Shear strength prediction of reinforced concrete beams by baseline, ensemble, and hybrid machine learning models

The shear strength of reinforced concrete (RC) beams is critical in the design of structural members. Developing an effective mathematical method for accurately estimating shear strength of RC beams is beneficial for civil engineers. This work presents a hybrid artificial intelligent (AI) model for effectively predicting the shear strength of various types of RC beam. The hybrid AI model was developed by integrating an optimization algorithm [smart firefly algorithm (SFA)] and machine learning [least squares support vector regression (LSSVR)], in which the SFA was used to optimize the hyperparameters of LSSVR, improving its predictive accuracy. Three large datasets were used to train and test the hybrid AI model in predicting shear strength of RC beams. The predictive accuracy of the hybrid AI model was compared comprehensively with those of single AI models, ensemble AI models, and empirical methods. The comparison results show that the hybrid AI model outperformed the others in predicting the shear strength of a wide range of RC beam types. In particular, with the test data of RC beams without stirrups, the hybrid AI model yielded a mean absolute percentage error (MAPE) of 21.703%. In predicting shear strength of RC beams with stirrups, the hybrid AI model yielded an MAPE of 12.941%. For RC beams with FRP reinforcement, the hybrid AI model yielded an MAPE 18.951%. Therefore, this hybrid AI model can be a better alternative method to help civil engineers in designing RC beams.

[1]  Juan R. Rabuñal,et al.  Optimization of existing equations using a new Genetic Programming algorithm: Application to the shear strength of reinforced concrete beams , 2012, Adv. Eng. Softw..

[2]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[3]  J. Platt.  Sequential Minimal Optimization : A Fast Algorithm for Training Support Vector Machines , 1998 .

[4]  Jui-Sheng Chou,et al.  Modified firefly algorithm for multidimensional optimization in structural design problems , 2016, Structural and Multidisciplinary Optimization.

[5]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[6]  Aly Marei Said,et al.  Predicting the effect of stirrups on shear strength of reinforced normal-strength concrete (NSC) and high-strength concrete (HSC) slender beams using artificial intelligence , 2006 .

[7]  Hua Liang,et al.  Improved estimation in multiple linear regression models with measurement error and general constraint , 2009, J. Multivar. Anal..

[8]  Ilker Fatih Kara,et al.  Prediction of shear strength of FRP-reinforced concrete beams without stirrups based on genetic programming , 2011, Adv. Eng. Softw..

[9]  Hojjat Adeli,et al.  Concept Drift-Oriented Adaptive and Dynamic Support Vector Machine Ensemble With Time Window in Corporate Financial Risk Prediction , 2013, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[10]  M. V. Suganyadevi,et al.  Assessment of voltage stability margin by comparing various support vector regression models , 2016, Soft Comput..

[11]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  David H. Wolpert,et al.  Stacked generalization , 1992, Neural Networks.

[13]  Antanas Verikas,et al.  Hybrid and ensemble-based soft computing techniques in bankruptcy prediction: a survey , 2010, Soft Comput..

[14]  Philip S. Yu,et al.  Top 10 algorithms in data mining , 2007, Knowledge and Information Systems.

[15]  M. Cheng,et al.  Nature-inspired metaheuristic multivariate adaptive regression splines for predicting refrigeration system performance , 2017, Soft Comput..

[16]  Michael C. Griffith,et al.  Presliding Shear Failure in Prestressed RC Beams. I: Partial-Interaction Mechanism , 2014 .

[17]  Juan R. Rabuñal,et al.  Optimal adjustment of EC-2 shear formulation for concrete elements without web reinforcement using Genetic Programming , 2010 .

[18]  Anil K. Jain.  Data clustering: 50 years beyond K-means , 2010, Pattern Recognit. Lett..

[19]  M. Nehdi,et al.  Proposed Shear Design Equations for FRP-Reinforced Concrete Beams Based on Genetic Algorithms Approach , 2007 .

[20]  Tomislav Kisicek,et al.  Deflections of concrete beams reinforced with FRP bars , 2010 .

[21]  Min-Yuan Cheng,et al.  Evolutionary multivariate adaptive regression splines for estimating shear strength in reinforced-concrete deep beams , 2014, Eng. Appl. Artif. Intell..

[22]  V. Mani,et al.  Clustering using firefly algorithm: Performance study , 2011, Swarm Evol. Comput..

[23]  Gülay Öke Günel,et al.  An adaptive support vector regressor controller for nonlinear systems , 2015, Soft Computing.

[24]  Dan Simon,et al.  Conceptual and numerical comparisons of swarm intelligence optimization algorithms , 2017, Soft Comput..

[25]  Pongsak Holimchayachotikul,et al.  Predictive performance measurement system for retail industry using neuro-fuzzy system based on swarm intelligence , 2016, Soft Computing.

[26]  Michael P. Collins,et al.  Where is Shear Reinforcement Required? Review of Research Results and Design Procedures , 2008 .

[27]  David W. Dinehart,et al.  Shear Strength of Normal Strength Concrete Beams Reinforced with Deformed GFRP Bars , 2001 .

[28]  Jui-Sheng Chou,et al.  The use of artificial intelligence combiners for modeling steel pitting risk and corrosion rate , 2017, Eng. Appl. Artif. Intell..

[29]  D. Oehlers,et al.  Shear Strength of FRP RC Beams and One-Way Slabs without Stirrups , 2014 .

[30]  P. K. Dash,et al.  An improved cuckoo search based extreme learning machine for medical data classification , 2015, Swarm Evol. Comput..

[31]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[32]  Arthur H. Nilson,et al.  Design of concrete structures , 1972 .

[33]  Edwin Lughofer,et al.  Editorial on the special issue “Hybrid and ensemble techniques in soft computing: recent advances and emerging trends” , 2015, Soft Comput..

[34]  Adolfo B. Matamoros,et al.  Design of Simply Supported Deep Beams Using Strut-and-Tie Models , 2003 .

[35]  U. Atici,et al.  Prediction of the strength of mineral-addition concrete using regression analysis , 2010 .

[36]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques with Java implementations , 2002, SGMD.

[37]  Subhash C. Bagui,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2005, Technometrics.

[38]  Layla Safwat Jamil.  DATA ANALYSIS BASED ON DATA MINING ALGORITHMS USING WEKA WORKBENCH , 2016 .

[39]  Michael P. Collins,et al.  Two-Parameter Kinematic Theory for Shear Behavior of Deep Beams , 2013 .

[40]  Jui-Sheng Chou,et al.  Shear Strength Prediction in Reinforced Concrete Deep Beams Using Nature-Inspired Metaheuristic Support Vector Regression , 2016, J. Comput. Civ. Eng..

[41]  Amir Hossein Gandomi,et al.  A new predictive model for compressive strength of HPC using gene expression programming , 2012, Adv. Eng. Softw..

[42]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[43]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[44]  Lionel Fine,et al.  A priori evaluation of simulation models preparation processes using artificial intelligence techniques , 2017, Comput. Ind..

[45]  João Paulo Papa,et al.  A social-spider optimization approach for support vector machines parameters tuning , 2014, 2014 IEEE Symposium on Swarm Intelligence.

[46]  Jui-Sheng Chou,et al.  Enhanced artificial intelligence for ensemble approach to predicting high performance concrete compressive strength , 2013 .

[47]  Jui-Sheng Chou,et al.  Smart Artificial Firefly Colony Algorithm‐Based Support Vector Regression for Enhanced Forecasting in Civil Engineering , 2015, Comput. Aided Civ. Infrastructure Eng..

[48]  A. S. Alnuaimi,et al.  Efficiency of near surface mounted technique using fiber reinforced polymers for the flexural strengthening of RC beams , 2016 .

[49]  Jui-Sheng Chou,et al.  Optimizing the Prediction Accuracy of Concrete Compressive Strength Based on a Comparison of Data-Mining Techniques , 2011, J. Comput. Civ. Eng..

[50]  Amir Hossein Alavi,et al.  An empirical model for shear capacity of RC deep beams using genetic-simulated annealing , 2013 .

[51]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machines , 2002 .

[52]  Ignacio J. Turias,et al.  Pitting potential modeling using Bayesian neural networks , 2013 .

[53]  Irfan Ahmad,et al.  Three empirical studies on predicting software maintainability using ensemble methods , 2015, Soft Comput..

[54]  Gaetano Russo,et al.  Reinforced Concrete Deep Beams - Shear Strength Model and Design Formula , 2005 .

[55]  Deric J. Oehlers,et al.  Shear Strength of RC Beams with Steel Stirrups , 2016 .

[56]  Michael C. Griffith,et al.  Presliding Shear Failure in Prestressed RC Beams. II: Behavior , 2014 .

[57]  Simon Fong,et al.  Accelerated Particle Swarm Optimization and Support Vector Machine for Business Optimization and Applications , 2011, NDT.

[58]  Frank Rosenblatt,et al.  PRINCIPLES OF NEURODYNAMICS. PERCEPTRONS AND THE THEORY OF BRAIN MECHANISMS , 1963 .