wide enough to Table 24.3.2.1 in ACI 318-19 (Building Code
cover expected magnitudes, for example, a safety fac­ Requirements for Structural Concrete (ACI 318-19)
tor of 1 should appear inside ranges of big datasets for Commentary on, & Building Code Requirements for
2884 W.-K. HONG AND T. D. PHAM

Structural Concrete (ACI 318R-19) 2019) for controlling including 5 and 10 layers and a combination of the two
crack widths. Inequality V68 in Table 5(g) constrains the types of neurons including 80 and 128 neurons are
maximum story drift ratios of all stories to be ≤0:015. implemented. A number of layers and neurons are
The limitation of story drift ratios in four-story frames shown in Table 6 with epochs that provide the best
with a Risk Category II is 0.02 according to training accuracies. Validation indicates both desig­
Table 12.12-1 in ASCE 7-16 (Loads and Structures nated number of epochs and terminating epochs to
2017). However, the present example uses prevent over-fitting. For example, training proceeded
a conservative limit of 0.015 (a default limitation in up to 50,000 epochs for Story 1 of column safety factor
MIDAS) for story drift ratios. Inequality V69 in Table 5 as designated, however, training terminated at Epoch
(g) constrains the stability coefficient to be smaller 45,506 to prevent over-fitting for story 3 of column
0:5
than or equal to θmax ¼ βC d
¼ 0:5
2:5 ¼ 0:2 according to safety factor.
Section 12.8.7 in ASCE 7-16 (Loads and Structures The best training accuracy for rebar strain corre­
2017). Inequality V70 in Table 5(g) constrains the lateral sponding to concrete strain of 0.003 at beam end of
deflections due to wind loads to be smaller than or Group 1 is obtained with 5 layers and 128 neurons,
equal to H500 ¼ 32 mm according to Section CC.2.2 yielding Test mean square errors (MSE) = 1.2727E-04
in ASCE 7–16 (Loads and Structures 2017). and Regression = 0.9991. Training accuracies in terms
In summary, the optimization determines 18 design of Test MSE and Regression are presented to judge
variables listed in Table 4(a) including sizes and rebar training results. Detailed descriptions of ANN training
ratios of beams and columns to minimize costs and on structural data can be found in the books by Hong
weights simultaneously. Designs are also constrained (2019, 2021).
by 70 inequalities constraints presented in Table 5,
ensuring the safety, stability and constructability of
optimized frames. 3.2. ANN-based Hong–Lagrange algorithm
The ANN-based optimization of multi-objective func­
3. Formulating ANN-based objective tions for RC frames shown in Figure 3 is performed in 5
functions and ANN-based Hong–Lagrange steps as presented in Figure 4. Steps 1 to 3 calculate
algorithm ANN-based Lagrange functions for single objective
function by which a UFO is derived in Step 4 to mini­
3.1. Formulating ANN-based objective functions
mize it in Step 5, leading to an identification of a Pareto
Table 6 presents training accuracies of the ANNs in frontier. A set of MOO results is a Pareto frontier or
which a combination of the two types of hidden layers a Pareto set which is obtained by solving KKT

Table 6. Training accuracy, showing test MSE and regression.

Number of Best Test
Parameter samples Layer Neuron epoch Validation MSE Regression
Column safety factor SFC1 S1 330,000 10 80 48,817 50,000 3.4E-05 0.9999
SFC1 S2 330,000 5 128 48,621 50,000 3.6E-05 0.9999
SFC2 S3 330,000 5 128 40,506 45,506 7.0E-05 0.9994
SFC2 S4 330,000 5 128 43,156 48,156 7.8E-05 0.9995
Beam at Story 1 SFB1 S1 330,000 5 128 49,999 50,000 3.1E-05 1.0000
Δs B1 S1 F250,000 10 80 11,298 16,298 2.9E-03 0.9978
ΔL B1 S1 F250,000 10 80 11,794 16,794 3.7E-03 0.9970
σ s B1 S1 F250,000 10 80 10,347 15,347 6.0E-03 0.9966
Beam at Story 2 SFB1 S2 330,000 5 128 49,524 50,000 3.3E-05 1.0000
Δs B1 S2 F250,000 5 128 13,961 18,961 5.8E-03 0.9962
ΔL B1 S2 F250,000 10 80 21,970 26,970 3.8E-03 0.9976
σ s B1 S2 F250,000 10 80 9806 14,806 7.7E-03 0.9957
Beam at Story 3 SFB2 S3 330,000 5 128 49,987 50,000 3.9E-05 1.0000
Δs B2 S3 F250,000 5 128 11,813 16,813 3.7E-03 0.9972
ΔL B2 S3 F250,000 5 128 5491 10,491 7.1E-03 0.9899
σ s B2 S3 F250,000 10 80 7932 12,932 7.5E-03 0.9956
Beam at Story 4 SFB2 S4 330,000 10 80 49,986 50,000 4.2E-05 1.0000
Δs B2 S4 F250,000 10 80 7698 12,698 5.4E-03 0.9960
ΔL B2 S4 F250,000 10 80 11,754 16,754 3.9E-03 0.9972
σ s B2 S4 F250,000 10 80 20,762 25,762 3.1E-03 0.9983
Rebar strain when concrete strain reaches εsp B1 330,000 5 128 36,056 41,056 1.2E-04 0.9991
0.003 εsm B1 330,000 5 128 35,736 40,736 1.4E-04 0.9991
εsp B2 330,000 5 128 30,896 35,896 1.2E-04 0.9991
εsm B2 330,000 5 128 47,476 50,000 1.1E-04 0.9991
T ðsÞ 330,000 5 128 48,670 50,000 2.6E-05 1.0000
Lateral deflection Dmax 330,000 5 128 48,756 50,000 5.7E-07 1.0000
Driftmax 330,000 5 128 47,621 50,000 1.3E-06 1.0000
θ 330,000 10 80 49,784 50,000 7.4E-07 1.0000
Objective function CI 330,000 5 128 49,992 50,000 1.2E-06 1.0000
CO2 330,000 5 128 49,987 50,000 2.1E-06 1.0000
W 330,000 5 128 49,993 50,000 6.4E-06 1.0000
Energy consumption 330,000 5 128 49,875 50,000 5.7E-07 1.0000
 JOURNAL OF ASIAN ARCHITECTURE AND BUILDING ENGINEERING 2885

conditions (Kuhn and Tucker 1951) with a Newton– Design parameters identified for Design P1, Design
Raphson method in the SQP algorithm (MathWorks P5, and Design P9 based on nine fractions are pre­
2022a). A Pareto frontier investigating particular trade­ sented in Table 7. Design P1 (wCI : wW ¼ 1 : 0),
off ratios estimates how much sacrifice is made by Design P5 (wCI : wW ¼ 0.5 : 0 .5), and Design P9
each objective function to UFO based on the proposed (wCI : wW ¼ 0:1) are indicated in Table 7. Design para­
ANN-based Hong–Lagrange algorithm. A design exam­ meters of Design P1 based on a fraction of wCI : wW ¼
ple of RC frames is performed in this study in which 1 : 0 in which CI is only minimized are obtained. Design
two objective functions, cost, and weight, are simulta­ P9 identifies an optimized design parameters where
neously minimized using ANNs, leading to optimizing weight of the RC frame, W, is only minimized based on
UFO. Design parameters minimizing UFO of RC frames (wCI : wW ¼ 0:1) in which a Pareto frontier similar to
are also obtained. that of Design P1 is obtained. Design P5 identifies an
optimized design parameters with an equal tradeoff
between the two objective functions based on
4. Optimal designs (wCI : wW ¼ 0.5 : 0 .5). Tables 7(a), 5(b), and 5(c) pre­
sent design parameters optimized by ANN-based
In this study, design parameters are optimized simul­ Hong–Lagrange algorithm of UFO while insignificant
taneously based on two objective functions (cost index errors are verified by structural mechanics-based ABBA
and weight of the RC frame). Designs P1 to P9 corre­ frame generator. Design accuracies of ANNs for Design
sponding to nine fractions (wCI : wW ¼ 1 : 0, wCI : P1, Design P5, and Design P9 are also shown in
wW ¼ 0.875 : 0 .125, wCI : wW ¼ 0.75 : 0 .25, wCI : Tables 7(a), 5(b), and 5(c) where differences between
wW ¼ 0.625 : 0 .375, wCI : wW ¼ 0.5 : 0 .5, wCI : wW ¼ design parameters and the ABBA frame generator are
0.375 : 0 .625, wCI : wW ¼ 0.25 : 0 .75, wCI : wW ¼ negligible.
0.125 : 0 .875, wCI : wW ¼ 0:1) on Pareto frontier are It is noted that, in Table 7(a), the upper tensile
indicated in Figure 5 which also demonstrates that big rebar ratio ρts B1 = 0.0065 at beam end is obtained
datasets hardly show minimized data in the lowest as shown in Design P1 when a beam cost CI is
data range, however, it does not mean that big data­ minimized at 71,174,081 KRW, whereas the upper
sets do not cover the data in the lowest data zone. The tensile rebar ratio ρts B1 = 0.0090 is obtained as
gaps between Pareto frontier and big datasets can be shown in Design P9 when a beam weight is mini­
filled if more big datasets are generated. It is the mized to 7,307 kN from 8,585 kN of Design P1,
proposed method that, more efficiently, optimizes resulting increased rebar ratio (ρst B1 Þ by
0:0090 0:0065
designs and predicts the lowest bound of the big 0:0065 � 0:39% ¼ 39% to reduce the beam
datasets with one run. weight, but sacrificing cost which increased from

Table 7. Optimal designs based on fraction combinations P1, P5, and P9 in Figure 5.
(a) Design P1; minimizing CI (WCI = 1 & WW = 0) (refer to Fig. 5)

(Continued)
2886 W.-K. HONG AND T. D. PHAM

Table 7. (Continued).
(b) Design P5; minimizing CI and W (WCI = 0.5 & WW = 0.5) (refer to Fig. 5)

(c) Design P9; minimizing CI and W (WCI = 0 & WW = 1) (refer to Fig. 5)

71,174,081 to 104,003,171 KRW with 46% increase. (wCI : wW ¼ 1 : 0), Design P5 (wCI : wW ¼ 0.5 : 0
It is noted, in Table 7(b), that the upper tensile .5), and Design P9 (wCI : wW ¼ 0 : 1) can also be
rebar ratio ρts B1 = 0.0092 at beam end is obtained obtained from Pareto curve. Input parameters
as shown in Design P5 when weight of the RC including preassigned input parameters and 18
frame is minimized based on an equal tradeoff varied input parameters shown in Table 4 are
between the two objective functions at Design P5 used for an ANN and a structural mechanics-
(wCI : wW ¼ 0.5 : 0.5). A cost CI and a beam weight based ABBA generator to obtain 32 corresponding
obtained with Design P5 are 74,914,364 KRW and outputs shown in Table 4. Design accuracies
7,845 kN which are mid-range of those obtained obtained using equation Error ¼
between Design P1 and Design P9. Other design Outputgenerator OutputANN
parameters than those shown with Design P1 OutputANN
� 100% based on ANN and
 JOURNAL OF ASIAN ARCHITECTURE AND BUILDING ENGINEERING 2887

structural mechanics-based software ABBA genera­ parameters which is challenging to obtain using
tor seen in Tables 7(a), (b), and (c) are as large conventional design methods. This study is
as −7.5%. a steppingstone for the next step in structural ana­
Probable designs are determined based on averages lysis and design research with the advent of AI-
of the top 688 (0.1%) designs among 688,000 designs based Data-centric Engineering which is not based
randomly generated based on the ABBA generator on structural mechanics (Hong W. K. 2023).
shown in Figure 5, resulting in probable design values
of 129,367,608 KRW and 10,924 kN for CI and W, respec­
tively. Optimized designs, and hence, produces a cost Disclosure statement
savings up to 44.983% and a weight reduction up to No potential conflict of interest was reported by the authors.
33.111% over probable designs.

Funding
5. Conclusions
This work was supported by the National Research
A resilient design capable of optimizing RC frames has
Foundation of Korea (NRF) grant funded by the Korean gov­
been performed beyond human efficiency. It is difficult ernment [MSIT 2019R1A2C2004965].
for engineers to pre-assign constraining conditions on an
input-side for a conventional design. The present study
replaced complex analytical objective functions by ANN- References
based objective functions. Any type of objective function Artificial Neural Network-based Optimized Design of
and design target of interest can be implanted as artificial Reinforced Concrete Structures. Taylor and Francis.
neural genes to govern an optimization process minimiz­ Asteris, P. G., A. K. Tsaris, L. Cavaleri, C. C. Repapis, A. Papalou,
ing design targets for RC frames. Design codes and con­ F. Di Trapani, and D. F. Karypidis. 2016. “Prediction of the
straining requirements include economies, Fundamental Period of Infilled Rc Frame Structures Using
Artificial Neural Networks.” Computational Intelligence and
environments, and serviceability. ANN is formulated to Neuroscience 2016: 1–12. doi:10.1155/2016/5104907.
provide 32 forward output parameters based on 18 for­ Bai, J., S. Jin, and J. Ou. 2020. “An Efficient Method for
ward input parameters to simultaneously optimize objec­ Optimizing the Seismic Resistance of Reinforced Concrete
tive functions of a cost CI and a weight W of RC frames. In Frame Structures.” Advances in Structural Engineering 23 (4):
this study, pure RC frames are optimized where the AI- 670–686. doi:10.1177/1369433219878856.
Blum, C., and A. Roli. 2003. “Metaheuristics in Combinatorial
based auto-designs are developed using the ANN-based
Optimization: Overview and Conceptual Comparison.”
Hong–Lagrange algorithm. Additional structural systems ACM Computing Surveys 35 (3): 268–308. doi:10.1145/
such as dual frames, SRC frames, and PT frames are under 937503.937505.
developments. AI-based auto-designs proposed in this Building Code Requirements for Structural Concrete (ACI
study replace conventional design optimization pro­ 318-19) Commentary on, & Building Code Requirements
cesses by automatically producing design parameters for Structural Concrete (ACI 318R-19). 2019. “An ACI
Standard.” ACI Committee 318.
while optimizing design targets. It is challenging to
Camp, C. V., and F. Huq. 2013. “CO2 and Cost Optimization of
achieve auto-designs by conventional approaches. Reinforced Concrete Frames Using a Big bang-big Crunch
In this study, ANN-based Hong–Lagrange algo­ Algorithm.” Engineering Structures 48: 363–372. doi:10.
rithm is introduced for a holistic optimization of 1016/j.engstruct.2012.09.004.
RC frames. Objective functions with equality and Esfandiari, M. J., G. S. Urgessa, S. Sheikholarefin, and
inequality constraints are implanted in ANN-based S. H. D. Manshadi. 2018. “Optimum Design of 3D
Lagrange functions to control optimizations of the Reinforced Concrete Frames Using DMPSO Algorithm.”
Advances in Engineering Software 115 (July 2017):
designs. Design parameters are obtained based on
149–160. doi:10.1016/j.advengsoft.2017.09.007.
330,000 data samples to minimize ANN-based Fernando Martha, L., R. Lopez Rangel, P. Cortez Lopes, and
objective functions for costs CI and weights Wc of C. Horta. 2022. “LESM.” PONTIFICAL CATHOLIC UNIVERSITY
RC frames. Structural optimality is verified by OF RIO DE JANEIRO.
668,000 data samples, resulting in cost savings up García-Segura, T., V. Yepes, and D. M. Frangopol. 2017. “Multi-
to 44.983% and weight reductions up to 33.111% objective Design of post-tensioned Concrete Road Bridges
Using Artificial Neural Networks.” Structural and
compared with probable designs based on the aver­ Multidisciplinary Optimization 56 (1): 139–150. doi:10.
age of 688 (0.1%) best designs among 688,000 big 1007/s00158-017-1653-0.
data samples. Design accuracies are enhanced and Hong, W. K. 2023. Artificial Neural Network-based Optimized
verified by conventional structural designs while Design of Reinforced Concrete Structures. United States:
reducing labors of human engineers in optimizing CRC Press.
HONG, W.-K. 2019. Hybrid Composite Precast Systems:
designs for beams, columns, and frames. ANN-based
Numerical Investigation to Construction. United Kingdom:
optimized designs were not available before the Woodhead Publishing, Elsevier.
present research. Now it is possible to autono­ Hong, W. K. 2021. Artificial intelligence-based Design of
mously optimize design targets to calculate design Reinforced Concrete Structures. 978-89-6285-291-2. Korea.
2888 W.-K. HONG AND T. D. PHAM

Hong, W.-K., J.-M. Kim, S.-C. Park, S.-G. Lee, S.-I. Kim, K.-J. Yoon, Reinforced Concrete Structural Elements.” Structure and
H.-C. Kim, and J. Tai Kim. 2010. “A New Apartment Infrastructure Engineering 16 (7): 917–930. doi:10.1080/
Construction Technology with Effective CO2 Emission 15732479.2019.1674893.
Reduction Capabilities.” Energy 35(6. doi:10.1016/j. Pelliciari, M., G. C. Marano, T. Cuoghi, B. Briseghella,
energy.2009.05.036. D. Lavorato, and A. M. Tarantino. 2018. “Parameter
Hong, W. K., and M. C. Nguyen. 2021. “AI-based Lagrange Identification of Degrading and Pinched Hysteretic
Optimization for Designing Reinforced Concrete Systems Using a Modified Bouc–Wen Model.” Structure
Columns.” Journal of Asian Architecture and Building and Infrastructure Engineering 14 (12): 1573–1585. doi:10.
Engineering 1–15. doi:10.1080/13467581.2021.1971998. 1080/15732479.2018.1469652.
Hong, W. K., V. T. Nguyen, and M. C. Nguyen. 2021. Sahab, M. G., A. F. Ashour, and V. V. Toropov. 2005. “Cost
“Optimizing Reinforced Concrete Beams Cost Based on Optimisation of Reinforced Concrete Flat Slab Buildings.”
AI-based Lagrange Functions.” Journal of Asian Engineering Structures 27 (3): 313–322. doi:10.1016/j.
Architecture and Building Engineering 1–18. doi:10.1080/ engstruct.2004.10.002.
13467581.2021.2007105. Sharafi, P., M. N. S. Hadi, and L. H. Teh. 2012. “Heuristic
Kuhn, H. W., and A. W. Tucker. 1951. “Nonlinear Approach for Optimum Cost and Layout Design of 3D
Programming.” Berkeley Symposium on Mathematical Reinforced Concrete Frames.” Journal of Structural
Statistics and Probability Engineering 138 (7): 853–863. doi:10.1061/(asce)st.1943-
Kuk Kim, S., W.-K. Hong, K. Hyo-Jin, and J. Tai Kim. 2013. “The 541x.0000508.
Energy Efficient Expansion Remodeling Construction Shin, J., D. W. Scott, L. K. Stewart, and J. S. Jeon. 2020.
Method of Bearing Wall Apartment Buildings with “Multi-hazard Assessment and Mitigation for
pre-cast Composite Structural Systems.” Energy and seismically-deficient RC Building Frames Using
Buildings 66: 714–723. doi:10.1016/j.enbuild.2013.07.080. Artificial Neural Network Models.” Engineering
Lagrange, J. L. 1804. Leçons sur le calcul des fonctions. Paris, Structures 207 (February 2019): 110204. doi:10.1016/j.
France: Imperiale. engstruct.2020.110204.
Loads, M. D., and O. Structures. 2017. “Minimum Design Sirotti, S., M. Pelliciari, F. Di Trapani, B. Briseghella, G. Carlo
Loads and Associated Criteria for Buildings and Other Marano, C. Nuti, and A. M. Tarantino. 2021. “Development
Structures.” Minimum Design Loads and Associated and Validation of New Bouc–Wen Data-Driven Hysteresis
Criteria for Buildings and Other Structures. doi:10.1061/ Model for Masonry Infilled RC Frames.” Journal of
9780784414248. Engineering Mechanics 147 (11): 1–15. doi:10.1061/(asce)
MathWorks. 2022a. “Deep Learning Toolbox: User’s Guide em.1943-7889.0002001.
(R2022a).” Accessed 26 July 2012. https://www.math Srinivas, V., and K. Ramanjaneyulu. 2007. “An Integrated
works.com/help/pdf_doc/deeplearning/nnet_ug.pdf Approach for Optimum Design of Bridge Decks Using
MathWorks. 2022a. “Global Optimization: User’s Guide Genetic Algorithms and Artificial Neural Networks.”
(R2022a).” Accessed 26 July 2012. https://www.math Advances in Engineering Software 38 (7): 475–487. doi:10.
works.com/help/pdf_doc/gads/gads.pdf 1016/j.advengsoft.2006.09.016.
MathWorks. 2022a. “MATLAB (R2022a).” Upton, G., and I. Cook. 2014. A Dictionary of Statistics 3e. UK:
MathWorks. 2022a. “Optimization Toolbox: Documentation Oxford university press.
(R2022a).” Accessed July 26, 2022. https://uk.mathworks. Villarrubia, G., J. F. De Paz, P. Chamoso, and F. De la Prieta.
com/help/optim/ 2018. “Artificial Neural Networks Used in Optimization
MathWorks. 2022a. “Parallel Computing Toolbox: Problems.” Neurocomputing 272: 10–16. doi:10.1016/j.neu
Documentation (R2022a).” Accessed 26 July 2022. com.2017.04.075.
https://uk.mathworks.com/help/parallel-computing/ Yeo, D., and F. A. Potra. 2015. “Sustainable Design of
MathWorks. 2022a. “Statistics and Machine Learning Reinforced Concrete Structures through CO2 Emission
Toolbox: Documentation (R2022a).” Accessed 26 July Optimization.” Journal of Structural Engineering 141 (3).
2022. https://uk.mathworks.com/help/stats/ doi:10.1061/(asce)st.1943-541x.0000888.
Paya-Zaforteza, I., V. Yepes, A. Hospitaler, and Zadeh, L. 1963. “Optimality and non-scalar-valued
F. González-Vidosa. 2009. “CO2-optimization of Performance Criteria.” IEEE Transactions on Automatic
Reinforced Concrete Frames by Simulated Control 8 (1): 59–60. doi:10.1109/TAC.1963.1105511.
Annealing.” Engineering Structures 31 (7): 1501–1508. Zou, X. K., C. M. Chan, G. Li, and Q. Wang. 2007.
doi:10.1016/j.engstruct.2009.02.034. “Multiobjective Optimization for Performance-Based
Pelliciari, M., B. Briseghella, F. Tondolo, L. Veneziano, C. Nuti, Design of Reinforced Concrete Frames.” Journal of
R. Greco, D. Lavorato, and A. M. Tarantino. 2020. Structural Engineering 133 (10): 1462–1474. doi:10.1061/
“A Degrading Bouc–Wen Model for the Hysteresis of (asce)0733-9445(2007)133:10(1462).