Structural Engineering and Mechanics

  • 제91권1호
  • /
  • Pages.39-47
  • /
  • 2024
  • /
  • 1225-4568(pISSN)
  • /
  • 1598-6217(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

Comparison of regression model and LSTM-RNN model in predicting deterioration of prestressed concrete box girder bridges

  • Gao Jing (School of Architecture and Civil Engineering, Xiamen University) ;
  • Lin Ruiying (Xiamen Road and Bridge Engineering Investment Development Co. LTD) ;
  • Zhang Yao (School of Architecture and Civil Engineering, Xiamen University)
  • 투고 : 2023.04.17
  • 심사 : 2024.06.21
  • 발행 : 2024.07.10
⟨ 이전 논문 다음 논문 ⟩

초록

Bridge deterioration shows the change of bridge condition during its operation, and predicting bridge deterioration is important for implementing predictive protection and planning future maintenance. However, in practical application, the raw inspection data of bridges are not continuous, which has a greater impact on the accuracy of the prediction results. Therefore, two kinds of bridge deterioration models are established in this paper: one is based on the traditional regression theory, combined with the distribution fitting theory to preprocess the data, which solves the problem of irregular distribution and incomplete quantity of raw data. Secondly, based on the theory of Long Short-Term Memory (LSTM) Recurrent Neural Network (RNN), the network is trained using the raw inspection data, which can realize the prediction of the future deterioration of bridges through the historical data. And the inspection data of 60 prestressed concrete box girder bridges in Xiamen, China are used as an example for validation and comparative analysis, and the results show that both deterioration models can predict the deterioration of prestressed concrete box girder bridges. The regression model shows that the bridge deteriorates gradually, while the LSTM-RNN model shows that the bridge keeps great condition during the first 5 years and degrades rapidly from 5 years to 15 years. Based on the current inspection database, the LSTM-RNN model performs better than the regression model because it has smaller prediction error. With the continuous improvement of the database, the results of this study can be extended to other bridge types or other degradation factors can be introduced to improve the accuracy and usefulness of the deterioration model.

키워드

과제정보

The authors would like to acknowledge the financial support from the Fundamental Research Funds for the Central Universities (20720220070).

참고문헌

  1. Abdelmaksoud, A.M., Balomenos, G.P. and Becker, T.C. (2022), "Fuzzy-Logistic models for incorporating epistemic uncertainty in bridge management decisions", ASCE-ASME J. Risk Uncertain. Eng. Syst., Part A: Civil Eng., 8(3), 04022025. https://doi.org/10.1061/AJRUA6.0001247. 
  2. Ali, G., Elsayegh, A., Assaad, R., El-Adaway, I.H. and Abotaleb, I.S. (2019), "Artificial neural network model for bridge deterioration and assessment", Missouri University of Science and Technology. 
  3. Axon, E.G., Murray, L.T. and Rucker, R.M. (1969), "A study of deterioration in concrete bridge decks", Highway Research Record, 268. 
  4. Busa, G., Cassella, M., Gazda, W. and Horn, R. (1985), "A national bridge deterioration model (Staff Study No. SS-42-U5-26)", Transportation Systems Center, Cambridge, MA, USA. 
  5. Callow, D., Lee, J., Blumenstein, M., Guan, H. and Loo, Y.C. (2013), "Development of hybrid optimisation method for Artificial Intelligence based bridge deterioration model-Feasibility study", Auto. Construct., 31, 83-91. https://doi.org/10.1016/j.autcon.2012.11.016. 
  6. Chakrabarty, D. (2013), "Curve fitting: Step-wise least squares method", Journal Impact Factor, 0-489. 
  7. Chang, M., Maguire, M. and Sun, Y. (2017), "Framework for mitigating human bias in selection of explanatory variables for bridge deterioration modeling", J. Infrastr. Syst., 23(3), 04017002. https://doi.org/10.1061/(ASCE)IS.1943-555X.0000352. 
  8. Choudhury, J.R. and Hasnat, A. (2015), "Bridge collapses around the world: Causes and mechanisms", IABSE-JSCE Joint Conference on Advances in Bridge Engineering-III, Dhaka, Bangladesh. 
  9. Choi, Y., Lee, J. and Kong, J. (2020), "Performance degradation model for concrete deck of bridge using pseudo-LSTM", Sustainab., 12(9), 3848. https://doi.org/10.3390/su12093848. 
  10. Crumpton, C.F., Pattengill, M.G. and Badgley, W.A. (1969). "Bridge deck deterioration study, part 8: special study of blue rapids bridge deck", State Highway Commission of Kansas, Planning and Development Department, Research Division. 
  11. Ghonima, O., Anderson, J.C., Schumacher, T. and Unnikrishnan, A. (2020), "Performance of US concrete highway bridge decks characterized by random parameters binary logistic regression", ASCE-ASME J. Risk Uncertain. Eng. Syst., Part A: Civil Eng., 6(1), 04019025. https://doi.org/10.1061/AJRUA6.0001031. 
  12. Guest, G., Zhang, J., Atadero, R. and Shirkhani, H. (2020), "Incorporating the effects of climate change into bridge deterioration modeling: the case of slab-on-girder highway bridge deck designs across Canada", J. Mater. Civil Eng., 32(7), 04020175. https://doi.org/10.1061/(ASCE)MT.1943-5533.0003245. 
  13. Guo, X., Chen, Z., Sun, L. and Ji, W. (2017). "Deterioration analysis and forecasting model of urban bridges", 17th COTA International Conference of Transportation Professionals, Reston, VA, July. 
  14. Hallinan Jr, A.J. (1993), "A review of the Weibull distribution", J. Qual. Technol., 25(2), 85-93. https://doi.org/10.1080/00224065.1993.11979431. 
  15. Hasan, M.S. (2015), "Deterioration prediction of concrete bridge components using artificial intelligence and stochastic methods", RMIT University. 
  16. Huang, R.Y., Mao, I.S. and Lee, H.K. (2010), "Exploring the deterioration factors of RC bridge decks: a rough set approach", Comput.-Aid. Civil Infrastr. Eng., 25(7), 517-529. https://doi.org/10.1111/j.14678667.2010.00665.x. 
  17. Huang, Y.H. (2010), "Artificial neural network model of bridge deterioration", J. Perform. Constr. Facil., 24(6), 597-602. https://doi.org/10.1061/(ASCE)CF.1943-5509.0000124. 
  18. Ilbeigi, M. and Ebrahimi Meimand, M. (2020), "Statistical forecasting of bridge deterioration conditions", J. Perform. Constr. Facil., 34(1), 04019104. https://doi.org/10.1061/(ASCE)CF.1943-5509.0001347. 
  19. Jiang, Y., Saito, M. and Sinha, K.C. (1988), Bridge Performance Prediction Model using the Markov Chain. 
  20. Kwon, T.H., Kim, J., Park, K.T. and Jung, K.S. (2022), "Long short-term memory-based methodology for predicting carbonation models of reinforced concrete slab bridges: Case Study in South Korea", Appl. Sci., 12(23), 12470. https://doi.org/10.3390/app122312470. 
  21. Lee, J., Guan, H., Loo, Y.C. and Blumenstein, M. (2014), "Development of a long-term bridge element performance model using Elman Neural Networks", J. Infrastr. Syst., 20(3), 04014013. https://doi.org/10.1061/(ASCE)IS.1943-555X.0000197. 
  22. Leivo, M., Sistonen, E., Al-Neshawy, F., Piironen, J., Kuosa, H., Holt, E., Koskinen, P. and Nordqvist, C. (2011), "Effect of interacted deterioration parameters on service life of concrete structures in cold environments", Laboratory Test Result 2009-2011, V. T. R. C. o., Finland. 
  23. Li, L., Li, F., Chen, Z. and Sun, L. (2016), "Use of Markov chain model based on actual repair status to predict bridge deterioration in Shanghai, China", Transp. Res. Record, 2550(1), 106-114. https://doi.org/10.3141/2550-14. 
  24. Li, Y., Dong, Y., Frangopol, D.M. and Gautam, D. (2020), "Long-term resilience and loss assessment of highway bridges under multiple natural hazards", Struct. Infrastr. Eng., 16(4), 626-641. https://doi.org/10.1080/15732479.2019.1699936. 
  25. Lim, S. and Chi, S. (2019), "Xgboost application on bridge management systems for proactive damage estimation", Adv. Eng. Inform., 41, 100922. https://doi.org/10.1016/j.aei.2019.100922. 
  26. Liu, K. and El-Gohary, N. (2022), "Deep learning-based analytics of multisource heterogeneous bridge data for enhanced data-driven bridge deterioration prediction", J. Comput. Civil Eng., 36(5), 04022023. https://doi.org/10.1061/(ASCE)CP.1943-5487.0001018. 
  27. Lu, P., Pei, S. and Tolliver, D. (2016), "Regression model evaluation for highway bridge component deterioration using national bridge inventory data", J. Transp. Res. Forum, 55(1), 5-16. https://doi.org/10.22004/ag.econ.262649. 
  28. Ma, Y., Zhang, J., Wang, L. and Liu, Y. (2013), "Probabilistic prediction with Bayesian updating for strength degradation of RC bridge beams", Struct. Saf., 44, 102-109. https://doi.org/10.1016/j.strusafe.2013.07.006. 
  29. Markovsky, I. and Van Huffel, S. (2007), "Overview of total least-squares methods", Signal Proc., 87(10), 2283-2302. https://doi.org/10.1016/j.sigpro.2007.04.004. 
  30. Miao, P. and Yokota, H. (2022), "Comparison of Markov chain and recurrent neural network in predicting bridge deterioration considering various factors", Struct. Infrastr. Eng., 20(2), 250-262. https://doi.org/10.1080/15732479.2022.2087691. 
  31. Miao, P., Yokota, H. and Zhang, Y. (2023), "Deterioration prediction of existing concrete bridges using a LSTM recurrent neural network", Struct. Infrastr. Eng., 19(4), 475-489. https://doi.org/10.1080/15732479.2021.1951778. 
  32. Morcous, G. (2000), "Case-based reasoning for modeling bridge deterioration", Concordia University. 
  33. Pan, N.F. (2007), "Forecasting bridge deck conditions using fuzzy regression analysis", J. Chin. Inst. Eng., 30(4), 593-603. https://doi.org/10.1080/02533839.2007.9671288. 
  34. Papadakis, V.G. (2013), "Service life prediction of a reinforced concrete bridge exposed to chloride induced deterioration", Adv. Concrete Constr., 1(3), 201. https://doi.org/10.12989/acc2013.1.3.201. 
  35. Riedmiller, M. and Braun, H. (1993), "A direct adaptive method for faster backpropagation learning: The RPROP algorithm", IEEE International Conference on Neural Networks, 586-591. https://doi.org/10.1109/ICNN.1993.298623. 
  36. Santamaria, M., Fernandes, J. and Matos, J.C. (2019), "Overview on performance predictive models-Application to Bridge Management Systems", IABSE Symposium, 1222-1229. 
  37. Sobanjo, J., Mtenga, P. and Rambo-Roddenberry, M. (2010), "Reliability-based modeling of bridge deterioration hazards", J. Bridge Eng., 15(6), 671-683. https://doi.org/10.1061/(ASCE)BE.1943-5592.0000074. 
  38. Srikanth, I. and Arockiasamy, M. (2020), "Deterioration models for prediction of remaining useful life of timber and concrete bridges: A review", J. Traffic Transp. Eng. (English Ed.), 7(2), 152-173. https://doi.org/10.1016/j.jtte.2019.09.005. 
  39. Srikanth, I. and Arockiasamy, M. (2022), "Development of non-parametric deterioration models for risk and reliability assessments of concrete and timber bridges", J. Perform. Constr. Facil., 36(1), 04021114. https://doi.org/10.1061/(ASCE)CF.19435509.0001692. 
  40. Vesikari, E., Kuosa, H., Piironen, J. and Ferreira, R.M. (2012), "Modelling synergistic effects of carbonation/chloride penetration and frost attack for service life design of concrete bridges", 6th International Conference on Bridge Maintenance, Safety and Management, IABMAS 2012, 3927-3933. 
  41. Wang, F., Lee, C.C.B. and Gharaibeh, N.G. (2022), "Network-level bridge deterioration prediction models that consider the effect of maintenance and rehabilitation", J. Infrastr. Syst., 28(1), 05021009. https://doi.org/10.1061/(ASCE)IS.1943-555X.0000662. 
  42. Wellalage, N.K.W., Zhang, T. and Dwight, R. (2015), "Calibrating Markov chain-based deterioration models for predicting future conditions of railway bridge elements", J. Bridge Eng., 20(2), 04014060. https://doi.org/10.1061/(ASCE)BE.1943-5592.0000640. 
  43. Zhu, J. and Wang, Y. (2021), "Feature selection and deep learning for deterioration prediction of the bridges", J. Perform. Constr. Facil., 35(6), 04021078. https://doi.org/10.1061/(ASCE)CF.1943-5509.0001653.