Optimization of nonlinear temperature gradient on eigenfrequency using genetic algorithm for reinforced concrete bridge structural health
College
Gokongwei College of Engineering
Department/Unit
Manufacturing Engineering and Management
Document Type
Article
Source Title
EAI/Springer Innovations in Communication and Computing
First Page
141
Last Page
151
Publication Date
1-1-2020
Abstract
Structural damage detection, based on global dynamic parameters, has received considerable attention from civil engineering and even by the local communities. The former sector is facing problems on providing structural integrity to its actual bridge construction due to climate change. Changes in the physical properties of structure such as boundary conditions, stiffness, and mass with respect to modal frequency are customarily studied; however, the unobservable factors such as wind force, humidity and, the most important, temperature must be given weight on analysis. In this study, the suitability of combined approach of supervised machine learning principal component analysis (PCA) and the metaheuristic genetic algorithm (GA) in generating the optimum condition for a reinforced concrete bridge was determined. The parameters that were optimized are the bridge and environment temperatures. These parameters were some of the essential bridge structural health parameters as they have impact on the boundary conditions and properties of materials. This entails that the developed model involves eigenfrequencies as function of temperatures only, which is a minimal parameter approach. The system selected the 50 fittest individuals based on the fitness score and then proceeded to the recombination process. The mutation with rate of 0.01 was applied to test if the solution is the global one. When the iterations had reached the required numbers of generation, the system stopped and gave the optimum condition for a bridge. The GA results showed that the optimum condition for a reinforced concrete bridge needs bridge temperature of 9.578 °C and environment temperature of −8.571 °C. Aside from these temperature values, the bridge is vulnerable to breakage or any damage condition. © Springer Nature Switzerland AG 2020.
html
Digitial Object Identifier (DOI)
10.1007/978-3-030-20904-9_11
Recommended Citation
Concepcion, R. S., Ilagan, L. C., & Valenzuela, I. C. (2020). Optimization of nonlinear temperature gradient on eigenfrequency using genetic algorithm for reinforced concrete bridge structural health. EAI/Springer Innovations in Communication and Computing, 141-151. https://doi.org/10.1007/978-3-030-20904-9_11
Disciplines
Civil Engineering | Manufacturing
Keywords
Concrete bridges—Foundations and piers; Genetic algorithms
Upload File
wf_yes