A collaborative machine learning-optimization algorithm to improve the finite element model updating of civil engineering structures

2020 ◽  
Vol 225 ◽  
pp. 111327
Author(s):  
Javier Naranjo-Pérez ◽  
María Infantes ◽  
Javier Fernando Jiménez-Alonso ◽  
Andrés Sáez
Keyword(s):  
Machine Learning ◽  
Finite Element ◽  
Finite Element Model ◽  
Optimization Algorithm ◽  
Civil Engineering ◽  
Model Updating ◽  
Element Model ◽  
Finite Element Model Updating ◽  
Engineering Structures ◽  
The Finite Element Model

Structural damage identification via physics-guided machine learning: a methodology integrating pattern recognition with finite element model updating

2020 ◽  
pp. 147592172092748 ◽  
Author(s):  
Zhiming Zhang ◽  
Chao Sun
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Finite Element ◽  
Finite Element Model ◽  
Health Monitoring ◽  
Damage Identification ◽  
Model Updating ◽  
Element Model ◽  
Data Driven ◽  
Finite Element Model Updating

Structural health monitoring methods are broadly classified into two categories: data-driven methods via statistical pattern recognition and physics-based methods through finite elementmodel updating. Data-driven structural health monitoring faces the challenge of data insufficiency that renders the learned model limited in identifying damage scenarios that are not contained in the training data. Model-based methods are susceptible to modeling error due to model idealizations and simplifications that make the finite element model updating results deviate from the truth. This study attempts to combine the merits of data-driven and physics-based structural health monitoring methods via physics-guided machine learning, expecting that the damage identification performance can be improved. Physics-guided machine learning uses observed feature data with correct labels as well as the physical model output of unlabeled instances. In this study, physics-guided machine learning is realized with a physics-guided neural network. The original modal-property based features are extended with the damage identification result of finite element model updating. A physics-based loss function is designed to evaluate the discrepancy between the neural network model output and that of finite element model updating. With the guidance from the scientific knowledge contained in finite element model updating, the learned neural network model has the potential to improve the generality and scientific consistency of the damage detection results. The proposed methodology is validated by a numerical case study on a steel pedestrian bridge model and an experimental study on a three-story building model.

scholarly journals Finite Element Model Updating of Reinforced Concrete Beams with Honeycomb Damage

2012 ◽  
Vol 58 (2) ◽  
pp. 135-151 ◽  
Author(s):  
Z. Ismail
Keyword(s):  
Finite Element ◽  
Reinforced Concrete ◽  
Finite Element Model ◽  
Model Updating ◽  
Element Model ◽  
Significant Loss ◽  
Reinforced Concrete Beams ◽  
Finite Element Model Updating ◽  
Finite Element Models ◽  
The Finite Element Model

Abstract A method of detecting honeycombing damage in a reinforced concrete beam using the finite element model updating technique was proposed. A control beam and two finite element models representing different severity of damage were constructed using available software and the defect parameters were updated. Analyses were performed on the finite element models to approximate the modal parameters. A datum and a control finite element model to match the datum test beams with honeycombs were prepared. Results from the finite element model were corrected by updating the Young’s modulus and the damage parameters. There was a loss of stiffness of 3% for one case, and a loss of 7% for another. The more severe the damage, the higher the loss of stiffness. There was no significant loss of stiffness by doubling the volume of the honeycombs.

Sign in / Sign up

Export Citation Format

Share Document