Machine Learning Applications in Sustainable Buildings

A special issue of Buildings (ISSN 2075-5309). This special issue belongs to the section "Building Structures".

Deadline for manuscript submissions: 29 August 2024 | Viewed by 9048

Special Issue Editors

Department of Structural Engineering, National Technical University of Athens, Zografou, 15780 Athens, Greece
Interests: earthquake engineering; structural analysis; structural design; dynamic analysis; numerical analysis and modeling; finite element analysis; computational mechanics; machine learning
Department of Civil Engineering, Chonnam National University, Yongbong-ro 77, Buk-gu, Gwangju 61186, Republic of Korea
Interests: finite element simulation; structural analysis; steel structures; steel and concrete composite structures; machine learning; optimization
Faculty of Civil Engineering, Thuyloi University, 175 Tay Son, Dong Da, Hanoi, Vietnam
Interests: machine learning; optimization; nonlinear analysis; steel structures; reliability

Special Issue Information

Dear Colleagues,

Structural design requires an amount of numerical computations with which predictions of response are made in order to evaluate if the structure satisfies certain criteria. The calculations required for this purpose are performed by analyzing deterministic models of the structure under question. However, with ongoing technological development, the variety of constraints and limitations that an acceptable design must satisfy have increased in number and complexity. Indeed, these sometimes cannot be afforded by traditional deterministic models. Therefore, a need has emerged for advanced ways of predicting structural response which are capable of processing large amounts of data and using these data to increase prediction accuracy. Recently, machine learning (ML), amongst the most successful branches of artificial intelligence, has emerged as a potential tool for predicting structural engineering behavior. Due to their capacity in solving complex nonlinear structural systems under extreme conditions, ML models are capable of making predictions towards establishing a sustainable built environment.

Although this Special Issue covers machine learning methods, other relevant artificial intelligence (AI) methods are also welcome, similar, or related to the following:

  • Machine learning algorithms;
  • Deep learning algorithms;
  • Artificial neural networks;
  • Regression, classification, clustering;
  • Supervised, unsupervised, and reinforcement learning;
  • Metaheuristic algorithms;
  • Model reduction techniques.

This Issue calls for papers which propose new methods applied in sustainable buildings including but not limited to the following:

  • Sustainable structures;
  • Structural safety assessment;
  • Structural strength prediction;
  • Structural damage detection;
  • Structural health monitoring;
  • Structural and material optimization;
  • Material properties prediction;
  • Structural control;
  • Non-destructive structure testing;
  • Structural analysis and design;
  • Environmental engineering.

Dr. George Papazafeiropoulos
Dr. Quang-Viet Vu
Dr. Viet-Hung Truong
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Buildings is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • machine learning
  • artificial intelligence
  • optimization
  • structural engineering
  • sustainable building

Published Papers (8 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

21 pages, 1051 KiB  
Article
Priority Needs for Facilities of Office Buildings in Thailand: A Copula-Based Ordinal Regression Model with Machine Learning Approach
by Jittaporn Sriboonjit, Jittima Singvejsakul, Worapon Yamaka, Sukrit Thongkairat, Songsak Sriboonchitta and Jianxu Liu
Buildings 2024, 14(3), 735; https://doi.org/10.3390/buildings14030735 - 08 Mar 2024
Viewed by 348
Abstract
In the rapidly evolving business landscape of Thailand, the design and facilities of office buildings play a crucial role in enhancing employee satisfaction and productivity. This study seeks to answer the question: “How can office building facilities be optimized to meet the diverse [...] Read more.
In the rapidly evolving business landscape of Thailand, the design and facilities of office buildings play a crucial role in enhancing employee satisfaction and productivity. This study seeks to answer the question: “How can office building facilities be optimized to meet the diverse preferences of occupants in Thailand, thereby improving their satisfaction and productivity”? This study employs a copula-based ordinal regression model combined with machine learning techniques to investigate the determinants of facility preferences in office buildings in Thailand. By analyzing data from 372 office workers in Bangkok, we identify the factors influencing facility needs and preferences, and measure the correlation between these preferences. Our findings reveal that safety and security are the highest-rated amenities, indicating their importance in the workplace. The findings reveal distinct preferences across demographic groups: age negatively influences the demand for certain amenities like lounges, while higher education levels increase the preference for cafeteria services. Employees in smaller firms show a higher preference for lounges and fitness centers but lower for restaurants and cafeterias. Interestingly, the size of the enterprise does not significantly affect preferences for fundamental facilities like security and cleaning. The study also uncovers the significant role of gender and income in shaping preferences for certain facilities. These results suggest that while basic amenities are universally valued, luxury or leisure-oriented facilities are more appreciated in smaller, possibly more community-focused work environments. This study highlights the need for tailored facility management in office buildings, considering the diverse needs of different employee groups, which has significant implications for enhancing workplace satisfaction and productivity. Full article
(This article belongs to the Special Issue Machine Learning Applications in Sustainable Buildings)
Show Figures

Figure 1

30 pages, 10895 KiB  
Article
Failure Mode Identification and Shear Strength Prediction of Rectangular Hollow RC Columns Using Novel Hybrid Machine Learning Models
by Viet-Linh Tran, Tae-Hyung Lee, Duy-Duan Nguyen, Trong-Ha Nguyen, Quang-Viet Vu and Huy-Thien Phan
Buildings 2023, 13(12), 2914; https://doi.org/10.3390/buildings13122914 - 22 Nov 2023
Cited by 1 | Viewed by 589
Abstract
Failure mode identification and shear strength prediction are critical issues in designing reinforced concrete (RC) structures. Nevertheless, specific guidelines for identifying the failure modes and for accurate predictions of the shear strength of rectangular hollow RC columns are not provided in design codes. [...] Read more.
Failure mode identification and shear strength prediction are critical issues in designing reinforced concrete (RC) structures. Nevertheless, specific guidelines for identifying the failure modes and for accurate predictions of the shear strength of rectangular hollow RC columns are not provided in design codes. This study develops hybrid machine learning (ML) models to accurately identify the failure modes and precisely predict the shear strength of rectangular hollow RC columns. For this purpose, 121 experimental results of such columns are collected from the literature. Eight widely used ML models are employed to identify the failure modes and predict the shear strength of the column. The moth-flame optimization (MFO) algorithm and five-fold cross-validation are utilized to fine-tune the hyperparameters of the ML models. Additionally, seven empirical formulas are adopted to evaluate the performance of regression ML models in predicting the shear strength. The results reveal that the hybrid MFO-extreme gradient boosting (XGB) model outperforms others in both classifying the failure modes (accuracy of 93%) and predicting the shear strength (R2 = 0.996) of hollow RC columns. Additionally, the results indicate that the MFO-XGB model is more accurate than the empirical models for shear strength prediction. Moreover, the effect of input parameters on the failure modes and shear strength is investigated using the Shapley Additive exPlanations method. Finally, an efficient web application is developed for users who want to use the results of this study or update a new dataset. Full article
(This article belongs to the Special Issue Machine Learning Applications in Sustainable Buildings)
Show Figures

Figure 1

25 pages, 11862 KiB  
Article
Binary Comprehensive Learning Particle Swarm Optimization Approach for Optimal Design of Nonlinear Steel Structures with Standard Sizes
by Rut Su, Sawekchai Tangaramvong, Thu Huynh Van, Atitaya Chaiwongnoi and Chongmin Song
Buildings 2023, 13(8), 1988; https://doi.org/10.3390/buildings13081988 - 03 Aug 2023
Viewed by 741
Abstract
This paper proposes the binary comprehensive learning particle swarm optimization (BCLPSO) method to determine the optimal design for nonlinear steel structures, adopting standard member sizes. The design complies with the AISC-LRFD standard specifications. Moreover, the sizes and layouts of cross-brace members, appended to [...] Read more.
This paper proposes the binary comprehensive learning particle swarm optimization (BCLPSO) method to determine the optimal design for nonlinear steel structures, adopting standard member sizes. The design complies with the AISC-LRFD standard specifications. Moreover, the sizes and layouts of cross-brace members, appended to the steel frames, are simultaneously optimized. Processing this design is as challenging as directly solving the nonlinear integer programming problem, where any solution approaches are often trapped into local optimal pitfalls or even do not converge within finite times. Herein, the BCLPSO method incorporates not only a comprehensive learning technique but also adopts a decoding process for discrete binary variables. The former ascertains the cross-positions among the sets of best swarm particles at each dimensional space. The latter converts design variables into binary bit-strings. This practice ensures that local optimal searches and premature termination during optimization can be overcome. The influence of an inertial weight parameter on the BCLPSO approach is investigated, where the value of 0.98 is recommended. The accuracy and robustness of the proposed method are illustrated through several benchmarks and practical structural designs. These indicate that the lowest minimum total design weight (some 3% reduction as compared to the benchmark) can be achieved of about 40% lower than the total number of analyses involved. Full article
(This article belongs to the Special Issue Machine Learning Applications in Sustainable Buildings)
Show Figures

Figure 1

21 pages, 7482 KiB  
Article
Effects of Superplasticizer and Water–Binder Ratio on Mechanical Properties of One-Part Alkali-Activated Geopolymer Concrete
by Thanh-Tung Pham, Ngoc-Linh Nguyen, Tuan-Trung Nguyen, Trung-Tu Nguyen and Thai-Hoan Pham
Buildings 2023, 13(7), 1835; https://doi.org/10.3390/buildings13071835 - 20 Jul 2023
Cited by 1 | Viewed by 1165
Abstract
This study presents an investigation of the mix proportion and mechanical properties of one-part alkali-activated geopolymer concrete (GPC). The procedure for determining the mix proportion of one-part alkali-activated GPC, which uses a solid alkali activator in crystal form, is proposed. The proposed procedure [...] Read more.
This study presents an investigation of the mix proportion and mechanical properties of one-part alkali-activated geopolymer concrete (GPC). The procedure for determining the mix proportion of one-part alkali-activated GPC, which uses a solid alkali activator in crystal form, is proposed. The proposed procedure was applied to a series of mixed proportions of GPC with different amounts of solid crystalline alkali activator (AA), water (W), and superplasticizer (SP), using the ratio between them to the total amount of binder (B, fly ash, and granulated blast furnace slag) by weight in order to evaluate their effect on the workability and compressive strength of the GPC. The slump, compressive and tensile strength, and elastic modulus of the one-part alkali-activated GPC were tested in various ways. The test results showed that solid crystalline alkali activators, water, and superplasticizers have significant effects on both the workability and compressive strength of GPC. The amount of one-part alkali activator should not exceed 12.0% of the total binder amount by weight (AA/B = 0.12) in order not to lose the workability of GPC. The minimum W–B ratio should be at least 0.43 to ensure the workability of the sample when no superplasticizer is added. An amount of 2.5% can be considered as the upper bound when using superplasticizer-based polysilicate for GPC. In addition, the elastic modulus and various types of tensile strength values of the one-part alkali-activated GPC were evaluated and compared with that predicted from compressive strength using equations given by two common ACI and Eurocode2 codes for ordinary Portland cement (OPC) concrete. Modifications of the equations showing the relationships between splitting tensile strength and compressive strength, as well as between elastic modulus and compressive strength and the development of compressive strength under the time provided by ACI and Eurocode2 for OPC concrete, were also made for one-part alkali-activated GPC. Full article
(This article belongs to the Special Issue Machine Learning Applications in Sustainable Buildings)
Show Figures

Graphical abstract

14 pages, 3283 KiB  
Article
Experimental Study on Flexural Behavior of RC–UHPC Slabs with EPS Lightweight Concrete Core
by Tuan-Anh Cao, Manh-Tuan Nguyen, Thai-Hoan Pham and Dang-Nguyen Nguyen
Buildings 2023, 13(6), 1372; https://doi.org/10.3390/buildings13061372 - 24 May 2023
Viewed by 977
Abstract
This paper presents an experimental investigation that focuses on the flexural behavior of an innovative reinforced concrete–ultra-high performance concrete slab with an expanded polystyrene lightweight concrete core. This type of slab is proposed to serve the semi-precast solution, in which the bottom layer [...] Read more.
This paper presents an experimental investigation that focuses on the flexural behavior of an innovative reinforced concrete–ultra-high performance concrete slab with an expanded polystyrene lightweight concrete core. This type of slab is proposed to serve the semi-precast solution, in which the bottom layer is ultra-high performance concrete working as a formwork during the construction of semi-precast slab, the expanded polystyrene lightweight concrete layer is used for the reduction of structure self-weight, and the top layer is normal concrete designed to withstand compressive stress when the slab is loaded. Two similar large-scale specimens with dimensions of 6200 mm × 1000 mm × 210 mm were fabricated and tested under four-point bending conditions to investigate the flexural behavior of composite slab. Test results indicated that three different layers of materials can work effectively together without separation. The bottom ultra-high performance concrete layer leads to the high ductility of the slab and has a good effect in limiting the widening of the crack width by forming other cracks. According to design code ACI 544.4R, a modified distribution stress diagram on the composite section was proposed and proven to be suitable for the prediction of flexural strength of the composite section with an error of 3.4% compared to the experimental result. The effect of the ultra-high performance concrete layer on the flexural strength of the composite slab was clearly demonstrated, and for the case in this study, the ultra-high performance concrete layer improves the flexural strength of the slab by about 11.5%. Full article
(This article belongs to the Special Issue Machine Learning Applications in Sustainable Buildings)
Show Figures

Figure 1

16 pages, 16634 KiB  
Article
A Multi-Layer Blowout Model for the Tunneling Face Stability Analysis
by Minh-Ngan Vu, Minh-Ngoc Vu, Duc-Tho Pham, Tuan Nguyen-Sy, Quoc-Bao Nguyen and Viet-Duc Dang
Buildings 2023, 13(6), 1362; https://doi.org/10.3390/buildings13061362 - 23 May 2023
Cited by 1 | Viewed by 1110
Abstract
The stability of the tunnel face during tunneling is one of the major criteria for the design and construction of the tunnel. Collapse and blowout are two modes of tunnel face failure during the excavation. The cover-to-diameter ratio is one of the main [...] Read more.
The stability of the tunnel face during tunneling is one of the major criteria for the design and construction of the tunnel. Collapse and blowout are two modes of tunnel face failure during the excavation. The cover-to-diameter ratio is one of the main parameters controlling these failure modes. Several analytical solutions have been proposed to estimate the range of support pressure applied on the tunnel face to avoid both the collapse and the blowout. However, most of those models deal with homogeneous soils. This paper aims at proposing an analytical model to predict the blowout of the tunneling face of a tunnel in multi-layered soils. The derivation is based on a limit equilibrium analysis, which considers the water tCiable. The proposed model is validated against the real blowout data reported from the tunneling in the Second Heinenoord Tunnel project in the Netherlands. Then, the maximum support pressure exerted on the tunneling face is predicted as a function of the cover-to-diameter ratio, the tunnel diameter, and the water table level for five representative soils. Finally, the model is applied to an underground segment of the Hanoi Metro Line 3 project (in Vietnam) to show the role of the multi-layer aspect. Full article
(This article belongs to the Special Issue Machine Learning Applications in Sustainable Buildings)
Show Figures

Figure 1

25 pages, 5847 KiB  
Article
An Efficient Model for the Coupling Beam Using Damping Devices in Coupled Shear Wall Structures under Earthquake Loads
by Thu-Hien Pham, Hai-Quang Nguyen, Tien-Chuong Nguyen and Anh-Dung Nguyen
Buildings 2023, 13(4), 941; https://doi.org/10.3390/buildings13040941 - 02 Apr 2023
Viewed by 1616
Abstract
This paper proposes a new element for modeling the energy-dissipation coupling beam to analyze the coupled shear wall structure under seismic loading. The new beam element includes 2 rigid beams and an energy dissipation device in the middle. The element stiffness matrix is [...] Read more.
This paper proposes a new element for modeling the energy-dissipation coupling beam to analyze the coupled shear wall structure under seismic loading. The new beam element includes 2 rigid beams and an energy dissipation device in the middle. The element stiffness matrix is derived based on principles of nonlinear mechanics. A procedure of the incremental-iterative solution is built using the Newmark method and adopted for solving the nonlinear equation of motion. A computer program using Matlab is developed to analyze the behavior of frame analogy which is modeled from the couped shear wall structure. Several numerical examples are presented to verify the developed program with the commercial finite element package SAP2000. The numerical results proved that the proposed program is efficient and reliable. The proposed element and program are then applied to analyze a 30-story coupled shear wall structure with energy dissipation devices. As a result, the locations of the device that provide effective seismic resistance for a 30-story coupled shear wall structure are in the region from the 5th to the 15th floor or assigned on all floors. Full article
(This article belongs to the Special Issue Machine Learning Applications in Sustainable Buildings)
Show Figures

Figure 1

26 pages, 14733 KiB  
Article
Performance of Six Metaheuristic Algorithms for Multi-Objective Optimization of Nonlinear Inelastic Steel Trusses
by Truong-Son Cao, Thi-Thanh-Thuy Nguyen, Van-Son Nguyen, Viet-Hung Truong and Huu-Hue Nguyen
Buildings 2023, 13(4), 868; https://doi.org/10.3390/buildings13040868 - 26 Mar 2023
Cited by 5 | Viewed by 1425
Abstract
This paper presents a multi-objective optimization of steel trusses using direct analysis. The total weight and the inter-story drift or displacements of the structure were two conflict objectives, while the constraints relating to strength and serviceability load combinations were evaluated using nonlinear inelastic [...] Read more.
This paper presents a multi-objective optimization of steel trusses using direct analysis. The total weight and the inter-story drift or displacements of the structure were two conflict objectives, while the constraints relating to strength and serviceability load combinations were evaluated using nonlinear inelastic and nonlinear elastic analyses, respectively. Six common metaheuristic algorithms such as nondominated sorting genetic algorithm-II (NSGA-II), NSGA-III, generalized differential evolution (GDE3), PSO-based MOO using crowding, mutation, and ε-dominance (OMOPSO), improving the strength Pareto evolutionary algorithm (SPEA2), and multi-objective evolutionary algorithm based on decomposition (MOEA/D) were applied to solve the developed MOO problem. Four truss structures were studied including a planar 10-bar truss, a spatial 72-bar truss, a planar 47-bar powerline truss, and a planar 113-bar truss bridge. The numerical results showed a nonlinear relationship and inverse proportion between the two objectives. Furthermore, all six algorithms were efficient at finding feasible optimal solutions. No algorithm outperformed the others, but NSGA-II and MOEA/D seemed to be better at both searching Pareto and anchor points. MOEA/D was also more stable and yields a better solution spread. OMOPSO was also good at solution spread, but its stability was worse than MOEA/D. NSGA-III was less efficient at finding anchor points, although it can effectively search for Pareto points. Full article
(This article belongs to the Special Issue Machine Learning Applications in Sustainable Buildings)
Show Figures

Figure 1

Back to TopTop