Utilizing ensemble learning in the classifications of ductile and brittle failure modes of UHPC strengthened RC members

• Autorzy: Taffese Woubishet Zewdu , Zhu Yanping , Chen Genda

Identyfikatory

DOI

10.1007/s43452-024-00897-7

• Języki publikacji: EN

Abstrakty

EN

This study aims to achieve the swift and precise classification of ductile and brittle failure modes in flexural reinforced concrete (RC) members, specifically those with tension sides strengthened by ultrahigh performance concrete (UHPC). Employing six ensemble learning techniques - Bagging, Random Forest, AdaBoost, Gradient Boosting, XGBoost, and LightGBM - the authors utilize a comprehensive dataset comprising 14 features, which include manually labeled failure modes obtain from load-deflection curves. The model training spans four scenarios, varying in the inclusion or exclusion of features describing the cross-sectional area of RC members and moment resistance. XGBoost emerges as the most effective classifier, achieving an impressive 84% accuracy with high confidence. Additionally, the study employs the Shapley Additive Explanation (SHAP) technique on the best-performing model to illuminate the significance and impacts of various features in UHPC-strengthened flexural members’ failure modes. Notably, moment resistance and UHPC tensile strength surface as the most influential factors in predicting failure modes. Increased rebar yield strength, UHPC compressive strength, UHPC reinforcement ratio, and steel fiber volume in UHPC contribute to enhanced ductility in flexural members, while heightened moment resistance and UHPC layer thickness, along with a robust RC-UHPC interface, tend to induce brittleness. The introduction of such an effective failure modes classification model, coupled with the model’s explainability, instills trust in its predictions and facilitates seamless integration into real-world applications, particularly in seismic areas. The model’s ability to operate without the need for pre-experimental tests marks a significant advancement in the field.

Słowa kluczowe

EN

ultrahigh performance concrete; reinforced concrete; flexural strengthening; ensemble learning method; failure mode classification

PL

beton ultrawysokowartościowy; beton zbrojony; wzmocnienie na zginanie; uczenie zespołowe

• Wydawca: Springer ; Wrocław University of Science and Technology
• Czasopismo: Archives of Civil and Mechanical Engineering
• Rocznik: 2024
• Tom: Vol. 24, no. 2
• Strony: art. no. e86, 2024
• Opis fizyczny: Bibliogr. 57 poz., rys., tab., wykr.

Twórcy

autor

Taffese Woubishet Zewdu

• Department of Civil, Architectural, and Environmental Engineering, Missouri University of Science and Technology, Rolla, MO 65401, USA

autor

Zhu Yanping

• Department of Civil, Architectural, and Environmental Engineering, Missouri University of Science and Technology, Rolla, MO 65401, USA
• Present Address: Civil and Mechanical Engineering, University of Mount Union, Alliance, OH 44601, USA

autor

Chen Genda

• Department of Civil, Architectural, and Environmental Engineering, Missouri University of Science and Technology, Rolla, MO 65401, USA

Bibliografia

• 1. El-Helou RG, Graybeal BA. Flexural behavior and design of ultrahigh-performance concrete beams. J Struct Eng. 2022;148:04022013.
• 2. Haber ZB, De la Varga I, Graybeal BA, Nakashoji B, El-Helou R. 2018. Properties and behavior of UHPC-class materials. Rep. No. FHWA-HRT-18-036. McLean, VA: Federal Highway Administration.
• 3. Shao Y. Improving ductility and design methods of reinforced HPFRCC flexural members, Ph.D. dissertation, 2020. Dept. of Civil and Environmental Engineering, Stanford Univ.
• 4. Shao Y, Billington SL. Predicting the two predominant flexural failure paths of longitudinally reinforced high-performance fiber-reinforced cementitious composite structural members. Eng Struct. 2019;199: 109581.
• 5. Chen SG, Guo QQ, Zhang YY, Hu HX, Shen B. Machine learning models for cracking torque and pre-cracking stiffness of RC beams. Arch Civ Mech Eng. 2023;23:6.
• 6. Hason MM, Hanoon AN, Al Zand AW, Abdulhameed AA, Al-Sulttani AO. Torsional strengthening of reinforced concrete beams with externally-bonded fibre reinforced polymer: an energy absorption evaluation. Civ Eng J. 2020;6:69.
• 7. Habel K, Denarié E, Brühwiler E. Experimental investigation of composite concrete and conventional concrete members. ACI Struct J. 2007;104:93-101.
• 8. Zhang Y, Zhu Y, Yeseta M, Meng D, Shao X, Dang Q, Chen G. Flexural behaviors and capacity prediction on damaged reinforcement concrete (RC)bridge deck strengthened by ultrahigh performance concrete (UHPC)layer. Constr Build Mater. 2019;215:347-59.
• 9. Teng L, Khayat KH. Effect of overlay thickness, fiber volume, and shrinkage mitigation on flexural behavior of thin bonded ultrahigh-performance concrete overlay slab. Cem Concr Compos. 2022;134:104752.
• 10. Graybeal B, Brühwiler E, Kim BS, Toutlemonde F, Voo YL, Zaghi A. International perspective on UHPC in bridge engineering. J Bridge Eng. 2020;25:04020094.
• 11. Solhmirzaeia R, Salehib H, Kodura V, Naser MZ. Machine learning framework for predicting failure mode and shear capacity of ultra high performance concrete beams. Eng Struct. 2020;224: 111221.
• 12. Mangalathu S, Jeon J. Machine learning-based failure mode recognition of circular reinforced concrete bridge columns: comparative Study. J Struct Eng. 2019;145:04019104.
• 13. Mangalathu S, Jeon J. Classification of failure mode and prediction of shear strength for reinforced concrete beam-column joints using machine learning techniques. Eng Struct. 2018;160:85-94.
• 14. Mangalathu S, Jang H, Hwang S, Jeon J. Data-driven machine-learning-based seismic failure mode identification of reinforced concrete shear walls. Eng Struct. 2020;208: 110331.
• 15. Taffese WZ, Espinosa-Leal L. Multitarget regression models for predicting comprehensive strength and chloride resistance of concrete. J Build Eng. 2023;72: 106523.
• 16. Mai HVT, Nguyen TA, Ly HB, Tran VQ. Prediction compressive strength of concrete containing GGBFS using random forest model. Adv Civ Eng. 2021;2021:1-12.
• 17. Guo X, Hao P. Using a random forest model to predict the location of potential damage on asphalt pavement. Appl Sci. 2021;11:10396.
• 18. Pan S, Zheng Z, Guo Z, Luo H. An optimized XGBoost method for predicting reservoir porosity using petrophysical logs. J Pet Sci Eng. 2022;208: 109520.
• 19. Taffese WZ, Espinosa-Leal L. Prediction of chloride resistance level of concrete using machine learning for durability and service life assessment of building structures. J Build Eng. 2022;60: 105146.
• 20. Taffese WZ, Espinosa-Leal L. Unveiling non-steady chloride migration insights through explainable machine learning. J Build Eng. 2023;82: 108370.
• 21. Cichosz P. Data mining algorithms: explained using R, John Wiley & Sons, Ltd, Chichester, United Kingdom, 2015.
• 22. Breiman L. Bagging predictors. Mach Learn. 1996;24:123-40.
• 23. Freund Y, Schapire RE. A decision-theoretic generalization of online learning and an application to boosting. J Comput Syst Sci. 1997;55:119-39.
• 24. Friedman JH. Greedy function approximation: a gradient boosting machine. Ann Stat. 2001;29:1189-232.
• 25. Chen T, Guestrin C. XGBoost: a scalable tree boosting system, in: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016: pp. 785-794.
• 26. Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, Ye Q, Liu TY. LightGBM: a highly efficient gradient boosting decision tree, in: Adv Neural Inf Process Syst, 2017.
• 27. Al-Osta MA, Isa MN, Baluch MH, Rahman MK. Flexural behavior of reinforced concrete beams strengthened with ultra-high performance fiber reinforced concrete. Constr Build Mater. 2017;134:279-96.
• 28. Lampropoulos AP, Paschalis SA, Tsioulou OT, Dritsos SE. Strengthening of reinforced concrete beams using ultra high performance fibre reinforced concrete (UHPFRC). Eng Struct. 2016;106:370-84.
• 29. Safdar M, Matsumoto T, Kakuma K. Flexural behavior of reinforced concrete beams repaired with ultra-high performance fiber reinforced concrete (UHPFRC). Compos Struct. 2016;157:448-60.
• 30. Paschalis SA, Lampropoulos AP, Tsioulou O. Experimental and numerical study of the performance of ultra high performance fiber reinforced concrete for the flexural strengthening of full scale reinforced concrete members. Constr Build Mater. 2018;186:351-66.
• 31. Ramachandra Murthy A, Karihaloo BL, Priya DS. Flexural behavior of RC beams retrofitted with ultra-high strength concrete. Constr Build Mater. 2018;175:815-24.
• 32. Zhang Y, Li X, Zhu Y, Shao X. Experimental study on flexural behavior of damaged reinforced concrete (RC) beam strengthened by toughness-improved ultra-high performance concrete (UHPC) layer. Compos B Eng. 2020;186: 107834.
• 33. Prem PR, Murthy AR, Ramesh G, Bharatkumar BH, Iyer NR. Flexural behaviour of damaged RC beams strengthened with ultra high performance concrete. Adv Struct Eng. 2015; 2507-2069.
• 34. Pimentel M, Nunes S. Experimental tests on RC beams reinforced with a UHPFRC layer failing in bending and shear, Proc. 4th Int. Symp. Ultra-High Perform. Concr. High Perform. Mater. 2016.
• 35. Hor Y, Teo W, Kazutaka S. Experimental investigation on the behaviour of reinforced concrete slabs strengthened with ultra-high performance concrete. Constr Build Mater. 2017;155:463-74.
• 36. Kharma KM, Ahmad S, Al-Osta MA, Maslehuddin M, Al-Huri M, Khalid H, Al-Dulaijan SU. Experimental and analytical study on the effect of different repairing and strengthening strategies on flexural performance of corroded RC beams. Structures. 2022;46:336-52.
• 37. Tanarslan HM, Alver N, Jahangiri R, Yalçınkaya, Yazıcı H. Flexural strengthening of RC beams using UHPFRC laminates: bonding techniques and rebar addition. Constr Build Mater. 2017;155:45-55.
• 38. Tanarslan HM. Flexural strengthening of RC beams with prefabricated ultra high performance fibre reinforced concrete laminates. Eng Struct. 2017;151:337-48.
• 39. Martinola G, Meda A, Plizzari GA, Rinaldi Z. Strengthening and repair of RC beams with fiber reinforced concrete. Cem Concr Compos. 2010;32:731-9.
• 40. Hussein L, Amleh L. Structural behavior of ultra-high performance fiber reinforced concrete-normal strength concrete or high strength concrete composite members. Constr Build Mater. 2015;93:1105-16.
• 41. Prem PR, Murthy AR, Verma M. Theoretical modelling and acoustic emission monitoring of RC beams strengthened with UHPC. Constr Build Mater. 2018;158:670-82.
• 42. Prem PR, Murthy AR. Acoustic emission and flexural behaviour of RC beams strengthened with UHPC overlay. Constr Build Mater. 2016;123:481-92.
• 43. Zhang Y, Huang S, Zhu Y, Hussein HH, Shao X. Experimental validation of damaged reinforced concrete beam strengthened by pretensioned prestressed ultra-high-performance concrete layer. Eng Struct. 2022;260: 114251.
• 44. Tarigan NJ, Aswin M, Abu Bakar BH, Hardjasaputra H. Structural behaviour of the strengthened reinforced concrete beams using ultra high-performance fibre reinforced concrete layer. Constr Innovat. 2022.
• 45. Paschalis SA, Lampropoulos AP. Developments in the use of Ultra High Performance Fiber Reinforced Concrete as strengthening material. Eng Struct. 2021;233: 111914.
• 46. Kadhim MMA, Jawdhari A, Nadir W, Cunningham LS. Behaviour of RC beams strengthened in flexure with hybrid CFRP-reinforced UHPC overlays. Eng Struct. 2022;262: 114356.
• 47. Mirdan D, Saleh AR. Flexural performance of reinforced concrete (RC) beam strengthened by UHPC layer. Case Stud Constr Mater. 2022;17: e01655.
• 48. Shihada SM, Oida YM. Repair of pre-cracked RC beams using several cementitious materials. J Sci Res Rep. 2013;2:655-64.
• 49. Alaee FJ, Karihaloo BL. Retrofitting of reinforced concrete beams with CARDIFRC. J Compos Constr. 2003;7:174-86.
• 50. Ahmad S, Sharifa AMA, Al-Osta MA, Al-Zahrani MM, Sharifa AM, Al-Huri MA. Flexural performance of pre-damaged RC beams strengthened with different configurations of UHPFRC layer-experimental and analytical investigation. Structures. 2023;48:1772-87.
• 51. Ahmed S, Mohamed EY, Mohamed HA, Emara M. Experimental and numerical investigation of flexural behavior of RC beams retrofitted with reinforced UHPFRC layer in tension surface. Structures. 2023;49:106-23.
• 52. Shao Y, Hung CC, Billington SL. Gradual crushing of steel reinforced HPFRCC beams: experiments and simulations. J Struct Eng. 2021;147:04021114.
• 53. Liu FT, Ting KM, Zhou ZH. Isolation Forest, in 2008 Eighth IEEE International Conference on Data Mining, IEEE, 2008: pp. 413-422.
• 54. Ripan RC, Sarker IH, Anwar MM, Furhad MH, Rahat F, Hoque MM, Sarfraz M. An isolation forest learning based outlier detection approach for effectively classifying cyber anomalies. In: Abraham A, Hanne T, Castillo O, Gandhi N, NogueiraRios T, Hong TP, editors. Hybrid intelligent systems. Cham: Springer; 2021. p. 270-9.
• 55. Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay É. Scikit-learn: machine learning in python. J Mach Learn Res. 2011;12:2825-30.
• 56. Lundberg SM, Lee S-I. A Unified Approach to Interpreting Model Predictions, in NIPS’17: Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017: pp. 4768-4777.
• 57. Molnar C. Interpretable machine learning: a guide for making black box models explainable, Leanpub, 2020.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).