skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Physics-Informed Data-Driven Prediction of 2D Normal Strain Field in Concrete Structures
Concrete exhibits time-dependent long-term behavior driven by creep and shrinkage. These rheological effects are difficult to predict due to their stochastic nature and dependence on loading history. Existing empirical models used to predict rheological effects are fitted to databases composed largely of laboratory tests of limited time span and that do not capture differential rheological effects. A numerical model is typically required for application of empirical constitutive models to real structures. Notwithstanding this, the optimal parameters for the laboratory databases are not necessarily ideal for a specific structure. Data-driven approaches using structural health monitoring data have shown promise towards accurate prediction of long-term time-dependent behavior in concrete structures, but current approaches require different model parameters for each sensor and do not leverage geometry and loading. In this work, a physics-informed data-driven approach for long-term prediction of 2D normal strain field in prestressed concrete structures is introduced. The method employs a simplified analytical model of the structure, a data-driven model for prediction of the temperature field, and embedding of neural networks into rheological time-functions. In contrast to previous approaches, the model is trained on multiple sensors at once and enables the estimation of the strain evolution at any point of interest in the longitudinal section of the structure, capturing differential rheological effects.  more » « less
Award ID(s):
2038761
PAR ID:
10466433
Author(s) / Creator(s):
;
Date Published:
Journal Name:
Sensors
Volume:
22
Issue:
19
ISSN:
1424-8220
Page Range / eLocation ID:
7190
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; (, Structure and Infrastructure Engineering)
    null (Ed.)
    Structural health monitoring (SHM) activities are essential for achieving a realistic characterisation of bridge structural performance levels throughout the service life. These activities can help detect structural damage before the potential occurrence of component- or system-level structural failures. In addition to their application at discrete times, SHM systems can also be installed to provide long-term accurate and reliable data continuously throughout the entire service life of a bridge. Owing to their superior accuracy and long-term durability compared to traditional strain gages, fiber optic sensors are ideal in extracting accurate real-time strain and temperature data of bridge components. This paper presents a statistical damage detection and localisation approach to evaluate the performance of prestressed concrete bridge girders using fiber Bragg grating sensors. The presented approach employs Artificial Neural Networks to establish a relationship between the strain profiles recorded at different sensor locations across the investigated girder. The approach is capable of detecting and localising the presence of damage at the sensor location without requiring detailed loading information; accordingly, it can be suitable for long-term monitoring activities under normal traffic loads. Experimental laboratory data obtained from the structural testing of a large-scale prestressed concrete bridge girder is used to illustrate the approach. 
    more » « less
  2. ; ; (, Proceedings of the Society for Experimental Mechanics)
    Structures experience large vibrations and stress variations during their life cycles. This causes reduction in their load-carrying capacity which is the main design criteria for many structures. Therefore, it is important to accurately establish the performance of structures after construction that often needs full-field strain or stress measurements. Many traditional inspection methods collect strain measurements by using wired strain gauges. These strain gauges carry a high installation cost and have high power demand. In contrast, this paper introduces a new methodology to replace this high cost with utilizing inexpensive data coming from wireless sensor networks. The study proposes to collect acceleration responses coming from a structure and give them as an input to deep learning framework to estimate the stress or strain responses. The obtained stress or strain time series then can be used in many applications to better understand the conditions of the structures. In this paper, designed deep learning architecture consists of multi-layer neural networks and Long Short-Term Memory (LSTM). The network achieves to learn the relationship between input and output by exploiting the temporal dependencies of them. In the evaluation of the method, a three-story steel building is simulated by using various dynamic wind and earthquake loading scenarios. The acceleration time histories under these loading cases are utilized to predict the stress time series. The learned architecture is tested on acceleration time series that the structure has never experienced. 
    more » « less
  3. ; ; (, Computer-Aided Civil and Infrastructure Engineering)
    Abstract Many of the civil structures experience significant vibrations and repeated stress cycles during their life span. These conditions are the bases for fatigue analysis to accurately establish the remaining fatigue life of the structures that ideally requires a full‐field strain assessment of the structures over years of data collection. Traditional inspection methods collect strain measurements by using strain gauges for a short time span and extrapolate the measurements in time; nevertheless, large‐scale deployment of strain gauges is expensive and laborious as more spatial information is desired. This paper introduces a deep learning‐based approach to replace this high cost by employing inexpensive data coming from acceleration sensors. The proposed approach utilizes collected acceleration responses as inputs to a multistage deep neural network based on long short‐term memory and fully connected layers to estimate the strain responses. The memory requirement of training long acceleration sequences is reduced by proposing a novel training strategy. In the evaluation of the method, a laboratory‐scale horizontally curved girder subjected to various loading scenarios is tested. 
    more » « less
  4. ; ; (, 55th US Rock Mechanics/Geomechanics Symposium)
    null (Ed.)
    We observed and modeled the elastic, inelastic and time-dependent viscous properties of damaged Berea Sandstone samples to investigate the impact of damage on the rheological properties of rocks. Cylindrical Berea Sandstone plugs were prepared both parallel and perpendicular to bedding. We impacted the samples with Split Hopkinson Pressure Bar to pervasively fracture the specimens at different strain rates. Longitudinal mode-I fractures are dominant in specimens impacted at relatively low strain rates (about 130 /s), whereas shear fractures also form in specimens deformed at high strain rates (up to 250 /s). The damaged rocks were subjected to multiple steps of differential stress loading and hold stages under 15 MPa confining pressure. A key observation is that higher damaged specimens showed greater axial and volumetric creep strain deformation during loading and hold stages. Poisson ratio also increase with increasing damage. We modeled the volumetric strain of the sandstone specimens using a Perzyna viscoplasticity law that employs the Modified Cam Clay model as the yield criterion (Haghighat et al. 2020). We deduced that fractured rocks undergo substantial bulk time-dependent deformation due to volumetric compaction and fracture closure. Damage increase results in decrease of the effective viscosity of the material. 
    more » « less
  5. ; ; ; (, ASME 2020 Verification and Validation Symposium)
    Abstract In order to accurately predict the performance of materials under dynamic loading conditions, models have been developed that describe the rate-dependent material behavior and irrecoverable plastic deformation that occurs at elevated strains and applied loads. Most of these models have roots in empirical fits to data and, thus, require the addition of specific parameters that reflect the properties and response of specific materials. In this work, we present a systematic approach to the problem of calibrating a Johnson-Cook plasticity model for 304L stainless steel using experimental testing in which the parameters are treated as dependent on the state of the material and uncovered using experimental data. The results obtained indicate that the proposed approach can make the presence of a discrepancy term in calibration unnecessary and, at the same time, improve the prediction accuracy of the model into new input domains and provide improved understanding of model bias compared to calibration with stationary parameter values. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email