CD Skripsi

Prakiraan Nilai N-Spt Berdasarkan Data Uji Lapangan Sondir Dan Laboratorium Menggunakan Jaringan Saraf Tiruan

---

In general, soils have properties that vary from place to place due to the complex formations of the soil. Soil investigation is the main key in starting a construction. The Standard Penetration Test (SPT) and Sondir are the field tests most often used to estimate soil parameters in foundation analysis and design. The SPT value shows a correlation with the Sondir value and other soil parameters. Artificial neural networks are often used to estimate a complex and nonlinear value. In this research, N-SPT value prediction based on sondir test data and soil physical properties using artificial neural network capabilities using the Backpropagation algorithm. This research was divided into 2 stages, for cohesive and non-cohesive soil types. The cohesive soil type uses 242 training data and 42 test data with input data in the form of tip resistance (qc), blanket resistance (fs), effective overburden pressure , LL, PL, and the percentage of sand, silt and clay. For non-cohesive soil types, 104 training data and 18 test data were used with input data in the form of tip resistance (qc), blanket resistance (fs), effective overburden pressure , and percentage of sand and fine grains. 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 cohesive soil types, RMSE was 3.278, MAE 1.783 and R2 0.9451 for training data and RMSE 2.012, MAE 1.328, R2 0.9792 for test data. For non-cohesive soil types, RMSE was 3.358, MAE 2.423, and R2 0.9228 for training data and RMSE 1.678, MAE 1.189, and R2 0.9909 for test data.
Keywords: SPT, Sondir, Cohesive, Non-cohesive, Artificial Neural Networks, Backpropagation

---

Ketersediaan

Informasi Detail

Judul Seri

-

No. Panggil

07 01. 120 (0115)

Penerbit

Pekanbaru : Universitas Riau – Fakultas Teknik – Teknik Sipil., 2020

Deskripsi Fisik

ix, 79 hlm.; ill.: 29 cm

Bahasa

Indonesia

ISBN/ISSN

-

Klasifikasi

07 01. 120 (0115)

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

TEKNIK SIPIL

Info Detail Spesifik

-

Pernyataan Tanggungjawab

Daus

Versi lain/terkait

Lampiran Berkas

Komentar

---

Anda harus masuk sebelum memberikan komentar