4.7 Article

Multi-objective design of post-tensioned concrete road bridges using artificial neural networks

Journal

STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
Volume 56, Issue 1, Pages 139-150

Publisher

SPRINGER
DOI: 10.1007/s00158-017-1653-0

Keywords

Multi-objective harmony search; Artificial neural networks; Post-tensioned concrete bridges; Durability; Safety

Funding

  1. Spanish Ministry of Economy and Competitiveness
  2. FEDER (BRIDLIFE Project) [BIA2014-56574-R]
  3. Universitat Politecnica de Valencia [PAID-02-15]

Ask authors/readers for more resources

In order to minimize the total expected cost, bridges have to be designed for safety and durability. This paper considers the cost, the safety, and the corrosion initiation time to design post-tensioned concrete box-girder road bridges. The deck is modeled by finite elements based on problem variables such as the cross-section geometry, the concrete grade, and the reinforcing and post-tensioning steel. An integrated multi-objective harmony search with artificial neural networks (ANNs) is proposed to reduce the high computing time required for the finite-element analysis and the increment in conflicting objectives. ANNs are trained through the results of previous bridge performance evaluations. Then, ANNs are used to evaluate the constraints and provide a direction towards the Pareto front. Finally, exact methods actualize and improve the Pareto set. The results show that the harmony search parameters should be progressively changed in a diversification-intensification strategy. This methodology provides trade-off solutions that are the cheapest ones for the safety and durability levels considered. Therefore, it is possible to choose an alternative that can be easily adjusted to each need.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

Article Engineering, Civil

Life-Cycle Risk-Based Optimal Maintenance Strategy for Bridge Networks Subjected to Corrosion and Seismic Hazards

Xu Han, Dan M. M. Frangopol

Summary: Structural deterioration can be caused by multiple mechanisms, such as aging, corrosion, and fatigue, as well as sudden events like earthquakes and hurricanes. These mechanisms have a significant impact on the performance indicators of structural components and systems throughout their lifespan. Most existing studies on structural deterioration focus on the effect of a single mechanism in a deterministic context, so further research is needed to understand the joint effects of multiple deterioration mechanisms in a probabilistic context. This paper presents a risk-based optimal management strategy that considers corrosion and seismic hazards in a bridge network.

JOURNAL OF BRIDGE ENGINEERING (2023)

Article Engineering, Civil

Structural identification via the inference of the stochastic volatility model conditioned on the time-dependent bridge deflection

Siyi Jia, Mitsuyoshi Akiyama, Bing Han, Huibing Xie, Dan M. Frangopol

Summary: This paper presents an inference framework for a stochastic volatility model (SVM) conditioned on the time-dependent deflection of prestressed concrete bridges (PSCBs). The framework includes a cyclic Markov chain Monte Carlo (MCMC) sampler to draw samples from the joint posterior distribution of the unobserved state variables and volatility parameters. The proposed framework supports accurate probabilistic analysis of the time-dependent deflection of PSCBs.

STRUCTURAL SAFETY (2023)

Article Chemistry, Physical

A Parametric Study of Optimum Road Modular Hinged Frames by Hybrid Metaheuristics

Andres Ruiz-Velez, Julian Alcala, Victor Yepes

Summary: This paper studies cost-optimal road modular hinged frames and evaluates their performance through three hybrid metaheuristics. The experiments involve varying the horizontal span and earth cover to study different structural configurations. The calibrated methodology is then applied to obtain optimal cost frames for each configuration. Regression analysis is used to study the economic, environmental, and geometrical characteristics of the optimum structures, providing valuable tools for calculating costs, emissions, energy consumption, and geometric properties. The optimum structures exhibit slender and densely reinforced designs, solving shear reinforcement issues with localized increases in longitudinal reinforcement.

MATERIALS (2023)

Article Chemistry, Physical

Optimal Design of Sustainable Reinforced Concrete Precast Hinged Frames

Andres Ruiz-Velez, Julian Alcala, Victor Yepes

Summary: The study focuses on optimizing material usage in the construction of precast hinged frames to achieve sustainable development. Custom software was developed using Python programming language to calculate, verify, and optimize the structure using metaheuristic techniques. Three algorithms were applied to achieve non-traditional designs that maximize the use of natural resources while maintaining a restricted final cost. By reducing upper slab and lateral wall depth and using dense passive reinforcement, the optimized designs reduced the structure's final cost by up to 24% and associated emissions by over 30%.

MATERIALS (2023)

Article Education, Scientific Disciplines

Enhancing a Comprehensive View of the Infrastructure Life Cycle through Project-Based Learning

Tatiana Garcia-Segura, Laura Montalban-Domingo, Amalia Sanz-Benlloch, Alberto Domingo, Joaquin Catala, Eugenio Pellicer

Summary: This paper describes a teaching innovation project that uses project-based learning to familiarize civil engineering students with their future roles and tasks in the infrastructure life cycle. Results show that students are aware of their learning improvement and are able to develop the necessary professional competencies.

JOURNAL OF CIVIL ENGINEERING EDUCATION (2023)

Article Engineering, Civil

A novel combined experimental-machine learning approach to estimate the probabilistic capacity of RC beams with spatially correlated rebar corrosion in transverse and longitudinal directions

Supasit Srivaranun, Mitsuyoshi Akiyama, Taiki Yamada, Dan M. Frangopol, Jiyu Xin

Summary: Chloride-induced corrosion of tensile rebars in reinforced concrete structures causes cracking in the concrete surface along corroded rebars. The width of these cracks could provide valuable information for estimating the amount of steel weight loss inside concrete beams. However, the distribution of cracks in beams with multiple rebars is affected by both the corrosion expansion of the corresponding rebar and that of adjacent rebars, resulting in a complex nonlinear relationship between crack width and amount of steel corrosion. A combined experimental-machine learning approach using generative adversarial networks (GANs) is developed in this study to estimate steel corrosion distributions in RC beams. A pix2pix network is trained using a dataset of steel weight loss generated based on random field theory and the distributions of corrosion crack widths constructed using finite element analysis. Monte Carlo-based FE analysis is then used to obtain the probability density function (PDF) of the flexural capacity for corroded RC beams. A case study is presented to investigate the effect of observed crack width distributions on the PDF of the flexural capacity for aging RC beams with spatially correlated rebar corrosion in transverse and longitudinal directions.

ENGINEERING STRUCTURES (2023)

Article Engineering, Civil

Application of first-order reliability method with orthogonal plane sampling for high-dimensional series system reliability analysis

Weiming Chen, Changqing Gong, Ziqi Wang, Dan M. Frangopol

Summary: The increasing complexity of modern engineering systems has led to a shift in research focus towards system reliability with interdependent components. This paper proposes an improved FORM-based method, integrating orthogonal plane sampling, to tackle the curse of dimensionality for high-dimensional systems. The method constructs secant hyperplanes using orthogonal plane samples and computes the series system reliability as a high-dimensional multi-normal integral. Numerical examples demonstrate the accuracy and efficiency of the proposed method, which outperforms Monte Carlo simulation and conventional FORM.

ENGINEERING STRUCTURES (2023)

Article Construction & Building Technology

Experimental Research on Diseases of Emulsified Asphalt Mortar Board for Ballastless Tracks

Zhi Wu Zhou, Julian Alcala, Victor Yepes

Summary: The stability, comfort, and safety of high-speed railway systems are crucial worldwide, with multiorder elastic modes of components being the key factors. Ensuring the quality of the backfill layer of flexible cement-emulsified asphalt mortar (CA mortar) to reduce elastic vibration in the car body is the core technology. This research, based on the manufacturability verification of the Beijing-Shanghai high-speed railway, used four theoretical model methods to improve the performance indicators of CA mortar. The research concluded that the best mix ratio, high gas content, and poor fluidity are the core factors affecting the technical indicators of mortar and quality control. The research findings provided valuable theoretical methods and practical experience data for ensuring the quality and qualified indicators of mortar, leading to the prevention of acute diseases and ensuring safe operation of high-speed railways.

JOURNAL OF MATERIALS IN CIVIL ENGINEERING (2023)

Article Engineering, Civil

Probabilistic structural identification and condition assessment of prestressed concrete bridges based on Bayesian inference using deflection measurements

Siyi Jia, Mitsuyoshi Akiyama, Bing Han, Dan M. Frangopol

Summary: This paper presents a model-based probabilistic structural identification method using the deflection of prestressed concrete bridges as observational information. The method incorporates a stochastic process for creep development and a stochastic field for structural rigidity. The Hamiltonian Markov chain Monte Carlo algorithm is used to derive the posterior distributions of the high-dimensional state variables. A case bridge is used as an example to update the state variables and perform probabilistic condition assessment.

STRUCTURE AND INFRASTRUCTURE ENGINEERING (2023)

Article Construction & Building Technology

IABSE Survey of Implemented Decision-making Models used by Public and Private Owners/Operators of Road- and Railway Infrastructures

Alfred Strauss, Andre Orcesi, Andreas Lampropoulos, Bruno Briseghella, Dan M. Frangopol, Helder S. Sousa, Joan Casas, Jose C. Matos, Kristian Schellenberg, Matias Valenzuela, Mitsuyoshi Akiyama, Poul Linneberg, Rade Hajdin, Thomas Moser

Summary: Infrastructure systems, such as bridges, play a crucial role in the economic growth and sustainable development of countries. Decision-making in infrastructure management involves a combination of qualitative and quantitative data, models, and expert judgement. However, there is still a gap between implemented decision-making models and research, which calls for further research and training.

STRUCTURAL ENGINEERING INTERNATIONAL (2023)

Article Engineering, Marine

Life-Cycle Cost Assessment Using the Power Spectral Density Function in a Coastal Concrete Bridge

Mehrdad Hadizadeh-Bazaz, Ignacio J. Navarro, Victor Yepes

Summary: In this study, the power spectral density (PSD) method was used to monitor the location and amount of damage caused by chloride ions and to determine the structure's life. The results showed that this method was effective in reducing and optimizing maintenance and repair costs caused by chloride corrosion.

JOURNAL OF MARINE SCIENCE AND ENGINEERING (2023)

Review Engineering, Civil

Metamodel-assisted design optimization in the field of structural engineering: A literature review

Ivan Negrin, Moacir Kripka, Victor Yepes

Summary: Metamodel-assisted optimization is a valuable alternative for expensive structural design optimization procedures. This paper provides an up-to-date literature review on metamodel-assisted structural design optimization (MASDO) with 111 publications and 169 case studies analyzed. The study reveals a limited number of published papers and highlights the importance of statistical analysis for practical recommendations in incorporating metamodeling strategies in future projects.

STRUCTURES (2023)

Article Mathematics

Optimizing Retaining Walls through Reinforcement Learning Approaches and Metaheuristic Techniques

Jose Lemus-Romani, Diego Ossandon, Rocio Sepulveda, Nicolas Carrasco-Astudillo, Victor Yepes, Jose Garcia

Summary: The structural design of civil works is based on empirical knowledge and the experience of design professionals. In this study, a new discretization technique using reinforcement learning and transfer functions is developed to optimize design and reduce associated costs and CO2 emissions. The application of metaheuristic techniques to the retaining wall problem is examined, showing that the use of S-shaped transfer functions consistently yields more robust outcomes.

MATHEMATICS (2023)

Article Chemistry, Physical

Embodied Energy Optimization of Prestressed Concrete Road Flyovers by a Two-Phase Kriging Surrogate Model

Lorena Yepes-Bellver, Alejandro Brun-Izquierdo, Julian Alcala, Victor Yepes

Summary: This study establishes a methodology for optimizing embodied energy in the construction of lightened road flyovers. The methodology includes a two-phase process of statistical sampling and optimization modeling to reduce energy cost and improve efficiency.

MATERIALS (2023)

Article Engineering, Industrial

An error-based stopping criterion for spherical decomposition-based adaptive Kriging model and rare event estimation

Yu Zhang, You Dong, Dan M. Frangopol

Summary: This paper proposes a new stopping criterion for the adaptive Kriging model with SDMCS, aiming to reduce the computational effort while maintaining accuracy in reliability analysis.

RELIABILITY ENGINEERING & SYSTEM SAFETY (2024)

No Data Available