ASSESSMENT OF FAILURES ON CONCRETE CULVERT USING ARTIFICIAL NEURAL NETWORK
Abstract
This paper assessed the failure on concrete culvert using Artificial Neural Networks (ANNs) as a predictive tool. The research analysed data on culvert failure, including factors such as culvert axial loadings, material, shape and environmental factors to identify patterns and develop an ANN model for predicting future failures. Failures on concrete structures are sometimes visible but mostly hidden within the structures. The failure conditions are inadequate flow capacity and structural collapse. The main objective of the assessment of failures on concrete culverts is to ascertain the presence, location and severity of structural failure given the structure's dynamic characteristics. The methodology of data gathering from field observations, records, documentations and simulation. Four (4) different axial loads were used to generate algorithm inputs. Finite Element Analysis (FEA) method and Artificial Neural Network (ANN) method were used for analysis. The field data was gotten using horizontal and Vertical transducers with sensors. FEA approach and ANNs approach were applied to predict the failure of concrete culverts using the collected data as input. FEA analysis was conducted using Solidworks Software while ANN analysis was conducted using Python and Scilab software. The ANN method involved the training of the ANN model using a backpropagation algorithm to learn from the training data and predict the future outcomes. The performance of the model was evaluated using the mean squared error (MSE) and coefficient of determination (R2) metrics. FEA result was successfully gotten whereby the stresses, strains and displacements behaviours were observed. ANN was successfully trained and validated for the range of data from the investigated culvert. The study revealed that ANNs can accurately predict the possible failure of concrete culverts with an R2 value of 0.87 and MSE of 0.22. The prediction with classification accuracy of 87% is above average which showed that ANNs can successfully predict culvert failure based on the input data, and can provide a comprehensive picture of the factors that influence culvert failure.
KEYWORDS: failures, structure, data, artificial neural network, finite element model, monitoring and evaluation.
Full Text:
PDFReferences
Abdel Aal, G. M., Elsaiad, A. A., Elnikhely, E. A. and Zaki, E. M. (2019, May). Reducing the Local Scour Depth at the Culvert Outlets. International Journal of Engineering Science and Computing, 9(5), 22540-22547. Retrieved from http://ijesc.org/
Abdulkareem, M., Ganiyu, A. & Majid, M. Z. A. (2019). Damage identification in plate using Wavelet Transform and Artificial Neural Network. 10th Asia Pacific Structural Engineering and Construction Conference 2018. Malaysia: IOP Publishing. doi:10.1088/1757-899X/513/1/012015
Al-Zwainy, F. M. S., Rashed, H. A. & Ibraheem, H. F. (2012, June). Development of the Construction Productivity Estimation Model using Artficial Neural Network for Finishing Works on Floors with Marble. Journal of Engineering and Applied Sciences, 7(6), 714-722. Retrieved from www.arpnjournals.com
Aswed, G. K. (2016, January). Productivity Estimation Model for Bricklayer in Construction Projectsusing Neural Network. Al-Qadisiyah Journal of Engineering Sciences, 9(2). Retrieved from https://www.researchgate.net/publication/309430059
Bakhary, N.,Hong, H. & Deeks, A. J. (2010, February). Structural Damage Detection using Neural Network with Multi-Stage sub-Structuring. (Y. Xia, Ed.) Article in Advances in Structural Engineering, Vol. 13(1). doi:DOI: 10.1260/1369-4332.13.1.95
Bandara, R. P. (2013). Damage Identification and Condition Assessment of Building Structures using Frequency Response Functions and Neural Networks. PhD Thesis, Queensland University of Technology, Department of Civil Engineering and Built Environment, Queensland.
Behera, P. (2012). Vibration Analysis of a Beam using Neural Network Technique. B.Tech Thesis, Mechanical Engineering National Institute of Technology, Deparment of Mechanical Engineering, Rourkela. doi:789-008
Bhargava, A. S. (2011). Artificial Neural Network Based Fault Location for Transmission Lines. University of Kentucky, Department of Electrical Engineering. Lexington, Kentucky: Graduate School at Uknowledge.
Caglar, N., Elmas, M., Yaman, Z. B. & Saribiyik, M. (2008). Neural Network in 3-Dimensional Dynamics of Reinforced Concrete Building. Construction and Building Material, 22(5), 788-800. doi:10.1016/j.conbuildmat.2007.01-029
Dackermann, U. (2010). Vibration-Based Damage Identification Methods for Civil Engineering Structures using Artificial Neural Networks. PhD Thesis, University of Technology Sydney, Department of Civil Engineering, Sydney, Australia.
Dackermann, U., Li, J. & Samali, B. (2010b). Quantitative of Notch-Type Damage in a Two-Storey Framed Structure Utilising Frequency Response Functions and Artificial Neural Network. 5th World Conference on Structural Control and Monitoring, 145, pp. 1-12. Australia.
Dehghani, F. & Nezami, H. A. (2013). A New Fault Location Technique on Radial Distribution Systems using Artificial Neural Network. 22nd International Conference and Exhibition on Electricity (pp. 1-4). IET Digital Library. doi:10.1049/cp.2013.0697
Dikmen, S. U. & Sonmez, M. (2010, November). An Artificial Neural Networks Model for the Estimation of Formwork Labour. Journal of Civil Engineering and Management, 17(3), 340–347. doi:doi:10.3846/13923730.2011.594154
El-Gohary, K. M., Aziz, R. F. & Abdel-Khalek, H. A. (2017, August). Engineering Approach Using Artificial Neural Network to Improve and Predict Construction Labor Productivity under Different Influences. Journal of Construction Engineering and Management, 143(8).
Farrar, C. R., Doebling, S. W., & Nix, D. A. (2001, January 15). Vibration-Based Structural Damage Identification. The Shock and Vibration Digest 30, 359, 131-149. doi:10.2172/249299
Gholamreza, K. & Ehsan, E. (2015, May). Applying Artificial Neural Network(s) for Measuring and Predicting Construction-Labour Productivity. Journal of Construction Engineering and Management, 141. doi:10.1061/(ASCE)CO.1943-7862.0001006
Golnaraghi, S., Zangenehmadar, Z., Moselhi, O. & Alkass, S. (2019, January). Application of Artificial Neural Network(s) in Predicting Formwork Labour Productivity. (A. R. V., Ed.) Advances in Civil Engineering Article, 2019. Retrieved from https://doi.org/10.1155/2019/5972620
Hagan, M. T., Demuth, H. B., & De Jesus, O. (n.d.). Neural Network Design.
Hagan, M. T., Demuth, H. B., Beala, M. H., & De Jesu, O. (n.d.). Neural Netwrok Design (2nd ed.).
Hecht-Nusen, R. (1987). The Counterpropagation Network. Ist IEEE International Conference on Neural Network, 3, pp. 213 - 262.
Hetch-Nilsen, R. (1987). The Counterpropagation Network. Ist IEEE International Conference on Neural Network, 3, pp. 11-14.
JSTOR, Wikipedia. (2012, July). Structural Integrity. Retrieved from Wikipedia web site: en.m.wikipedia.org
Khoshnoudian, F., Talaei, S. & Fallahian, M. (2016, September). Structural Damage Detection Using FRF Data, 2D-PCA, Artiï¬cial Neural Networks and Imperialist Competitive Algorithm Simultaneously. International Journal of Structural Stability and Dynamics, 17(7), 23. doi:10.1142/S0219455417500730
King, C.H. (2017). Predicting Failures of Culverts and Associated Impact in Low Order Streams of Northern Michigan. Michigan Technological Univertsity, Department of Forest Ecology and Management. Michigan: Digital Commons, Michigan Technological Univertsity.
Kulkarni, P. S., Londhe, S. N. & Deo, M. C. (2017, August). Artificial Neural Network for Construction Management. Journal of Soft Computing Engineering1 - 2, 70-88. Retrieved from http://www.jsoftcivil.com/
Lian, Y. & Yen, B.C. (2003, February). Comparison of Risk Calculation Methods for a Culvert. Journal of Hydraulic Engineering, 140-152.
Masri S.F., Nakamma, M., Chassiakes, A.G., Caughey, T.K. (1996, April). Neural Network Approach to Detection of Changes in Structural Parameters. Journal of Engineering Mechanics, 122(4).
Masri, S. F., Nakamma, M., Chassiakes, A. G. & Caughey, T. K. (1996, April). Neural Network Approach to Detection of Changes in Structural Parameters. Journal of Engineering Mechanics, 122(4).
Meruane, V. & Heylen, W. (2011, December). Structural Damage Assessment with Anti-Resonance Versus Mode Shapes usinh Parallel Genetic Algorithm. Article in Structural Control and Health Monitoring. doi:DOI: 10.1002/stc.401
Meruane, V. & Mahu, J. (2014, February). Real-Time Structural Damage Assessment using Artificial Neural Network and Anti-Resonant Frequencies. (G. Park, Ed.) Shock and Vibration, 2014, 14 pages.
Mohammed, S. R. & Tofan, A. S. (2011, January). Neural Networks for Estimating the Ceramics Productivity of Walls. Article in University of Baghdad Engineering Journal. Retrieved from https://www.researchgate.net/publication/330910761
Mukhopadhyay, S. C & Ihara, I. (n.d.). Sensors and Technologies for Structural Health Monitoring (Vol. 96). Berlin Macquarie University, Sydney, Australia: Spinger.
Muqeem, S., Idrus, A., Khamidi, M. F., Ahmed, J. B. & Zakaria, S.B. (2011, June). Construction Labor Production Rates Modelling using Artificial Neural Network. (T. Z, Ed.) Journal of Information Technology in Construction (ITcon), 16, 713-726. Retrieved from http://www.itcon.org/2011/42
Naidu, K., Ali, M. S., Tan, C. K., Arof, H. & Mokhilis, H. (2020, January). Optimized Artificial Neural Network to Improve The Accuraccy of Estimated Fault Impedences and Distances for Underground Distribution System. (P. Ptawiak, Ed.) PLOS ONE Research Article, 1-22. Retrieved from https://doi.org/10.1371/journal.pone.0227494
Olorunfemi, K. O. & Baiyeri, M. R. (2017, June). An Investigation on Hydrogical Failure in Culverts at Ajegunle-Egbejila Road and Coca-Cola Road. Journal of Research and Development Studies, 5, 1-9.
Orukotan, A. S. (2020). Fault Detection and Classification of a Single Phase Inverter using Artificial Neural Networks. Minnesota State University, Department of Electrical Engineering. Mankato: Cornerstone.
Pan, D. G., Lei, S. S. & Wu, S. C. (2010). Two-Stage Damage Detection Method using the Artificial Neural Network(s) and Genetic Algorithms. University of Science and Technology, Beijing, Department of Civil Engineering. Beijing, China: Verlag Berlin Heidelberg.
Park, Y. S. & Lek, S. (2008). Encyclopedia of Ecology (Artificial Neural Network). Retrieved from https://doi,org/10.1016/13978-008045405-4.0073-7
Ramos, F. D., Guevara, M. S. S. L., Contreras, A. D. & Diaz, M. P. (2014). A Methodology for the Inventory of Road Culverts Pathologies Applied to the Province of Jaen (Andalusia, Spain). Procedia - Sicial and Behavioral Sciences. 160, pp. 597-606. Andalusia, Spain: Elsevier Ltd.
Raza, S., Mokhlis, H., Arof, H., Naidu, K., Laghari, J. A. & Khairuddin, A. S. M. (2016, October). Minimum-Feature-Based ANN-PSO Approach for Islanding Detection in Distribution System. IET Renewable Power Generation, 10(9), 1255 – 1263. doi: 10.1049/iet-rpg.2016.0080
Reboucas, D. L., De Araujo, F. M. U. & Maitelli, A. L. (2012). Use of Artificial Neural Network to Fault Detection and Diagnosis. An ABCM Symposium Series in Mechatronics, 5, 666-675.
Reducing the Local Scour Depth at the Culvert Outlets†International Journal of Engineering Science and Computing. (n.d.).
Rossum, G. V. (1991). Python. Python Software Foundation.
Sasan Golnaraghi, Zahra Zangenehmadar, Osama Moselhi, and Sabah Alkass. (2019, January). Application of Artificial Neural Network(s) in Predicting Formwork Labour Productivity. (A. R. Vosoughi, Ed.) Article in Advances in Civil Engineering.
Sorourian, S., Keshavarzi, A. & Ball, J. E. (2016). Scour at partially blocked Box-culverts under steady flow. Proceedings of the Institution of Civil Engineers Water Management. 169 Issue WM6, pp. 247-59. Australia: ICE Institution of Civil Engineering. Retrieved from http://dx.doi.org/10.1680/jwama.15.00019
Systemes, D. (1995). SolidWorks. Dassault Systemes.
Systemes, D. (2021). Scilab. Dassault Systemes.
Zweiri, Y. H., Whidborne, J. & Seneviratue, L. (2003, January). A Three-Term Backpropagation Algorithm. doi:10.1016/Soa25-2312(02)00569-6
Zweiri, Y. H., Whidborne, J., & Seneviratue, L. (2003, January). A Three-Term Backpropagation Algorithm. Neurocomputing, 50(3), 305 - 318. doi:10.1016/soa25-2312(02)00569-6
Refbacks
- There are currently no refbacks.
Copyright © 2022-2025. Department of Civil Engineering, Nnamdi Azikiwe University. All Rights Reserved..