scholarly journals Potential of Neural Networks for Structural Damage Localization

2021 ◽  
Author(s):  
Miguel Abambres ◽  
Marcy M ◽  
Doz G
Keyword(s):  
Structural Damage ◽  
Structural Engineering ◽  
Dynamic Properties ◽  
Structural Safety ◽  
Damage Localization ◽  
Proposed Model ◽  
Data Points ◽  
Ann Models ◽  
Artificial Neural Network Ann

<p>Fabrication technology and structural engineering states-of-art have led to a growing use of slender structures, making them more susceptible to static and dynamic actions that may lead to some sort of damage. In this context, regular inspections and evaluations are necessary to detect and predict structural damage and establish maintenance actions able to guarantee structural safety and durability with minimal cost. However, these procedures are traditionally quite time-consuming and costly, and techniques allowing a more effective damage detection are necessary. This paper assesses the potential of Artificial Neural Network (ANN) models in the prediction of damage localization in structural members, as function of their dynamic properties – the three first natural frequencies are used. Based on 64 numerical examples from damaged (mostly) and undamaged steel channel beams, an ANN-based analytical model is proposed as a highly accurate and efficient damage localization estimator. The proposed model yielded maximum errors of 0.2 and 0.7 % concerning 64 numerical and 3 experimental data points, respectively. Due to the high-quality of results, authors’ next step is the application of similar approaches to entire structures, based on much larger datasets.</p>

scholarly journals Potential of Neural Networks for Structural Damage Localization

2020 ◽  
Author(s):  
Abambres M ◽  
Marcy M ◽  
Doz G
Keyword(s):  
Structural Damage ◽  
Structural Engineering ◽  
Dynamic Properties ◽  
Structural Safety ◽  
Damage Localization ◽  
Proposed Model ◽  
Data Points ◽  
Ann Models ◽  
Artificial Neural Network Ann

<p>Fabrication technology and structural engineering states-of-art have led to a growing use of slender structures, making them more susceptible to static and dynamic actions that may lead to some sort of damage. In this context, regular inspections and evaluations are necessary to detect and predict structural damage and establish maintenance actions able to guarantee structural safety and durability with minimal cost. However, these procedures are traditionally quite time-consuming and costly, and techniques allowing a more effective damage detection are necessary. This paper assesses the potential of Artificial Neural Network (ANN) models in the prediction of damage localization in structural members, as function of their dynamic properties – the three first natural frequencies are used. Based on 64 numerical examples from damaged (mostly) and undamaged steel channel beams, an ANN-based analytical model is proposed as a highly accurate and efficient damage localization estimator. The proposed model yielded maximum errors of 0.2 and 0.7 % concerning 64 numerical and 3 experimental data points, respectively. Due to the high-quality of results, authors’ next step is the application of similar approaches to entire structures, based on much larger datasets.</p>

scholarly journals Potential of neural networks for structural damage localization

2019 ◽  
Vol 11 (2) ◽  
Author(s):  
Miguel Abambres ◽  
Marilia Marcy ◽  
Graciela Doz
Keyword(s):  
Structural Damage ◽  
Structural Engineering ◽  
Dynamic Properties ◽  
Structural Safety ◽  
Damage Localization ◽  
Proposed Model ◽  
Data Points ◽  
Ann Models ◽  
Artificial Neural Network Ann

Fabrication technology and structural engineering states-of-art have led to a growing use of slender structures, making them more susceptible to static and dynamic actions that may lead to some sort of damage. In this context, regular inspections and evaluations are necessary to detect and predict structural damage and establish maintenance actions able to guarantee structural safety and durability with minimal cost. However, these procedures are traditionally quite time-consuming and costly, and techniques allowing a more effective damage detection are necessary. This paper assesses the potential of Artificial Neural Network (ANN) models in the prediction of damage localization in structural members, as function of their dynamic properties – the three first natural frequencies are used. Based on 64 numerical examples from damaged (mostly) and undamaged steel channel beams, an ANN-based analytical model is proposed as a highly accurate and efficient damage localization estimator. The proposed model yielded maximum errors of 0.2 and 0.7 % concerning 64 numerical and 3 experimental data points, respectively. Due to the high-quality of results, authors’ next step is the application of similar approaches to entire structures, based on much larger datasets.

scholarly journals Potential of Neural Networks for Structural Damage Localization

2020 ◽  
Author(s):  
Abambres M ◽  
Marcy M ◽  
Doz G
Keyword(s):  
Structural Damage ◽  
Structural Engineering ◽  
Dynamic Properties ◽  
Structural Safety ◽  
Damage Localization ◽  
Proposed Model ◽  
Data Points ◽  
Ann Models ◽  
Artificial Neural Network Ann

<p>Fabrication technology and structural engineering states-of-art have led to a growing use of slender structures, making them more susceptible to static and dynamic actions that may lead to some sort of damage. In this context, regular inspections and evaluations are necessary to detect and predict structural damage and establish maintenance actions able to guarantee structural safety and durability with minimal cost. However, these procedures are traditionally quite time-consuming and costly, and techniques allowing a more effective damage detection are necessary. This paper assesses the potential of Artificial Neural Network (ANN) models in the prediction of damage localization in structural members, as function of their dynamic properties – the three first natural frequencies are used. Based on 64 numerical examples from damaged (mostly) and undamaged steel channel beams, an ANN-based analytical model is proposed as a highly accurate and efficient damage localization estimator. The proposed model yielded maximum errors of 0.2 and 0.7 % concerning 64 numerical and 3 experimental data points, respectively. Due to the high-quality of results, authors’ next step is the application of similar approaches to entire structures, based on much larger datasets.</p>

scholarly journals Potential of Neural Networks for Structural Damage Localization

2018 ◽  
Author(s):  
Miguel Abambres ◽  
Marília Marcy ◽  
Graciela Doz
Keyword(s):  
Structural Damage ◽  
Structural Engineering ◽  
Dynamic Properties ◽  
Structural Safety ◽  
Damage Localization ◽  
Proposed Model ◽  
Data Points ◽  
Ann Models ◽  
Artificial Neural Network Ann

Fabrication technology and structural engineering states-of-art have led to a growing use of slender structures, making them more susceptible to static and dynamic actions that may lead to some sort of damage. In this context, regular inspections and evaluations are necessary to detect and predict structural damage and establish maintenance actions able to guarantee structural safety and durability with minimal cost. However, these procedures are traditionally quite time-consuming and costly, and techniques allowing a more effective damage detection are necessary. This paper assesses the potential of Artificial Neural Network (ANN) models in the prediction of damage localization in structural members, as function of their dynamic properties – the three first natural frequencies are used. Based on 64 numerical examples from damaged (mostly) and undamaged steel channel beams, an ANN-based analytical model is proposed as a highly accurate and efficient damage localization estimator. The proposed model yielded maximum errors of 0.2 and 0.7 % concerning 64 numerical and 3 experimental data points, respectively. Due to the high-quality of results, authors’ next step is the application of similar approaches to entire structures, based on much larger datasets.

scholarly journals Newly Developed Correlations to Predict the Rheological Parameters of High-Bentonite Drilling Fluid Using Neural Networks

Sensors ◽  
2020 ◽  
Vol 20 (10) ◽  
pp. 2787
Author(s):  
Ahmed Gowida ◽  
Salaheldin Elkatatny ◽  
Khaled Abdelgawad ◽  
Rahul Gajbhiye
Keyword(s):  
Rheological Properties ◽  
Drilling Fluid ◽  
Rheological Parameters ◽  
Percentage Error ◽  
Cleaning Efficiency ◽  
Periodic Monitoring ◽  
Data Points ◽  
Ann Models ◽  
Artificial Neural Network Ann ◽  
Marsh Funnel

High-bentonite mud (HBM) is a water-based drilling fluid characterized by its remarkable improvement in cutting removal and hole cleaning efficiency. Periodic monitoring of the rheological properties of HBM is mandatory for optimizing the drilling operation. The objective of this study is to develop new sets of correlations using artificial neural network (ANN) to predict the rheological parameters of HBM while drilling using the frequent measurements, every 15 to 20 min, of mud density (MD) and Marsh funnel viscosity (FV). The ANN models were developed using 200 field data points. The dataset was divided into 70:30 ratios for training and testing the ANN models respectively. The optimized ANN models showed a significant match between the predicted and the measured rheological properties with a high correlation coefficient (R) higher than 0.90 and a maximum average absolute percentage error (AAPE) of 6%. New empirical correlations were extracted from the ANN models to estimate plastic viscosity (PV), yield point (YP), and apparent viscosity (AV) directly without running the models for easier and practical application. The results obtained from AV empirical correlation outperformed the previously published correlations in terms of R and AAPE.

scholarly journals Length of Hospital Stay Prediction at the Admission Stage for Cardiology Patients Using Artificial Neural Network

2016 ◽  
Vol 2016 ◽  
pp. 1-11 ◽  
Author(s):  
Pei-Fang (Jennifer) Tsai ◽  
Po-Chia Chen ◽  
Yen-You Chen ◽  
Hao-Yuan Song ◽  
Hsiu-Mei Lin ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Coronary Atherosclerosis ◽  
Inpatient Care ◽  
Length Of Hospital Stay ◽  
Ann Models ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Christian Hospital

For hospitals’ admission management, the ability to predict length of stay (LOS) as early as in the preadmission stage might be helpful to monitor the quality of inpatient care. This study is to develop artificial neural network (ANN) models to predict LOS for inpatients with one of the three primary diagnoses: coronary atherosclerosis (CAS), heart failure (HF), and acute myocardial infarction (AMI) in a cardiovascular unit in a Christian hospital in Taipei, Taiwan. A total of 2,377 cardiology patients discharged between October 1, 2010, and December 31, 2011, were analyzed. Using ANN or linear regression model was able to predict correctly for 88.07% to 89.95% CAS patients at the predischarge stage and for 88.31% to 91.53% at the preadmission stage. For AMI or HF patients, the accuracy ranged from 64.12% to 66.78% at the predischarge stage and 63.69% to 67.47% at the preadmission stage when a tolerance of 2 days was allowed.

scholarly journals Application of ANN in Predicting the Cantilever Wall Deflection in Undrained Clay

2021 ◽  
Vol 11 (20) ◽  
pp. 9760
Author(s):  
Zhongkai Huang ◽  
Dongmei Zhang ◽  
Dongming Zhang
Keyword(s):  
Pressure Coefficient ◽  
Earth Pressure ◽  
Numerical Data ◽  
Absolute Error ◽  
Ann Model ◽  
Soil Stiffness ◽  
Wall Deflection ◽  
Proposed Model ◽  
Ann Models ◽  
Artificial Neural Network Ann

The main objective of this study is to propose an artificial neural network (ANN)-based tool for predicting the cantilever wall deflection in undrained clay. The excavation width, the excavation depth, the wall thickness, the at-rest lateral earth pressure coefficient, the soil shear strength ratio at mid-depth of the wall, and the soil stiffness ratio at mid-depth of the wall were selected as the input parameters, whereas the cantilever wall deflection was selected as an output parameter. A set of verified numerical data were utilized to train, test, and validate the ANN models. Two commonly used performance indicators, namely, root mean square error (RMSE) and mean absolute error (MAE), were selected to evaluate the performance of the proposed model. The results indicated that the proposed model can reliably predict the cantilever wall deflection in undrained clay. Moreover, the sensitivity analysis showed that the excavation depth is the most important parameter. Finally, a graphical user interface (GUI) tool was developed based on the proposed ANN model, which is much easier and less expensive to be used in practice. The results of this study can help engineers to better understand and predict the cantilever wall deflection in undrained clay.

Reliability of Pipeline Affected by Corrosion and Third Parts

2003 ◽  
Author(s):  
Jorge L. Alamilla ◽  
Oscar Flores-Maci´as ◽  
Alejandro Vargas
Keyword(s):  
Probability Function ◽  
Safety Margin ◽  
Structural Safety ◽  
Proposed Model ◽  
Pipeline Segment ◽  
Corrosion Defects ◽  
Pressure Stress ◽  
Corrosion State ◽  
Over Time

An approach to evaluate the structural safety of pipelines affected by corrosion and third parts is presented. This formulation is applied when the information about the corrosion state of the system is available. This information includes: the total number of detected corrosion defects, depth and length of each measured defect. The probabilistic model considers the detected and undetected corrosion, and generation of new corrosion defects over time. In other words, the model takes into account the corrosion state of the system and the quality of the inspection tool. The failure is defined by a safety margin that is evaluated in terms of pressure stress. The undetected defects and the generation of new defects are modeled by a Poisson process. The contribution of failure by third parts to the failure probability is taken into account in a simplified way. For this case the probability function is obtained from the reported failures. The proposed model is applied to a pipeline segment in which reliability indexes over time are represented in terms of reliability functions that characterize the probability distribution between failures.

scholarly journals A NEW HYBRID ANN MODEL FOR EVALUATING THE EFFICIENCY OF Π-TYPE FLOATING BREAKWATER

2017 ◽  
pp. 25 ◽  
Author(s):  
Hadi Ghasemi ◽  
Morteza Kolahdoozan ◽  
Enrique Pena ◽  
Javier Ferreras ◽  
Andrés Figuero
Keyword(s):  
Experimental Data ◽  
Wave Energy ◽  
Model Performance ◽  
Accurate Estimate ◽  
Ann Model ◽  
Proposed Model ◽  
Wave Basin ◽  
Short Period ◽  
Ann Models ◽  
Artificial Neural Network Ann

Floating breakwaters (FBs) have been specially regarded in recent years as a means to protect small harbors and marine structures against affection of short period waves. FBs have different types in terms of geometric shapes; one of the most common of which is the π-type FB. Generally, FBs are designed to reduce wave energy. The parameter used to evaluate the efficiency of FBs in the wave energy reduction is the wave transmission coefficient (Kt). Thus, accurate estimate of Kt is an important aspect in FBs design. In the present study, new hybrid artificial neural network (ANN) models are developed for predicting Kt of π-type FBs. Actually, a new algorithm that combines particle swarm optimization (PSO) and Levenberg-Marquardt (LM) is used for learning ANN models. These models are developed by the use of experimental data sets obtained from the Kt of π-type FBs using a wave basin of the University of a Coruña, Spain. A proposed model performance was evaluated and results show that this model can be successfully applied for the prediction of the Kt. Also, results of proposed model show that the efficiency of this model is improved in compare with the introduced formulas cited in the literature. After assuring the acceptability of the prediction results, this model as one of an efficient tool was used for extending the experimental data and selection of the optimal design of π-type FBs in terms of the geometric characteristics.

scholarly journals PRETEEN AGE: THE ANALYSIS OF THE MULTILEVEL PSYCHO-DIAGNOSTIC DATA BASED ON NEURAL NETWORK MODELS

2018 ◽  
Vol 5 ◽  
pp. 455 ◽  
Author(s):  
Elena Slavutskaya ◽  
Leonid Slavutskii
Keyword(s):  
Neural Network ◽  
System Analysis ◽  
Network Models ◽  
Neural Network Models ◽  
Diagnostic Data ◽  
Ann Models ◽  
Artificial Neural Network Ann ◽  
Mathematical Preparation ◽  
Statistical Criteria

The use of the artificial neural network (ANN) models for vertical system analysis of psycho-diagnostic data is suggested. It is shown that the ANN training, as the problem of nonlinear multi-parameter optimization, allows to create effective algorithms for the psycho-diagnostic data processing when the results of psychological testing for the different level’s characteristics have different numerical scales. On the example of processing the author's data of psycho-diagnostics (preadolescent schoolchildren), it is shown that neural network models can be used to estimate latent (hidden) connections between psychological characteristics. The proposed algorithms are based on a statistical assessment of the quality of such models, do not require a large sample of respondents. The quantitative statistical criteria for evaluating the quality of the models are estimated. The approach is sufficiently clear for practical use by psychologists who do not have a special mathematical preparation.

Sign in / Sign up

Export Citation Format

Share Document