Abstract
Prediction of liquefaction potential of soils is significant in order to mitigate risk and major damages to structures. Currently used deterministic methods have drawbacks like mismatch between the assumptions in modelling and the actual in-situ conditions, observational errors. Hence many predictive techniques are being used as an alternative solution to reach a better decision and the neural networking approaches are an ideal one. This paper presents the technique of neural network to develop an Artificial Neural Network (ANN) model optimized by Particle Swarm Optimization (PSO), based on CPT data to predict the liquefaction potential of soils. The database used in this study consists of 235 CPT-based field records from ten major earthquakes over a period of 35 years. Important parameters including normalized peak horizontal acceleration at ground surface, earthquake magnitude, total vertical stress, effective vertical stress, cone resistance and depth of penetration, are selected as the input parameters for the ANN-PSO model. PSO technique is hybridized along with Artificial Neural Network (ANN) to utilize the advantage of both the techniques.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Juang H, Yuan H, Lee D-H, Lin P-S (2003) Simplified cone penetration test-based method for evaluating liquefaction resistance of soils. J Geotech Geoenviron Eng 129:66–80
Rahbarzare A, Azadi M (2019) Improving prediction of soil liquefaction using hybrid optimization algorithms and a fuzzy support vector machine. Bull Eng Geol Environ 78:4977–4987 (Springer)
Xue X, Liu E (2017) Seismic liquefaction potential assessed by neural networks. Environ Earth Sci 76:192
Farrokhzad F, Barari A, Choobbasti AJ (2010) Liquefaction micro zonation of Babol city using artificial neural network. J King Saud Univ Sci 24:89–100
Chern S-G, Lee C-Y, Wang C-C (2008) CPT-based liquefaction assessment by using fuzzy-neural network. J Mar Sci Technol 16(2):139–148
Bagheripour MH, Shooshpasha I, Afzalirad M (2012) A genetic algorithm approach for assessing soil liquefaction potential based on reliability method. J Earth Syst Sci 121:45–62
Rukhaiyar S, Alam MN, Samadhiya NK (2017) A PSO-ANN hybrid model for predicting factor of safety of slope. Int J Geotech Eng. ISSN: 1938–6362
Goharzay M, Noorzad A, Ardakani AM, Jalal M (2020) Computer-aided SPT-based reliability model for probability of liquefaction using hybrid PSO and GA. J Comput Des Eng 7(1):107–127
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Anitta Justin, C., Sankar, N. (2022). Prediction of Liquefaction of Soils Using Particle Swarm Optimization (PSO). In: Marano, G.C., Ray Chaudhuri, S., Unni Kartha, G., Kavitha, P.E., Prasad, R., Achison, R.J. (eds) Proceedings of SECON’21. SECON 2021. Lecture Notes in Civil Engineering, vol 171. Springer, Cham. https://doi.org/10.1007/978-3-030-80312-4_85
Download citation
DOI: https://doi.org/10.1007/978-3-030-80312-4_85
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-80311-7
Online ISBN: 978-3-030-80312-4
eBook Packages: EngineeringEngineering (R0)