Gradient tree boosting machine learning on predicting the failure modes of the RC panels under impact loads
- 43 Downloads
This paper proposed a new approach in predicting the local damage of reinforced concrete (RC) panels under impact loading using gradient boosting machine learning (GBML), one of the most powerful techniques in machine learning. A number of experimental data on the impact test of RC panels were collected for training and testing of the proposed model. With the lack of test data due to the high cost and complexity of the structural behavior of the panel under impact loading, it was a challenge to predict the failure mode accurately. To overcome this challenge, this study proposed a machine-learning model that uses a robust technique to solve the problem with a minimal amount of resources. Although the accuracy of the prediction result was not as high as expected due to the lack of data and the unbalance experimental output features, this paper provided a new approach that may alternatively replace the conventional method in predicting the failure mode of RC panel under impact loading. This approach is also expected to be widely used for predicting the structural behavior of component and structures under complex and extreme loads.
KeywordsImpact loading Reinforced concrete Local damage Machine learning XGboost Gradient boosting
This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2018R1C1B5086385).
Compliance with ethical standards
Conflict of interest
The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.
- 2.Ali SA, Candra H, Pires JA (2011) Finite element simulation of soft missile impacts on reinforced concrete slabs. Transactions of the 21st SMiRT, New Delhi, India, NovemberGoogle Scholar
- 4.American Concrete Institute (2001). Code Requirements of Nuclear Safety Related Concrete Structures (ACI 349-01)Google Scholar
- 6.Bao YQ, Tang ZY, Li H, Zhang YF (2018) Computer vision and deep learning–based data anomaly detection method for structural health monitoring. Struct Health Monit 18:1–21Google Scholar
- 9.Chang WS (1981) Impact of solid missiles on concrete barries. J Struct Div (ASCE) 107(2):257–271Google Scholar
- 10.Chen T, Guestrin C (2016) XGBoost: a scalable tree boosting system. arXiv preprint arXiv:1603.02754
- 12.Dunne RA, Campbell NA (1997) On the pairing of the softmax activation and cross-entropy penalty functions and the derivation of the softmax activation function. 8th Aust. Conf. on the Neural Networks, MelbourneGoogle Scholar
- 13.Goutte C, Gaussier E (2005) A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. LLNCS 3408 (Springer)Google Scholar
- 17.Hashimoto J, Takiguchi K, Nishimura K, Matsuzawa K, Tsutsui M, Ohashi Y, Kojima I, Torita H (2005) Experimental study on behavior of RC panels covered with steel plates subjected to missile impact. Transactions of the 18th SMiRT, Beijing, China, AugustGoogle Scholar
- 21.Kozlovskaia N, Zaytsev A (2017) Deep ensembles for imbalanced classification. In: 16th IEEE International Conference on Machine Learning and Applications (ICMLA). Cancun, pp 908–913Google Scholar
- 29.Orbovic N, Blahoianu A (2011) Tests on concrete slabs under hard missile impact to evaluate the influence of the transverse reinforcement and pres-stressing on perforation velocity. Transactions of the 21st SMiRT, New Delhi, India, NovemberGoogle Scholar
- 30.Orbovic N, Elgohary M, Lee NH, Blahoianu A (2009) Test on reinforced concrete slabs with pre-stressing and with transverse reinforcement under impact loading. Transactions of the 20st SMiRT, Espoo, Finland, AugustGoogle Scholar
- 32.Pires JA, Ali SA, Candra H (2011) Finite element simulation of hard missile impacts on reinforced concrete slabs. Transactions of the 21st SMiRT, New Delhi, India, NovemberGoogle Scholar
- 38.Tsubota H, Koshika N, Mizuno J, Sanai M, Peterson B, Saito H, Imamura A (1999) Scale model tests of multiple barriers against aircraft impact: part 1. experimental program and test results. Transactions of the 15th SMiRT, Seoul, Korea, AugustGoogle Scholar
- 39.Vepsa A, Saarenheimo A, Tarallo F, Rambach J-M, Orbovic N (2011) IRIS_2010-Part II: experiment data. Transaction of the 21st SMiRT, New Delhi, India, NovemberGoogle Scholar
- 45.Zhang Y, Huang Q, Ma X, Yang Z, Jiang J (2016) Using multi-features and ensemble learning method for imbalanced malware classification. IEEE Trust Com-Big DataSE-ISPA 2016:965–973Google Scholar