Neural Network for Structure Control

Chen, H. M.; Tsai, K. H.; Qi, Guilin; Yang, Jianming; Amini, Fereidoun

doi:10.1061/(asce)0887-3801(1995)9:2(168)

Cited by 131 publications

(60 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This technique has caught the interest of most researchers and has today become an essential part of the technology industry, providing a good ground for solving many of the most difficult prediction problems in various areas of engineering applications (Baughman 1995;Guler 2005;Inan et al 2006;Li and Jiao 2002;Moghadassi et al 2009;Mohaghegh 1995;Nascimento et al 2000;Phung and Bouzerdoum 2007;Ü beyli 2009). ANN has also gained vast popularity in solving various Civil Engineering problems (Baughman 1995;Beale and Demuth 2013;Chen et al 1995;Flood and Kartam 1994;Hasancebi and Dumlupınar 2013;Kang and Yoon 1994;Kirkegaard and Rytter 1994;Neaupane and Adhikari 2006;Pandey and Barai 1995;Rafiq et al 2001). Azad et al (2010) proposed the following two-step procedure to predict the residual flexural strength of corroded beams for which the cross-sectional details, material strengths, corrosion activity index I corr T , and diameter of rebar, D were known.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Residual Strength of Corroded Reinforced Concrete Beams Using an Adaptive Model Based on ANN

Imam

Anifowose

Azad

2015

International Journal of Concrete Structures and Materials

View full text Add to dashboard Cite

Estimation of the residual strength of corroded reinforced concrete beams has been studied from experimental and theoretical perspectives. The former is arduous as it involves casting beams of various sizes, which are then subjected to various degrees of corrosion damage. The latter are static; hence cannot be generalized as new coefficients need to be re-generated for new cases. This calls for dynamic models that are adaptive to new cases and offer efficient generalization capability. Computational intelligence techniques have been applied in Construction Engineering modeling problems. However, these techniques have not been adequately applied to the problem addressed in this paper. This study extends the empirical model proposed by Azad et al. (Mag Concr Res 62(6):405-414, 2010), which considered all the adverse effects of corrosion on steel. We proposed four artificial neural networks (ANN) models to predict the residual flexural strength of corroded RC beams using the same data from Azad et al. (2010). We employed two modes of prediction: through the correction factor (C f ) and through the residual strength (M res ). For each mode, we studied the effect of fixed and random data stratification on the performance of the models. The results of the ANN models were found to be in good agreement with experimental values. When compared with the results of Azad et al. (2010), the ANN model with randomized data stratification gave a C f -based prediction with up to 49 % improvement in correlation coefficient and 92 % error reduction. This confirms the reliability of ANN over the empirical models.

show abstract

Section: Artificial Neural Networkmentioning

confidence: 99%

Residual Strength of Corroded Reinforced Concrete Beams Using an Adaptive Model Based on ANN

Imam

Anifowose

Azad

2015

International Journal of Concrete Structures and Materials

View full text Add to dashboard Cite

show abstract

“…While in figure 12 and 13 for smaller R values, we observe faster training of the neuro-controller and after 7 seconds significant attenuation of the structural vibration can be observed. The control forces for the above values of the weighting factor are shown in figs [14][15][16]. Fig.…”

Section: Multi -Degree Of Freedom (Mdof) Systemmentioning

confidence: 99%

“…Pioneering research on application of neural control to reduce vibration of seismically excited structures has been conducted in the middle of the 1990s by Chen [16], Ghaboussi and Joghataie [17]. Chen et al (1995) proposed a back propagation-through-time neural controller, which consisted of two components: a) a neural emulator to represent a structure to be controlled and b) a neural network to determine the control action on the structure. Ghaboussi and Joghataie (1995) developed neural-network-based control for a three-story frame structure subjected to ground excitations.…”

Section: Introductionmentioning

confidence: 99%

Neural Network Based Vibration Control of Seismically Excited Civil Structures

Błachowski

Pnevmatikos

2018

Period. Polytech. Civil Eng.

View full text Add to dashboard Cite

show abstract

“…ANN has been helpful in solving structural engineering [30] and construction engineering related problems [21]. This includes structural analysis and design [31], [32], prediction of load-deflection of CFRF strengthened RC slabs [15]; prediction of shear capacity of concrete beam [27], [33]- [36], and shear strength of steel-fiber reinforced high strength concrete deep beams [24], prediction of moment capacity of ferrocement members [19], detection of structural damage [37]- [38], identification of structural system identification [39]- [40], modeling of material behavior, structural optimization [41] and structural dynamics and control [42].…”

Section: Ann Prediction and Modeling Studiesmentioning

confidence: 99%

Modeling and Prediction of Flexural Strength of Hybrid Mesh and Fiber Reinforced Cement-Based Composites Using Artificial Neural Network (Ann)

Sakthivel¹

2016

geomate

View full text Add to dashboard Cite

ABSTRACT:In this paper, Artificial Neural Network (ANN) has been used to predict the equivalent flexural strength of hybrid mesh and fiber reinforced cement-based composites (HMFRCBC). Three ANN models (Models 1, 2 and 3) were developed for predicting the flexural strength of cement-based composites. Model 1 used 48 data of the previously published data of the present authors and Model 2 used 48 data (out of the 75 ANN validated data) from previous studies related to mesh reinforced cement-based composites. Model 3 with 98 data (combined data sets of Model 1 and Model 2) employed seven input parameters, namely the width and depth of slab, cylinder compressive strength, mesh ultimate strength, mesh volume fraction, fiber volume fraction, fiber ultimate strength, and an output, the ultimate flexural strength of mesh and fiber reinforced cement based composites. Hidden layer was fixed based on 5 trial runs for Models 1 and 2, and 10 trial runs for Model 3. All the three models (Models 1, 2 and 3) were trained with 80% of the data, and tested with balance 20% of the data. For Models 1, 2 and 3, the Lowest Individual Error (LIE) of 11.18%, 6.95% and 11.56% (respectively) is achieved in Trial Run No.1.4 (with I-H-O, Input-Hidden Neurons-Output of 5-6-1), Trial Run No.2.2 (5-4-1) and Trial Run No.3.7 (7-10-1) respectively. Also, the lowest absolute average deviation (AAD%) of 4.81%, 3.51% and 4.58% (respectively); lowest Root Mean Square Error (RMSE) of 0.86, 0.76 and 0.99 (respectively); and highest R 2 of 0.933, 0.988 and 0.975 (respectively) are seen for these trials 1.4, 2.2, 3.7 in Models 1, 2 and 3 respectively. All the three ANN models were found to be in good agreement with actual results, and these three ANN models can serve as simple but reliable predictive tools in determination of flexural strength of HMFRCBC.

show abstract

Neural Network for Structure Control

Cited by 131 publications

References 17 publications

Residual Strength of Corroded Reinforced Concrete Beams Using an Adaptive Model Based on ANN

Residual Strength of Corroded Reinforced Concrete Beams Using an Adaptive Model Based on ANN

Neural Network Based Vibration Control of Seismically Excited Civil Structures

Modeling and Prediction of Flexural Strength of Hybrid Mesh and Fiber Reinforced Cement-Based Composites Using Artificial Neural Network (Ann)

Contact Info

Product

Resources

About