Prediksi Nilai SPT Tanah Granular Berdasarkan Data CPT dan Properties Tanah di Sumatera Menggunakan Jaringan Saraf Tiruan
DOI:
https://doi.org/10.5614/jts.2022.29.1.5Keywords:
Standard Penetration Test, Cone Penetration Test (CPT), Tanah Nonkohesif, Jaringan Saraf Tiruan, Backpropagation.Abstract
Abstrak
Standard Penetration Test (SPT) dan Cone Penetration Test (CPT) merupakan tes penyelidikan tanah awal yang sering digunakan saat memulai suatu konstruksi. Telah banyak penelitian sebelumnya yang membahas tentang korelasi linier antara nilai SPT dan CPT, namun nilai koefisien korelasinya (R2) cenderung kecil. Jaringan saraf tiruan (JST) merupakan teknik yang dapat memecahkan masalah yang kompleks dan non-linier. Pada penelitian ini akan dilakukan prediksi nilai SPT menggunakan jaringan saraf tiruan pada tanah granular menggunakan algoritma backpropagation. Panelitian ini menggunakan 117 data dari beberapa wilayah di Provinsi Riau. Data masukan yang digunakan berupa nilai tahanan ujung (qc) dan nilai tahanan selimut (fs) dari pengujian CPT dan nilai tekanan overburden efektif (?'0) serta persentase pasir dan butiran halus. JST dianggap efektif dalam penelitian ini dengan nilai RMSE 3,646, MAE 2,533 dan R2 0,9103 untuk data latih dan RMSE 2,955, MAE 2,190, R2 0,9311 untuk data uji. Selanjutnya model JST ini disebut sebagai NN_Nspt (NC).
Kata-kata Kunci: back-propagation, CPT, granular, Jaringan Saraf Tiruan, SPT
Abstract
The Standard Penetration Test (SPT) and the Cone Penetration Test (CPT) are kinds of Soil Investigation Tests that are used to determine bearing capacity and soil parameters for designing a construction. There are many previous studies had been defined the linear correlation between SPT and CPT values. However, the linear correlation predisposed get correlation coefficient (R2) small. Artificial neural networks (ANN) is an Artificial Intelligence model that can solve complex and non-linear problems. This research aims to conduct SPT value prediction using ANN in granular soil (non-cohesive) with a backpropagation algorithm function. This study used 117 data taken from several provinces on Sumatera island. The variables of input data are taken from CPT, i.e cone resistance (qc)and sleeve resistance (fs), and from the UDS test. The laboratory data were effective overburden pressure (??0), the percentage of sand, and the percentage of fine grain. The best ANN model had a single hidden layer and 40 neurons with RMSE values 3.646, MAE 2.533, and R2 0.9103 for training data and RMSE 2.955, MAE 2.190, R2 0.9311 for testing data. Thus, the best ANN model has been proposed as NN_Nspt (NC).
Keywords: Artificial Neuron Network, back-propagation, CPT, granular, SPT
References
Ahmed, S. M., Agaiby, S. W., & Abdel-Rahman, A. H. (2014). A unified CPT-SPT correlation for non-crushable and crushable cohesionless soils. Ain Shams Engineering Journal, 5(1), 63-73. https://doi.org/10.1016/j.asej.2013.09.009
Akca, N. (2003). Correlation of SPT-CPT data from the United Arab Emirates. Engineering Geology, 67(3-4), 219-231. https://doi.org/10.1016/S0013-7952(02)00181-3
Alam, M., Aaqib, M., Sadiq, S., Mandokhail, S. J., Adeel, M. B., Maqsood-Ur-Rehman, & Kakar, N. A. (2018). Empirical SPT-CPT correlation for soils from Lahore, Pakistan. IOP Conference Series: Materials Science and Engineering, 414(1). https://doi.org/10.1088/1757-899X/414/1/012015
Chen, Y.-L., Azzam, R., & Zhang, F.-B. (2006). The displacement computation and construction pre-control of a foundation pit in Shanghai utilizing FEM and intelligent methods. Geotechnical & Geological Engineering, 24(6), 1781-1801.
dos Santos, M. D., & Bicalho, K. V. (2017). Proposals of SPT-CPT and DPL-CPT correlations for sandy soils in Brazil. Journal of Rock Mechanics and Geotechnical Engineering, 9(6), 1152-1158. https://doi.org/10.1016/j.jrmge.2017.08.001
Erzin, Y., & Tuskan, Y. (2017). Prediction of standard penetration test (SPT) value in Izmir, Turkey using radial basis neural network. Celal Bayar oeniversitesi Fen Bilimleri Dergisi, 37-41. https://doi.org/10.18466/cbayarfbe.319912
Ghaderi, A., Abbaszadeh Shahri, A., & Larsson, S. (2019). An artificial neural network based model to predict spatial soil type distribution using piezocone penetration test data (CPTu). Bulletin of Engineering Geology and the Environment, 78(6), 4579-4588. https://doi.org/10.1007/s10064-018-1400-9
Goh, A. T. C. (2002). Probabilistic neural network for evaluating seismic liquefaction potential. Canadian Geotechnical Journal, 39(1), 219-232. https://doi.org/10.1139/t01-073
Jaksa, M. B. (1995). The influence of spatial variability on the geotechnical design properties of a stiff, overconsolidated clay. Ph.D. Thesis, University of Adelaide, Australia., December. https://www.researchgate.net/publication/238346452
Kuo, Y. L., Jaksa, M. B., Lyamin, A. V., & Kaggwa, W. S. (2009). ANN-based model for predicting the bearing capacity of strip footing on multi-layered cohesive soil. Computers and Geotechnics, 36(3), 503-516. https://doi.org/10.1016/j.compgeo.2008.07.002
Kurup, P. U., & Griffin, E. P. (2006). Prediction of soil composition from CPT data using general regression neural network. Journal of Computing in Civil Engineering, 20(4), 281-289.
Lingwanda, M. I., Larsson, S., & Nyaoro, D. L. (2015). Correlations of SPT, CPT and DPL Data for Sandy Soil in Tanzania. Geotechnical and Geological Engineering, 33(5), 1221-1233. https://doi.org/10.1007/s10706-015-9897-1
Mayne, P. W. (2007). In-situ test calibrations for evaluating soil parameters. In Characterisation and Engineering Properties of Natural Soils (Vols. 3-4). https://doi.org/10.1201/noe0415426916.ch2
Neaupane, K. M., & Achet, S. H. (2004). Use of backpropagation neural network for landslide monitoring: A case study in the higher Himalaya. Engineering Geology, 74(3-4), 213-226. https://doi.org/10.1016/j.enggeo.2004.03.010
Padmini, D., Ilamparuthi, K., & Sudheer, K. P. (2008). Ultimate bearing capacity prediction of shallow foundations on cohesionless soils using neurofuzzy models. Computers and Geotechnics, 35(1), 33-46.
Shahin, M. A., Jaksa, M. B., & Maier, H. R. (2005). Neural network based stochastic design charts for settlement prediction. Canadian Geotechnical Journal, 42(1), 110-120. https://doi.org/10.1139/t04-096
Shahin, M. A., Maier, H. R., & Jaksa, M. B. (2003). Settlement prediction of shallow foundations on granular soils using B-spline neurofuzzy models. Computers and Geotechnics, 30(8), 637-647. https://doi.org/10.1016/j.compgeo.2003.09.004
Shahin, Mohamed A., Maier, H. R., & Jaksa, M. B. (2002). Predicting Settlement of Shallow Foundations using Neural Networks. Journal of Geotechnical and Geoenvironmental Engineering, 128(9), 785-793. https://doi.org/10.1061/(asce)1090-0241(2002)128:9(785)
Shahri, A., Juhlin, C., & Malemir, A. (2014). A reliable correlation of SPT-CPT data for southwest of Sweden. Electronic Journal Of Geotechnical Engineering.
Tarawneh, B. (2017). Predicting standard penetration test N-value from cone penetration test data using artificial neural networks. Geoscience Frontiers. https://doi.org/10.1016/j.gsf.2016.02.003
Zhao, H. (2008). Slope reliability analysis using a support vector machine. Computers and Geotechnics, 35(3), 459-467.