Open AccessEstimation of standard penetration test value on cohesive soil using artificial neural network without data normalization
Author(s) -
Soewignjo Agus Nugroho,
Hendra Fernando,
Reni Suryanita
Publication year - 2022
Publication title -
iaes international journal of artificial intelligence
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.341
H-Index - 7
eISSN - 2252-8938
pISSN - 2089-4872
DOI - 10.11591/ijai.v11.i1.pp210-220
Subject(s) - mean squared error , artificial neural network , standard penetration test , normalization (sociology) , test data , cone penetration test , silt , penetration test , atterberg limits , nonlinear system , computer science , mean absolute error , statistics , mathematics , geotechnical engineering , soil science , environmental science , artificial intelligence , geology , soil water , paleontology , physics , subgrade , quantum mechanics , sociology , anthropology , programming language , liquefaction
Artificial neural networks (ANNs) are often used recently by researchers to solve complex and nonlinear problems. Standard penetration test (SPT) and cone penetration test (CPT) are field tests that are often used to obtain soil parameters. There have been many previous studies that examined the value obtained through the SPT test with the CPT test, but the research carried out still uses equations that are linear. This research will conduct an estimated value of SPT on cohesive soil using CPT data in the form of end resistance and blanket resistance, and laboratory test data such as effective overburden pressure, liquid limit, plastic limit and percentage of sand, silt and clay. This study used 242 data with testing areas in several cities on the island of Sumatra, Indonesia. The developed artificial neural network will be created without data normalization. The final results of this study are in the form of root mean square error (RMSE) values 3.441, mean absolute error (MAE) 2.318 and R2 0.9451 for training data and RMSE 2.785, MAE 2.085, R2 0.9792 for test data. The RMSE, MAE and R2 values in this study indicate that the ANN that has been developed is considered quite good and efficient in estimating the SPT value.