Deep Neural Network-Based Storey Drift Modelling of Precast Concrete Structures Using RStudio

Document Type : Regular Article


1 Ph.D. Student, Faculty of Civil Engineering, National Institute of Technology Kurukshetra, Haryana, India

2 Associate Professor, Faculty of Civil Engineering, National Institute of Technology Kurukshetra, Haryana, India

3 Assistant Professor, Faculty of Civil Engineering, National Institute of Technology Kurukshetra, Haryana, India


In this research, storey drift has been determined using Deep neural networks (DNN Keras). DNN Keras has various hyper tuning parameters (hidden layer, drop out layer, epochs, batch size and activation function) that make it capable to model complex problems. Building height, number of bays, number of storeys, time period, storey displacement, and storey acceleration were the input parameters while storey drift was the output parameter. The dataset consists of 288 models, out of 197 were used as training data and the remaining 91 were used as test data. 0.9598 correlation coefficient was observed for DNN Keras as compared to 0.8905 by resilient back-propagation neural networks (BPNN), indicating that DNN Keras has about 8 per cent improved efficiency in predicting storey drift. Wilcoxon signed-rank test (non-parametric test) was used to compare and validate the performance of DNN Keras and resilient BPNN algorithms. The positive results of this study point to the need for further research into the use of DNN Keras in structural and civil engineering.


Main Subjects

[1]     Omran BA, Chen Q, Jin R. Comparison of Data Mining Techniques for Predicting Compressive Strength of Environmentally Friendly Concrete. J Comput Civ Eng 2016;30:04016029.
[2]     Asteris PG, Kolovos KG, Douvika MG, Roinos K. Prediction of self-compacting concrete strength using artificial neural networks. Eur J Environ Civ Eng 2016;20:s102–22.
[3]     Asteris PG, Plevris V. Anisotropic masonry failure criterion using artificial neural networks. Neural Comput Appl 2017;28:2207–29.
[4]     Asteris PG, Kolovos KG. Self-compacting concrete strength prediction using surrogate models. Neural Comput Appl 2019;31:409–24.
[5]     Asteris P, Roussis P, Douvika M. Feed-Forward Neural Network Prediction of the Mechanical Properties of Sandcrete Materials. Sensors 2017;17:1344.
[6]     Asteris PG, Nozhati S, Nikoo M, Cavaleri L, Nikoo M. Krill herd algorithm-based neural network in structural seismic reliability evaluation. Mech Adv Mater Struct 2019;26:1146–53.
[7]     Veletsos AS, Newmark NM. Effect of inelastic behavior on the response of simple systems to earthquake motions, Department of Civil Engineering, University of Illinois; 1960.
[8]     Jacobsen LS. Motion of a soil subjected to a simple harmonic ground vibration. Bull Seismol Soc Am 1930;20:160–95.
[9]     Iwan WD. Estimating inelastic response spectra from elastic spectra. Earthq Eng Struct Dyn 1980;8:375–88.
[10]   Brunesi E, Peloso S, Pinho R, Nascimbene R. Cyclic testing of a full-scale two-storey reinforced precast concrete wall-slab-wall structure. Bull Earthq Eng 2018;16:5309–39.
[11]   Menegon SJ, Wilson JL, Lam NT, Gad EF. Experimental assessment of the ultimate performance and lateral drift behaviour of precast concrete building cores. Adv Struct Eng 2020;23:2597–613.
[12]   Seifi P, Henry RS, Ingham JM. In-plane cyclic testing of precast concrete wall panels with grouted metal duct base connections. Eng Struct 2019;184:85–98.
[13]   Sun J, Qiu H, Lu Y. Experimental study and associated numerical simulation of horizontally connected precast shear wall assembly. Struct Des Tall Spec Build 2016;25:659–78.
[14]   Sun J, Qiu H, Jiang H. Lateral load behaviour of a rectangular precast shear wall involving vertical bolted connections. Adv Struct Eng 2019;22:1211–24.
[15]   Nikoo M, Sadowski Ł, Khademi F, Nikoo M. Determination of Damage in Reinforced Concrete Frames with Shear Walls Using Self-Organizing Feature Map. Appl Comput Intell Soft Comput 2017;2017:1–10.
[16]   Pal M, Deswal S. Modelling pile capacity using Gaussian process regression. Comput Geotech 2010;37:942–7.
[17]   Pal M, Deswal S. Support vector regression based shear strength modelling of deep beams. Comput Struct 2011;89:1430–9.
[18]   Zhang Z, Wang Y, Chen P, Yu G. Application of Long Short-Term Memory Neural Network for Multi-Step Travel Time Forecasting on Urban Expressways. CICTP 2017, Reston, VA: American Society of Civil Engineers; 2018, p. 444–54.
[19]   Zhou L, Chen X (Michael). Short-Term Forecasting of Traffic Flow and Speed: A Deep Learning Approach. CICTP 2018, Reston, VA: American Society of Civil Engineers; 2018, p. 2186–96.
[20]   Kumar SS, Abraham DM. A Deep Learning Based Automated Structural Defect Detection System for Sewer Pipelines. Comput. Civ. Eng. 2019, Reston, VA: American Society of Civil Engineers; 2019, p. 226–33.
[21]   Pal M. Deep neural network based pier scour modeling. ISH J Hydraul Eng 2019:1–6.
[22]   F. Chollet. Keras., 2015 n.d.
[23]   RStudio Team (2015). RStudio: Integrated Development for R. RStudio, Inc., Boston, MA. n.d.
[24]   E-Tabs (2018)- Integrated software for structural analysis and design. Version 18.0.2 Berkeley. Computer & Structures, Inc 2019 n.d.
[25]   Baker WF, Pawlikowski JJ, Young BS. The Challenges in Designing the World’s Tallest Structure: The Burj Dubai Tower. Struct. Congr. 2009, Reston, VA: American Society of Civil Engineers; 2009, p. 1–10.
[26]   Bowden GJ, Maier HR, Dandy GC. Input determination for neural network models in water resources applications. Part 2. Case study: forecasting salinity in a river. J Hydrol 2005;301:93–107.
[27]   DAHIYA N. Machine learning based modelling for estimation of the fundamental time period of precast concrete structures using computer programming. Stavební Obz - Civ Eng J 2021;30.
[28]   Dahiya N, Saini B, Chalak HD. Gradient boosting-based regression modelling for estimating the time period of the irregular precast concrete structural system with cross bracing. J King Saud Univ - Eng Sci 2021.