Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks

Computer Aided Civil and Infrastructure Engineering

The application of structural health monitoring (SHM) systems to civil engineering structures has been a developing studied and practiced topic, that has allowed for a better understanding of structures’ conditions and increasingly lead to a more cost-effective management of those infrastructures In this field, the use of fiber optic sensors has been studied, discussed and practiced with encouraging results The possibility of understanding and monitor the distributed behavior of extensive stretches of critical structures it’s an enormous advantage that distributed fiber optic sensing provides to SHM systems In the past decade, several R & D studies have been performed with the goal of improving the knowledge and developing new techniques associated with the application of distributed optical fiber sensors (DOFS) in order to widen the range of applications of these sensors and also to obtain more correct and reliable data This paper presents, after a brief introduction to the theoretical background of DOFS, the latest developments related with the improvement of these products by presenting a wide range of laboratory experiments as well as an extended review of their diverse applications in civil engineering structures

A review of distributed optical fiber sensors for civil engineering applications

FRP-strengthened RC beams. I: review of debonding strength models

A review of vibration-based damage detection in civil structures : from traditional methods to Machine Learning and Deep Learning applications

The goal of this article is to detect structural damage in the presence of operational and environmental variations using vibration-based damage identification procedures. For this purpose, four ma...

Machine learning algorithms for damage detection under operational and environmental variability

In this paper the results of tests performed on specimens and structural elements made of steel fiber reinforced concrete (SFRC) are presented. Fiber content of the concrete ranged from 0 to 60 kg/m³. Using the results of the uniaxial compression tests performed under displacement control condition, a stress-strain relationship for fiber concrete in compression was derived. Three-point bending tests on notched beams were carried out to simulate the postcracking behavior and to evaluate the fracture energy. Based on the constitutive relationships derived from the experiments, a layered model for the analysis of steel fiber reinforced concrete cross sections was developed. The model performance and the benefits of fiber reinforcement on thin slabs reinforced with steel bars were assessed by carrying out tests on slab strips. The main results are presented and discussed.

/pdf/flexural-behavior-of-sfrc-testing-and-modeling-3p2wflbwng.pdf

Flexural Behavior of SFRC: Testing and Modeling

The real-world structures are subjected to operational and environmental condition changes that impose difficulties in detecting and identifying structural damage. The aim of this report is to detect damage with the presence of such operational and environmental condition changes through the application of the Los Alamos National Laboratory’s statistical pattern recognition paradigm for structural health monitoring (SHM). The test structure is a laboratory three-story building, and the damage is simulated through nonlinear effects introduced by a bumper mechanism that simulates a repetitive impact-type nonlinearity. The report reviews and illustrates various statistical principles that have had wide application in many engineering fields. The intent is to provide the reader with an introduction to feature extraction and statistical modelling for feature classification in the context of SHM. In this process, the strengths and limitations of some actual statistical techniques used to detect damage in the structures are discussed. In the hierarchical structure of damage detection, this report is only concerned with the first step of the damage detection strategy, which is the evaluation of the existence of damage in the structure. The data from this study and a detailed description of the test structure are available for download at: http://institute.lanl.gov/ei/software-and-data/.

/pdf/structural-health-monitoring-algorithm-comparisons-using-2n20jd9zda.pdf

Structural health monitoring algorithm comparisons using standard data sets

An elasto-plastic analysis of anisotropic plates and shells is undertaken by means of the finite element displacement method. A thick shell formulation accounting for shear deformation is considered, which is based on a degenerate three-dimensional continuum element. The accommodation of variable material properties, not only along the surface of the structure but also through the thickness, is made possible by a discrete layered approach. Although isoparametric elements of the Serendipity family give satisfactory solutions for thick and moderately thin shells the results exhibit ‘locking’ for an increasing ratio of span to thickness. To develop a numerical model which is applicable to thick or thin plates and shells, the nine-node Lagrangian element and the Heterosis element are also introduced into the present model. Plastic yielding is based on the Huber-Mises yield surface extended by Hill for anisotropic materials. The yield function is generalized by introducing anisotropic parameters of plasticity which are updated during the material strain hardening history. Numerical examples are presented and compared with available solutions. The effects of anisotropy on these solutions are also discussed.

Anisotropic elasto-plastic finite element analysis of thick and thin plates and shells

In view of the growing use of High Performance Concrete, with large hydration-induced volumetric changes (both thermal and shrinkage related), numerical modelling of concrete at early ages has become an important issue, regarding the possible formation of cracks, with undesirable consequences on aesthetics and structural durability. In this paper a thermo-mechanical model based on the framework of finite element techniques is presented, and involves the consideration of phenomena such as the heat production induced by the cement hydration, the evolving properties of concrete during hydration and early-age creep. A numerical application is presented, focused on the thermo-mechanical behaviour of a slab strongly restrained by the supporting piles, which has been monitored during the construction phase. For this particular problem it is shown that by making a reasonable thermal and mechanical characterization of concrete, the thermo-mechanical model provides results that are well correlated with the observed in situ measurements, namely the temperatures and the strains.

Joaquim Figueiras

Papers

Machine learning algorithms for damage detection under operational and environmental variability

Flexural Behavior of SFRC: Testing and Modeling

Structural health monitoring algorithm comparisons using standard data sets

Anisotropic elasto-plastic finite element analysis of thick and thin plates and shells

Modelling of concrete at early ages: Application to an externally restrained slab