Artificial neural networks (ANN) are now widely used and are becoming popular among researchers, especially in the geotechnical field. In general, data normalization is carried out to make ANN whose range is in accordance with the activation function used. Other studies have tried to create an ANN without normalizing the data and ANN is considered capable of making predictions. In this study, a comparison of ANN with and without data normalization was carried out in predicting SPT values based on CPT data and soil physical properties on cohesive soils. The input data used in this study are the value of tip resistance, sleeve resistance, effective soil overburden pressure, liquid limit, plastic limit and percentage of sand, silt and clay. The results showed that the ANN was able to make predictions effectively both on networks with and without data normalization. In this study, it was found that the ANN without data normalization showed a smaller error value than the ANN with data normalization. In the network model without data normalization, RMSE values were 3.024, MAE 1.822, R2 0.952 on the training data and RMSE 2.163, MAE 1.233 and R2 0.976 on the test data. Whereas in the ANN with data normalization, the RMSE values were 3.441, MAE 2.318, R2 0.936 in the training data and RMSE 2.785, MAE 2.085 and R2 0.963 in the test data. ANN with normalization provides a simpler architecture, which only requires 1 hidden layer compared to ANN without normalization which requires 2 hidden layer architecture.
Soil investigation is the main key in starting a construction. Standard Penetration Test (SPT) and Cone Penetration Test (CPT) are field tests that are often used in estimating soil parameters for foundation design purposes. The SPT value shows a correlation with the CPT value and other soil parameters. At present, there have been many conventional correlations examining these correlations, but the nonlinear nature of the soil due to very complex soil formations means that this correlation cannot be used in all situations. Artificial neural networks (ANN) are often used to estimate a complex and nonlinear value. In this study, that will predict the value of SPT on cohesive soil based on CPT test data and soil physical properties using artificial neural network capabilities using the Backpropagation algorithm and the activation function is bipolar sigmoid. This study uses 284 data from several places in Sumatra Island, Indonesia with data input are tip resistance (qc), shaft resistance (fs), effective overburden pressure (σ'0), percentage of liquid limit, plastic limit, sand, silt and clay. This study shows that the artificial neural network is able and effective in predicting the N-SPT value with a small error value and a strong regression equation. In this study, RMSE 3,441, MAE 2,318 and R 2 0,9451 for training data and RMSE 2,785, MAE 2,085, R 2 0,9792 for test data. This model is hereinafter referred to as NN_Nspt(C).
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.
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 antara nilai SPT dan CPT, namun korelasinya cenderung linier. Jaringan saraf tiruan merupakan teknik yang dapat memecahkan masalah yang kompleks dan nonlinier. Pada penelitian ini akan dilakukan prediksi nilai SPT menggunakan jaringan saraf tiruan pada tanah nonkohesif menggunakan algoritma backpropagation. Panelitian ini menggunakan 117 data dari beberapa wilayah di pulau Sumatera. Data masukan yang digunakan berupa nilai tahanan ujung (qc) dan nilai tahanan selimut (fs) dari pengujian CPT dan nilai tekanan overburden efektif (σ'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).
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 antara nilai SPT dan CPT, namun korelasinya cenderung linier. Jaringan saraf tiruan merupakan teknik yang dapat memecahkan masalah yang kompleks dan nonlinier. Pada penelitian ini akan dilakukan prediksi nilai SPT menggunakan jaringan saraf tiruan pada tanah nonkohesif menggunakan algoritma backpropagation. Panelitian ini menggunakan 117 data dari beberapa wilayah di pulau Sumatera. Data masukan yang digunakan berupa nilai tahanan ujung (qc) dan nilai tahanan selimut (fs) dari pengujian CPT dan nilai tekanan overburden efektif (σ'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).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.