PSI - Issue 44

ScienceDirect Structural Integrity Procedia 00 (2022) 000–000 Structural Integrity Procedia 00 (2022) 000–000 Available online at www.sciencedirect.com Available online at www.sciencedirect.com ScienceD rect Available online at www.sciencedirect.com ScienceDirect

www.elsevier.com/locate/procedia www.elsevier.com/locate/procedia

Procedia Structural Integrity 44 (2023) 1688–1695

© 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the XIX ANIDIS Conference, Seismic Engineering in Italy. Abstract This contribution presents a numerical model for the shear capacity prediction of reinforced concrete (RC) elements with transverse reinforcement. The proposed model originates from one of the most popular mechanical models adopted in building codes, namely the variable-angle truss model. Starting from the formulation proposed in the Eurocode 2, two empirical coefficients governing the concrete contribution (i.e., the shear capacity ascribed to crushing of compressed struts) are adjusted and enriched through machine learning, in such a way to improve the predictive efficiency of the model against experimental results. More specifically, genetic programming is used to derive closed-form expressions of the two corrective coefficients, thus facilitating the use of this model for practical purposes. The proposed expressions are validated by comparison with a wide set of experimental results collected from the literature concerning RC beams and columns failing in shear under both monotonic and cyclic loading conditions, respectively. It is demonstrated that the proposed formulation, thanks to the two novel corrective coefficients, not only attains higher accuracy than the original Eurocode 2 formulation, but also outperforms many other existing design code provisions while preserving a sound mechanical basis. © 2022 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license ( https://creativecommons.org/licenses/by-nc-nd/4.0 ) Peer-review under responsibility of the scientific committee of the XIX ANIDIS Conference, Seismic Engineering in Italy Keywords: Reinforced concrete beams; Reinforced concrete columns; Design code; Genetic programming; Machine learning; Reinforced concrete; Shear capacity; Variable-angle truss model; Eurocode. 1. Introduction The prediction of the shear capacity of reinforced concrete (RC) elements with transverse reinforcement is a critical topic to which several studies have been devoted over the last four decades (ASCE-ACI Committee 445, 1998). This is motivated by the fact that existing RC structures are often provided with transverse reinforcement much lower than 2452-3216 © 2022 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the XIX ANIDIS Conference, Seismic Engineering in Italy Abstract This contribution presents a numerical model for the shear capacity prediction of reinforced concrete (RC) elements with transverse reinforcemen . The proposed model originates f om on of the most popular mecha ical models adopted in building codes, amely the va iabl -angle truss mo el. Starting from the formulation proposed in the Eurocode 2, two empirical coeff cie ts g verning the concrete contribution (i.e., th she r capacity ascribed to crushing f compressed struts) are adjusted and enriched through machin learning, in such a way to improve the predictive efficiency of the m del against experimental r sults. More specifically, genetic programming is used to derive closed-form expressions of the two corrective coefficients, thus facilitating the use of this model for actical purpo e . The proposed expressions a validated by c mpa ison with a wide set of experimental results collecte from the literature c ncerning RC beams and columns failing in shear under b th monoton c and cyclic loading conditions, respectively. It is d monstrated that the proposed formulation, tha ks to the two novel corrective oeffi ients, not o ly atta ns high r a curacy than the riginal Eurocode 2 f rmulation, but also outperforms many othe xisting des gn code pr visions while preserving a sou d mechanical basis. © 2022 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license ( https://creativecommons.org/licenses/by-nc-nd/4.0 ) Peer-review u der re ponsibility of scientific committe of the XIX ANIDIS C nfere ce, Seismic Engineering in Italy K ywords: Reinforced concrete beams; Reinforced concrete columns; Design code; Genetic programming; Machine lear ing; Reinforced concrete; Shear capacity; Variabl -angle truss mo el; Eurocode. 1. Introduction The prediction of the shear capacity of reinforced concrete (RC) elements with transverse reinforcement is a critical topic to which several studies h ve been d voted over the last four d cade (ASCE-ACI Committee 445, 1998). This is mo ivated by th f ct hat existing RC struc ures are often provided with transverse reinf rcement much lower than 2452-3216 © 2022 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the XIX ANIDIS Conference, Seismic Engineering in Italy XIX ANIDIS Conference, Seismic Engineering in Italy Machine-learning-enhanced variable-angle truss model to predict the shear capacity of RC elements with transverse reinforcement Dario De Domenico a , Giuseppe Quaranta b,* , Qingcong Zeng c , Giorgio Monti c,d a Department of Engineering, University of Messina, Contrada Di Dio, 98166 SantAgata, Messina, Italy b Department of Structural and Geotechnical Engineering, Sapienza University of Rome, Via Eudossiana 18, 00184 Rome, Italy c College of Engineering and Architecture, Zhejiang University, 866 Yuhangtang Road, Hangzhou 310058, China d Department of Structural and Geotechnical Engineering, Sapienza University of Rome, Via Gramsci 53, 00197 Roma, Italy XIX ANIDIS Conference, Seismic Engineering in Italy Machine-learning-enhanced variable-angle truss model to predict the shear capacity of RC elements with transverse reinforcement Dario De Domenico a , Giuseppe Quaranta b,* , Qingcong Zeng c , Giorgio Monti c,d a Department of Engineering, University of Messina, Contrada Di Dio, 98166 SantAgata, Messina, Italy b Department of St uctural and Geotechnical Engineering, Sapienza University of Rome, Vi Eudossiana 18, 00184 Rome, Italy c College of Engineering and Architecture, Zhejiang University, 866 Yuhangtang Ro d, Hangzhou 310 58, China d Department of Structural and Geote nical Engin eri , Sapienza University of Rome, Via Gramsci 53, 00197 Rom , Italy

2452-3216 © 2023 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the XIX ANIDIS Conference, Seismic Engineering in Italy. 10.1016/j.prostr.2023.01.216