Correlation between Cone Penetration Test parameters, soil type, and soil liquidity index using long short-term memory neural network

• Autorzy: Jocz Mateusz , Lefik Marek

Identyfikatory

DOI

10.2478/sgem-2023-0023

• Konferencja: 19th KKMGiIG
• Języki publikacji: EN

Abstrakty

EN

Accuracy and quality of recognizing soil properties are crucial for optimal building design and for ensuring safety in the construction and exploitation stages. This article proposes use of long short-term memory (LSTM) neural network to establish a correlation between Cone Penetration Test (CPTU) results, the soil type, and the soil liquidity index IL. LSTM artificial neural network belongs to the class of networks requiring deep machine learning and is qualitatively different from artificial neural networks of the multilayer perceptron type, which have long been widely used to interpret the results of geotechnical experiments. The article outlines the methodology of CPTU testing and laboratory testing of the liquidity index, as well as construction and preparation of data for the network. The proposed network achieved good results when considering a database consisting of the parameters of eight CPTU soundings, soil stratifications, and laboratory test results.

Słowa kluczowe

EN

geotechnical parameter; Cone Penetration Test; CPTU; liquidity index; Long Short-Term Memory neural network; LSTM

• Wydawca: De Gruyter
• Czasopismo: Studia Geotechnica et Mechanica
• Rocznik: 2023
• Tom: Vol. 45, nr s1
• Strony: 405--415
• Opis fizyczny: Bibliogr. 21 poz., rys., tab.

Twórcy

autor

Jocz Mateusz

• Interdisciplinary Doctoral School, Lodz University of Technology, Żeromskiego 116, 90-924 Łódź
• Division of Geotechnics and Engineering Structures Department of Concrete Structures, Lodz University of Technology, Al. Politechniki 6, 90-924 Łódź

autor

Lefik Marek

• Division of Geotechnics and Engineering Structures Department of Concrete Structures, Lodz University of Technology, Al. Politechniki 6, 90-924 Łódź

Bibliografia

• [1] Ghaboussi J., Garrett J.H., Wu X.: Knowledge-Based Modeling of Material Behavior with Neural Networks, Journal of Engineering Mechanics, 117, s. 132–151 (1991).
• [2] Lefik M., Some aspects of application of artificial neural network for numerical modeling in civil engineering, Bulletin of the Polish Academy of Sciences. Technical Sciences, pp. 39–50. (2013).
• [3] Mayne, P.W. (2014). KN2: Interpretation of geotechnical parameters from seismic piezocone tests. Proceedings, 3rd International Symposium on Cone Penetration Testing (CPT’14, Las Vegas), ISSMGE Technical Committee TC 102, Edited by P.K. Robertson and K.I. Cabal: p 47–73 (2014).
• [4] Obrzud R.F., Truty A., and Vulliet L., Numerical modeling and neural networks to identify model parameters from piezocone tests: II. Multi-parameter identification from piezocone data, Int. J. Numerical and Analytical Methods in Geomechanics 36 (6), 743–779 (2012).
• [5] Phoon K-K., Kulhawy F.H., Characterization of geotechnical variability, Canadian geotechnical journal 36 (4), 612–624 (1999).
• [6] PN-EN 1997-1:2004: 2004 Eurocode 7: Geotechnical design.
• [7] Puakowski S., Ossowski R., Szarf K.,: Data Mining in Quick Clay Investigation – RCPTU Results Analysis with Neural Networks, International Journal for Numerical and Analytical Methods in Geomechanics (2018).
• [8] Robertson P.K., Cone penetration test (CPT)-based soil behavior type (SBT) classification system — an update, NRC Research Press, pp. 1910–1926.
• [9] Sulewska M. J., Applying Artificial Neural Networks for analysis of geotechnical problems, Computer Assisted Mechanics and Engineering Sciences, 18: 231–241, 2011.
• [10] Hochreiter S., Schmidhuber J., Long Short-term Memory, Neural Computations 9(8), 1997, 1735–1780.
• [11] Understanding LSTM Networks, https://colah.github.io/posts/2015-08-Understanding-LSTMs/index.html, 27-06-2023.
• [12] Haojie C., Gongxing Y., Jie L., Haiyan C., Xialin Y., Predicting undrained shear strength of soil from cone penetration test data applying optimized RBF approaches, Journal of Applied Science and Engineering, Vol 26, No 1, Page 121–130, 2022.
• [13] Lunne T., Robertson P.K. and Powell J.J.M., Cone Penetration Testing in Geotechnical Practice, Blackie Academic and Proffesional, 1997.
• [14] Senneset K., Sandven R., Janbu N., Evaluation of Soil Parameters from Piezocone Tests, Transportation Research Record 1235, 1989.
• [15] Lipton Z.C., Berkowitz J., Elkan C., A Critical Review of Recurrent Neural Networks for Sequence Learning, 2015.
• [16] Sulewska M.J., Zabielska-Adamska K., ANN-Based Modelling of Fly Ash Compaction Curve, Archives of Civil Engineering, LVIII, 2012.
• [17] Tumay M.T., Karasulu Y. H., Młynarek Z., Wierzbicki J., Effectiveness of CPT-Based classification methods for identification of subsoil stratigraphy, Proceedings of the 15th European Conference on Soil Mechanics and Geotechnical Engineering, IOS Press, 2011.
• [18] Wrzesiński G., Sulewska M.J., Lechowicz Z., Evaluation of the Change in Undrained Shear Strength in Cohesive Soils due to Principal Stress Rotation Using an Artificial Neural Network, Applied Sciences, 8, 781, 2018.
• [19] Sherstinsky A., Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network, Physica D: Nonlinear Phenomena, Volume 404, 2020.
• [20] Kłos M., Waszczyszyn Z., Sulewska M.J., Neural indentification of compaction characteristics for granular soils, Computer Assisted Mechanics and Engineering Sciences, 18, 265–273, 2011.
• [21] Młynarek Z., Wierzbicki J., Wołyński W., Use of functional cluster analysis of CPTU data for assessment of a subsoil rigidity, Studia Geotechnica et Mechanica, 40(2), 117–124, 2018.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).