Skip to main content
SpringerLink
Log in

Damage Prediction on Bridge Decks considering Environmental Effects with the Application of Deep Neural Networks

  • Construction Management
  • Published:
KSCE Journal of Civil Engineering Aims and scope

Abstract

Due to limited budgets and professional manpower, predicting possible damage in advance is essential for supporting on-site bridge inspections. This study aims to predict the severity of damage on bridge decks considering the effects of traffic and weather. First, the authors obtained identification, structural, environmental, and inspection data of pre-stressed concrete I-type bridges from the Korean Bridge Management System, and the final dataset of 16,728 tuples and 53 variables was prepared. Next, correlation analysis was performed to remove redundant variables, and random forest identified important factors that caused the more serious condition of damage to the deck. A total of 32 variables were finally used to develop Deep Neural Networks to predict different types of deck damage. The developed model successfully predicted the occurrences of seven different types of damage to bridge decks, that is, linear cracking, map cracking, scaling, breakage, leakage, efflorescence, and corrosion of exposed rebar, with the average weighted F1 score of 91%. Environmental effects on prediction were also determined; for example, traffic, temperature, and precipitation increased the F1 score of linear cracking by 4%. This research was a pioneering attempt to develop a model that enables specific damage-level prediction using both statistics and artificial intelligence techniques.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Aberle T, Keller A, Zurbriggen R (2007) Efflorescence mechanisms of formation and ways to prevent. Proceedings of 2nd national congress of construction mortars, November 24–25, Lisbon, Portugal (in Portuguese)

  • Agrawal AK, Kawaguchi A, Chen Z (2010) Deterioration rates of typical bridge elements in New York. Journal of Bridge Engineering 15(4):419–429, DOI: https://doi.org/10.1061/(ASCE)BE.1943-5592.0000123

    Article  Google Scholar 

  • Akula M, Sandur A, Kamat VR, Prakash A (2015) Context-aware framework for highway bridge inspections. Journal of Computing in Civil Engineering 29(1):04014027, DOI: https://doi.org/10.1061/(ASCE)CP.1943-5487.0000292

    Article  Google Scholar 

  • ASCE (2017) ASCE’s 2017 infrastructure report card — Bridges. American Society of Civil Engineers (ASCE), Retrieved March 25, 2018, https://www.infrastructurereportcard.org/cat-item/bridges/

  • Bektas BA, Carriquiry A, Smadi O (2013) Using classification trees for predicting National Bridge Inventory condition ratings. Journal of Infrastructure Systems 19(4):425–433, DOI: https://doi.org/10.1061/(ASCE)IS.1943-555X.0000143

    Article  Google Scholar 

  • Bishop CM (2006) Pattern recognition and machine learning. Springer, New York, NY, USA, 241–249

    MATH  Google Scholar 

  • Castro-Borges P, Veleva L, Balancán-Zapata M, Mendoza-Rangel JM, Juárez-Ruiz LA (2013) Effect of environmental changes on chemical and electrochemical parameters in reinforced concrete: The case of a tropical marine atmosphere. International Journal of Electrochemical Science 8(5):6204–6211

    Google Scholar 

  • Cattan J, Mohammadi J (1997) Analysis of bridge condition rating data using neural networks. Computer — Aided Civil and Infrastructure Engineering 12(6):419–429, DOI: https://doi.org/10.1111/0885-9507.00074

    Article  Google Scholar 

  • Colignatus T (2007) A measure of association (correlation) in nominal data (contingency tables), using determinants. MPRA Paper No. 2662, Munich Personal RePEc Archive (MPRA), Retrieved March 26, 2019, https://mpra.ub.uni-muenchen.de/2662/

  • Cramér H (1946) Mathematical methods of statistics. Princeton University Press, Princeton, NJ, USA

    MATH  Google Scholar 

  • Creary PA, Fang FC (2013) The data mining approach for analyzing infrastructure operating conditions. Procedia — Social and Behavioral Sciences 96:2835–2845, DOI: https://doi.org/10.1016/j.sbspro.2013.08.316

    Article  Google Scholar 

  • Cusson D, Lounis Z, Daigle L (2011) Durability monitoring for improved service life predictions of concrete bridge decks in corrosive environments. Computer-Aided Civil and Infrastructure Engineering 26(7):524–541, DOI: https://doi.org/10.1111/j.1467-8667.2010.00710.x

    Article  Google Scholar 

  • Dadson DK, de la Garza JM, Weyers RE (2002) Service life and impact of Virginia environmental exposure condition on paint on steel girder bridges. Journal of Infrastructure Systems 8(4):149–159, DOI: https://doi.org/10.1061/(ASCE)1076-0342(2002)8:4(149)

    Article  Google Scholar 

  • Dekelbab W, Al-Wazeer A, Harris B (2008) History lessons from the national bridge inventory. Public Roads 71(6):30–41

    Google Scholar 

  • Deschenes Jr. RA, Giannini ER, Drimalas T, Fournier B, Hale WM (2018) Effects of moisture, temperature, and freezing and thawing on alkali-silica reaction. ACI Materials Journal 115(4):575–584, DOI: https://doi.org/10.14359/5170219

    Article  Google Scholar 

  • Elhag T, Wang Y (2007) Risk assessment for bridge maintenance projects: Neural networks versus regression techniques. Journal of Computing in Civil Engineering 21(6):402–409, DOI: https://doi.org/10.1061/(ASCE)0887-3801(2007)21:6(402)

    Article  Google Scholar 

  • Freyermuth CL, Klieger P, Stark DC, Wenke HN (1970) Durability of concrete bridge decks — A review of cooperative studies. Highway Research Record (328):50–60

  • Gong H, Sun Y Huang B (2019) Gradient boosted models for enhancing fatigue cracking prediction in mechanistic-empirical pavement design guide. Journal of Transportation Engineering, Part B: Pavements 145(2):4019014, DOI: https://doi.org/10.1061/JPEODX.0000121

    Google Scholar 

  • Goodfellow I, Bengio Y, Courville A (2016) Deep learning. The MIT Press, Cambridge, MA, USA

    MATH  Google Scholar 

  • Hammerla NY, Halloran S, Plötz T (2016) Deep, convolutional, and recurrent models for human activity recognition using wearables. Proceedings of 25th international joint conference on artificial intelligence (IJCAI-16), July 9–15, New York, NY, USA

  • Han J, Pei J, Kamber M (2012) Data mining: Concepts and techniques, 3rd edition. Elsevier, Waltham, MA, USA, 420–421, 489–490

    MATH  Google Scholar 

  • Haykin S (1999) Neural networks: A comprehensive foundation — Introduction. Prentice-Hall, Upper Saddle River, NJ, USA

    MATH  Google Scholar 

  • Hira ZM, Gillies DF (2015) A review of feature selection and feature extraction methods applied on microarray data. Advances in Bioinformatics 2015, DOI: https://doi.org/10.1155/2015/198363

  • Huang Y (2010) Artificial Neural Network model of bridge deterioration. Journal of Performance of Constructed Facilities 24(6):597–602, DOI: https://doi.org/10.1061/(ASCE)CF.1943-5509.0000124

    Article  Google Scholar 

  • Huang RY, Chen PF (2012) Analysis of influential factors and association rules for bridge deck deterioration with utilization of national bridge inventory. Journal of Marine Science and Technology 20(3):336–344, DOI: https://doi.org/10.6119/JMST.201207_20(3).0013

    Google Scholar 

  • Huang J, Huang N, Zhang L, Xu H (2012) A method for feature selection based on the correlation analysis. 2012 international conference on measurement, information and control (MIC), May 18–20, Harbin, China

  • Huang R-Y, Mao IS, Lee H-K (2010) Exploring the deterioration factors of RC bridge decks: A rough set approach. Computer-Aided Civil and Infrastructure Engineering 25(7):517–529, DOI: https://doi.org/10.1111/J.1467-8667.2010.00665.x

    Article  Google Scholar 

  • Huang Q, Ong K-L, Alahakoon D (2015) Improving bridge deterioration modelling using rainfall data from the bureau of meteorology. Proceedings of 13th Australasian data mining conference (AusDM 2015), August 8–9, Sydney, Australia

  • Jović A, Brkić K, Bogunović N (2015) A review of feature selection methods with applications. Proceedings of 38th international convention on information and communication technology, electronics and microelectronics (MIPRO), May 25–29, Opatija, Croatia

  • KISTEC (2018) Annual report of facility management system. Korea Infrastructure Safety Corporation (KISTEC), Goyang, Korea (in Korean)

    Google Scholar 

  • Kušar M (2017) Bridge inspection quality improvement using standard inspection methods. Proceedings of the Joint COST TU1402 — COST TU1406 — IABSE WC1 Workshop: The value of structural health monitoring for the reliable bridge management, March 2–3, Zagreb, Croatia

  • Lee J, Guan H, Loo Y, Blumenstein M (2014) Development of a long-term bridge element performance model using Elman Neural Networks. Journal of Infrastructure Systems 20(3):4014013, DOI: https://doi.org/10.1061/(ASCE)IS.1943-555X.0000197

    Article  Google Scholar 

  • Lee J, Sanmugarasa K, Blumenstein M, Loo Y-C (2008) Improving the reliability of a bridge management system (BMS) using an ANN-based backward prediction model (BPM). Automation in Construction 17(6):758–772, DOI: https://doi.org/10.1016/j.autcon.2008.02.008

    Article  Google Scholar 

  • Melhem HG, Cheng Y, Kossler D, Scherschligt D (2003) Wrapper methods for inductive learning: Example application to bridge decks. Journal of Computing in Civil Engineering 17(1):46–57, DOI: https://doi.org/10.1061/(ASCE)0887-3801(2003)17:1(46)

    Article  Google Scholar 

  • Mitchell MN (2010) Data management using Stata: A practical handbook. Stata Press, College Station, TX, USA

    Google Scholar 

  • MOLIT, KISTEC (2017) A guidebook of detailed instructions of safety inspection and precise diagnosis. Ministry of Land, Infrastructure and Transport of Korea (MOLIT) and Korea Infrastructure Safety Corporation (KISTEC) (in Korean)

  • Morcous G (2005) Modeling bridge deck deterioration by using decision tree algorithms. Transportation Research Record: Journal of the Transportation Research Board 11(S):509–516

    Article  Google Scholar 

  • Morcous G, Rivard H, Hanna A (2002) Modeling bridge deterioration using case-based reasoning. Journal of Infrastructure Systems 8(3):86–95, DOI: https://doi.org/10.1061/(ASCE)1076-0342(2002)8:3(86)

    Article  Google Scholar 

  • PCA (2002) Types and causes of concrete deterioration. PCA R&D Serial No. 2617, Portland Cement Association (PCA), Stokie, IL, USA

    Google Scholar 

  • Pedregosa F, Varoquaux Q 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 E (2011a) Scikit-learn: Machine Learning in Python — 3.3.2.8.2. Multiclass and multilabel classification. Scikit-Learn Developers, Retrieved December 20, 2019, https://scikit-learn.org/stable/modules/model_evaluation.html#multiclass-and-multilabel-classification

  • 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 E (2011b) Scikitlearn: Machine learning in Python — Selecting the number of clusters with silhouette analysis on KMeans clustering. Scikit-Learn Developers, Retrieved April 12, 2019, https://scikit-learn.org/stable/auto_examples/cluster/plot_kmeans_silhouette_analysis.html

  • Reddy MC, Balasubramanyam P, Subbarayudu M (2013) An effective approach to resolve multicollinearity in agriculture data. International Journal of Research in Electronics and Computer Engineering 1(1):27–30

    Google Scholar 

  • Ryan TW, Mann JE, Chill ZM, Ott BT (2012) Bridge inspector’s reference manual. FHWA NHI 12–049, Federal Highway Administration National Highway Institute (HNHI-10), Arlington, VA, USA

    Google Scholar 

  • Scherer WT, Glagola DM (1994) Markovian models for bridge maintenance management. Journal of Transportation Engineering 120(1):37–51, DOI: https://doi.org/10.1061/(ASCE)0733-947X(1994)120:1(37)

    Article  Google Scholar 

  • Schultz AE, Gastineau AJ (2015) Innovative bridge design handbook — Bridge collapse. Butterworth-Heinemann, Oxford, UK, 795–815

    Google Scholar 

  • Scott M, Rezaizadeh A, Delahaza A, Santos CG, Moore M, Graybeal B, Washer G (2003) A comparison of nondestructive evaluation methods for bridge deck assessment. NDT and E International 36(4):245–255, DOI: https://doi.org/10.1016/S0963-8695(02)00061-0

    Article  Google Scholar 

  • Shan Y, Contreras-Nieto C, Lewis P (2016) Using data analytics to characterize steel bridge deterioration. Proceedings of construction research congress 2016, May 31-June 2, San Juan, Puerto Rico

  • Tokdemir OB, Ayvalik C, Mohammadi J (2000) Prediction of highway bridge performance by artificial neural networks and genetic algorithms. Proceedings of 17th international association for automation and robotics in construction (ISARC), September 18–20, Taipei, Taiwan

  • Tuv E, Borisov A, Runger G, Torkkola K (2009) Feature selection with ensembles, artificial variables, and redundancy elimination. Journal of Machine Learning Research 10(7):1341–1366

    MathSciNet  MATH  Google Scholar 

  • Wang X, Nguyen M, Foliente G, Ye L (2007) An approach to modelling concrete bridge condition deterioration using a statistical causal relationship based on inspection data. Structure and Infrastructure Engineering 3(1):3–15, DOI: https://doi.org/10.1080/15732470500103682

    Article  Google Scholar 

  • Wang H, Yang F, Luo Z (2016) An experimental study of the intrinsic stability of random forest variable importance measures. BMC Bioinformatics 17(1):60–77, DOI: https://doi.org/10.1186/s12859-016-0900-5

    Article  Google Scholar 

  • Wang H, Zheng H (2013) True positive rate. In: Dubitzky W, Wolkenhauer O, Cho KH, Yokota H (eds) Encyclopedia of systems biology. Springer, New York, NY, USA, DOI: https://doi.org/10.1007/978-1-4419-9863-7_255

    Google Scholar 

  • Yianni PC, Neves LC, Rama D, Andrews JD, Dean R (2016) Incorporating local environmental factors into railway bridge asset management. Engineering Structures 128:362–373, DOI: https://doi.org/10.1016/j.engstruct.2016.09.038

    Article  Google Scholar 

  • Zhang Y, O’Connor SM, van der Linden GW, Prakash A, Lynch JP (2016) SenStore: A scalable cyberinfrastructure platform for implementation of data-to-decision frameworks for infrastructure health management. Journal of Computing in Civil Engineering 30(5):4016011–4016012, DOI: https://doi.org/10.1061/(ASCE)CP.1943-5487.0000560

    Article  Google Scholar 

  • Zhao Z, Chen C (2002) A fuzzy system for concrete bridge damage diagnosis. Computers & Structures 80(7–8):629–641, DOI: https://doi.org/10.1016/S0045-7949(02)00031-7

    Article  Google Scholar 

Download references

Acknowledgments

This research was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF), funded by the Ministry of Science, ICT & Future Planning under Grant [number 2017R1C1B2009237] and the MOTIE (Ministry of Trade, Industry, and Energy) in Korea, under the Fostering Global Talents for Innovative Growth Program under Grant [number P0008747] supervised by the Korea Institute for Advancement of Technology (KIAT).

Author information

Authors and Affiliations

  1. Dept. of Construction Science, Texas A&M University, College Station, TX, 77843, USA

    Soram Lim

  2. Dept. of Civil and Environmental Engineering, Seoul National University, Seoul, 08826, Korea

    Seokho Chi

  3. The Institute of Construction and Environmental Engineering (ICEE), Seoul, 08826, Korea

    Seokho Chi

Authors
  1. Soram Lim
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Seokho Chi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Seokho Chi.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lim, S., Chi, S. Damage Prediction on Bridge Decks considering Environmental Effects with the Application of Deep Neural Networks. KSCE J Civ Eng 25, 371–385 (2021). https://doi.org/10.1007/s12205-020-5669-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12205-020-5669-4

Keywords

Search

Navigation