Multi-objective integrated optimization study of prefabricated building projects introducing sustainable levels

Peng, Junlong; Feng, Yong; Zhang, Qi; Liu, Xiangjun

doi:10.1038/s41598-023-29881-6

Cited by 16 publications

(9 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In such cases, AI-based optimization methods can be employed to generate Pareto e cient solutions (the Pareto front). In this study, the non-dominated sorting Genetic Algorithm (NSGA-II) 17,71 is employed, which has shown to provide e cient solutions to complex multi-objective construction engineering and management optimization problems 72 . For this, two case studies from real-world SkS projects are utilized as baseline for generative optimization.…”

Section: Generative Modeling and Optimizationmentioning

confidence: 99%

Field Information Modeling (FIM)®: Beyond point cloud processing - The case of generative decision support for skeletal spatial structure systems

Maalek

2023

Preprint

View full text Add to dashboard Cite

This study investigated the application of point cloud processing using the Field Information Modeling (FIM)® framework for the generative redesign of existing skeletal space structure systems (SkS). Three new algorithms were proposed to (i) expand FIM® to include generative decision-support; (ii) generate as-built BIM for SkS; and (iii) modularize SkS designs with repeating patterns for optimal production and supply chain management. These algorithms incorporated a host of new AI-inspired methods, including support vector machine (SVM) for decision support; Bayesian optimization for neighborhood definition; Bayesian Gaussian mixture clustering for modularization; and Monte Carlo stochastic multi-criteria decision making (MCDM) for selection of the top Pareto front solutions obtained by the non-dominant sorting Genetic Algorithm (NSGA II). The algorithms were tested and validated on four real-world point cloud datasets to solve two generative modeling problems, namely, engineering design optimization and facility location optimization. It was observed that the proposed Bayesian neighborhood definition outperformed particle swarm and uniform sampling by 34% and 27%, respectively. The proposed SVM-based linear feature detection outperformed k-means and spectral clustering by 56% and 9%, respectively. Finally, the NSGA II algorithm combined with the stochastic MCDM produced diverse “top four” solutions based on project-specific criteria. The results indicate promise for future utilization of the framework to produce training datasets for generative adversarial networks that generate new designs based only on stakeholder requirements.

show abstract

Section: Generative Modeling and Optimizationmentioning

confidence: 99%

Field Information Modeling (FIM)®: Beyond point cloud processing - The case of generative decision support for skeletal spatial structure systems

Maalek

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In this case, heuristic algorithms are particularly suitable due to this characteristic. Genetic algorithm is a commonly used heuristic algorithm, which is frequently applied in various aspects of the construction industry, such as labor allocation 44 , resource allocation 45 , and building design 46 .…”

Section: Related Workmentioning

confidence: 99%

Optimization of construction safety resource allocation based on evolutionary game and genetic algorithm

Peng,

Zhang,

Feng

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

In the construction industry, ensuring the safety performance of a project relies heavily on the effective allocation of safety resources. As the importance of mental health in the construction industry increases, evolutionary game theory can be used to analyze the interaction mechanism of various factors affecting safety performance during the construction phase. The objective of this paper is to construct an analytical model that combines evolutionary game theory with genetic algorithms from the perspective of Leader-Member Exchange Ambivalence. The model aims to quantify and compare the various factors that influence achieving the expected safety state and identify the specific necessary constraints. Initially, we analyzed the relationships among construction site employees, divided them into superiors and subordinates, and established a game model and payoff matrix based on the research background. Next, we introduced genetic algorithms into the model via the replicator dynamic equation for optimization. We adjusted the coefficients of safety risk level, psychological expected return, moral identity, and other factors to simulate various construction site scenarios. Simulation and optimization results indicate that genetic algorithms provide more accurate reference values for safety resource allocation compared to preset or manually assigned values.

show abstract

“…Generative design (GD) [28][29][30][31] is the process of utilizing artificial intelligence (AI) to generate meaningful heuristic results when either traditional methods fail, or a single solution cannot be obtained (e.g., no single solution exists that satisfies all objectives simultaneously). In such cases, many good solutions (in the case of multi-objective optimization, Pareto front) are generated to solve the optimization problem [32,33].…”

Section: Design Optimization For Sustainabilitymentioning

confidence: 99%

Renovation or Redevelopment: The Case of Smart Decision-Support in Aging Buildings

Maalek

2023

Smart Cities

View full text Add to dashboard Cite

In Germany, as in many developed countries, over 60% of buildings were constructed before 1978, where most are in critical condition, requiring either demolition with plans for redevelopment or renovation and rehabilitation. Given the urgency of climate action and relevant sustainable development goals set by the United Nations, more attention must be shifted toward the various sustainability aspects when deciding on a strategy for the renovation or redevelopment of existing buildings. To this end, this study focused on developing a smart decision support framework for aging buildings based on lifecycle sustainability considerations. The framework integrated digital technological advancements, such as building information modeling (BIM), point clouds processing with field information modeling (FIM)®, and structural optimization, together with lifecycle assessment to evaluate and rate the environmental impact of different solutions. Three sustainability aspects, namely, cost, energy consumption, and carbon emissions, were quantitatively evaluated and compared in two scenarios, namely, renovation, and demolition or deconstruction combined with redevelopment. A real building constructed in 1961 was the subject of the experiments to validate the framework. The result outlined the limitations and advantages of each method in terms of economics and sustainability. It was further observed that optimizing the building design with the goal of reducing embodied energy and carbon in compliance with modern energy standards was crucial to improving overall energy performance. This work demonstrated that the BIM-based framework developed to assess the environmental impact of rehabilitation work in aging buildings can provide effective ratings to guide decision-making in real-world projects.

show abstract

Multi-objective integrated optimization study of prefabricated building projects introducing sustainable levels

Cited by 16 publications

References 35 publications

Field Information Modeling (FIM)®: Beyond point cloud processing - The case of generative decision support for skeletal spatial structure systems

Field Information Modeling (FIM)®: Beyond point cloud processing - The case of generative decision support for skeletal spatial structure systems

Optimization of construction safety resource allocation based on evolutionary game and genetic algorithm

Renovation or Redevelopment: The Case of Smart Decision-Support in Aging Buildings

Contact Info

Product

Resources

About