Response Spectrum with Uncertain Damping Using Artificial Neural Networks

2021 ◽  
Vol 56 ◽  
pp. 136-144
Author(s):  
Lazhar Hariche ◽  
Baizid Benahmed ◽  
Abbas Moustafa
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Response Spectrum ◽  
Structural Response ◽  
Response Spectra ◽  
Dynamic Loads ◽  
Linear Structures ◽  
The Monte Carlo Method ◽  
Artificial Neural ◽  
Target Design

It is evident that the response of linear structures under dynamic loads depends to two important dynamics parameters of structures, namely, the natural periods and structural damping. These parameters always characterize the oscillation and the energy dissipation of buildings. In fact, the values of these parameters differ significantly, before, during and after an earthquake from values selected during the design phase. This phenomenon, among other, introduces uncertainty into the building simulation process, which remarkably influences the structural response and associated performance of the structure under dynamic loads. This paper develops a new methodology to estimate the maximum absolute response for linear structures with uncertain damping using the Artificial Neural Networks (ANN) and the Monte Carlo method. The proposed method is illustrated using the target design response spectra corresponding to the EC8 for linear structures exposed to seismic loads. The numerical results revealed the practical applicability of the proposed methodology and the crucial influence of accounting the damping uncertainty in structural dynamics. Additionally, the method can be used in practice, mainly for important and special structures where uncertainty could lead to significant changes in structural response.

Application of Magnetorheological Damper Semi-Active Control Based on Artificial Neural Networks

2010 ◽  
Vol 171-172 ◽  
pp. 654-658
Author(s):  
De Kun Yue ◽  
Qi Wang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
System Identification ◽  
Active Control ◽  
Bp Neural Network ◽  
Structural Response ◽  
Magnetorheological Damper ◽  
Building Structure ◽  
Artificial Neural

Uncertainty for the building structure and nonlinear, this simulation of a multi-storey structure under earthquake is presented based on the BP neural network and system identification, controller will be built to effectively reduce the structural response, and to strengthen the unique damper performance.

scholarly journals Identification of dynamic loads on structural component with artificial neural networks

2020 ◽  
Vol 52 ◽  
pp. 181-186
Author(s):  
Osman Altun ◽  
Danyang Zhang ◽  
Renan Siqueira ◽  
Philipp Wolniak ◽  
Iryna Mozgova ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Structural Component ◽  
Dynamic Loads ◽  
Artificial Neural

scholarly journals STUDY OF UNCERTAINTY OF THE INVERSION OF DISPERSION CURVES OF SURFACE WAVES USING ARTIFICIAL NEURAL NETWORKS

2021 ◽  
Vol 2 (3) ◽  
pp. 82-89
Author(s):  
Alexandr V. Yablokov ◽  
Aleksander S. Serdyukov
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Surface Waves ◽  
Dispersion Curves ◽  
Problem Solution ◽  
Inverse Problem Solution ◽  
Phase Velocities ◽  
The Monte Carlo Method ◽  
Multichannel Analysis ◽  
Artificial Neural

The results of using an adapted sampling algorithm by the Monte Carlo method to estimate the ambiguity domain of the inversion of synthetic dispersion curves of the phase velocities of surface waves using artificial neural networks are discussed in the paper. The expediency of using the considered algorithm for calculating a probabilistic estimate of the results of the inverse problem solution in the method of multichannel analysis of surface waves has been confirmed.

Development of Artificial Neural Networks for Predicting the Response of Bonded Concrete Overlays of Asphalt for Use in a Faulting Prediction Model

2018 ◽  
Vol 2672 (40) ◽  
pp. 360-370 ◽  
Author(s):  
John W. DeSantis ◽  
Julie M. Vandenbossche ◽  
Kevin Alland ◽  
John Harvey
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Prediction Model ◽  
Three Dimensional ◽  
Structural Response ◽  
Fractional Factorial ◽  
Finite Element Program ◽  
Concrete Overlays ◽  
Element Program ◽  
Artificial Neural

Transverse joint faulting is a common distress in bonded concrete overlays of asphalt pavements (BCOAs), also known as whitetopping. However, to date, there is no predictive faulting model available for these structures. To account for conditions unique to BCOA, a computational model was developed using a three-dimensional finite element program, ABAQUS, to predict the response of these structures. The model was validated with falling weight deflectometer (FWD) data from existing field sections at the Minnesota Road Research Facility (MnROAD) as well as at the University of California Pavement Research Center (UCPRC). A large database of analyses was then developed using a fractional factorial design. The database is used to develop predictive models, based on artificial neural networks (ANNs), to rapidly estimate the structural response at the joint in BCOA to environmental and traffic loads. The structural response will be related to damage using the differential energy concept. Future work includes the implementation of the developed ANNs in this study into a faulting prediction model for designing BCOA.

Artificial Neural Networks for Predicting the Response of Unbonded Concrete Overlays in a Faulting Prediction Model

2019 ◽  
Vol 2673 (10) ◽  
pp. 762-769 ◽  
Author(s):  
John W. DeSantis ◽  
Julie M. Vandenbossche ◽  
Steven G. Sachs
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Prediction Model ◽  
Structural Response ◽  
Finite Element Program ◽  
Concrete Overlays ◽  
Transverse Joint ◽  
Element Program ◽  
Artificial Neural ◽  
Future Work

Transverse joint faulting is a common distress in unbonded concrete overlays (UBOLs). However, the current faulting model in Pavement mechanistic-empirical (ME) is not suitable for accurately predicting the response of UBOLs. Therefore, to develop a more accurate faulting prediction model for UBOLs, the first step was to develop a predictive model that would be able to predict the response (deflections) of these structures. To account for the conditions unique to UBOLs, a computational model was developed using the pavement-specific finite element program ISLAB, to predict the response of these structures. The model was validated using falling weight deflectometer (FWD) data from existing field sections at the Minnesota Road Research Facility (MnROAD) as well as sections in Michigan. A factorial design was performed using ISLAB to efficiently populate a database of fictitious UBOLs and their responses. The database was then used to develop predictive models, based on artificial neural networks (ANNs), to rapidly estimate the structural response of UBOLs to environmental and traffic loads. The structural response can be related to damage through the differential energy concept. Future work will include implementation of the ANNs developed in this study into a faulting prediction model for designing UBOLs.

Redevelopment of Artificial Neural Networks for Predicting the Response of Bonded Concrete Overlays of Asphalt for use in a Faulting Prediction Model

2021 ◽  
pp. 036119812110010
Author(s):  
John W. DeSantis ◽  
Julie M. Vandenbossche
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Prediction Model ◽  
Predictive Models ◽  
Computational Models ◽  
Structural Response ◽  
Fractional Factorial ◽  
Finite Element Program ◽  
Concrete Overlays ◽  
Artificial Neural

Transverse joint faulting is a common distress in bonded concrete overlays of asphalt pavements (BCOAs), also known as whitetopping. However, to date, there is no predictive faulting model available for these structures. Therefore, the intended research is to develop a predictive faulting model for BCOAs. In addition, it is important to be able to account for conditions unique to BCOA when characterizing the response in a faulting prediction model. To address this, computational models were developed using a three-dimensional finite element program, ABAQUS, to accurately predict the response of these structures. These models account for different depths of joint activation, as well as full and partial bonding between the concrete overlay and existing asphalt pavement. The models were validated with falling weight deflectometer (FWD) data from existing field sections at the Minnesota Road Research Facility (MnROAD) as well as at the University of California Pavement Research Center (UCPRC). A fractional factorial analysis was executed using the computational models to generate a database to be used in the development of the predictive models. The predictive models, based on artificial neural networks (ANNs), are used to rapidly estimate the structural response at the joint in BCOA to environmental and traffic loads so that these responses can be incorporated into the design process. The structural response obtained using the ANNs is related to damage using the differential energy concept. Future work includes the implementation of the ANNs developed in this study into a faulting prediction model for designing BCOA.

scholarly journals A Monte Carlo-Based Method for Assessing the Measurement Uncertainty in the Training and Use of Artificial Neural Networks

2016 ◽  
Vol 23 (2) ◽  
pp. 281-294 ◽  
Author(s):  
Rodrigo Coral ◽  
Carlos A. Flesch ◽  
Cesar A. Penz ◽  
Mauro Roisenberg ◽  
Antonio L. S. Pacheco
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Monte Carlo ◽  
Artificial Neural Networks ◽  
Measurement Uncertainty ◽  
Neural Model ◽  
Measuring Systems ◽  
Propagation Of Uncertainty ◽  
The Monte Carlo Method ◽  
Artificial Neural

Abstract When an artificial neural network is used to determine the value of a physical quantity its result is usually presented without an uncertainty. This is due to the difficulty in determining the uncertainties related to the neural model. However, the result of a measurement can be considered valid only with its respective measurement uncertainty. Therefore, this article proposes a method of obtaining reliable results by measuring systems that use artificial neural networks. For this, it considers the Monte Carlo Method (MCM) for propagation of uncertainty distributions during the training and use of the artificial neural networks.

Sign in / Sign up

Export Citation Format

Share Document