CD Skripsi

Identifikasi Dan Klasifikasi Gangguan Pada Sistem Tenaga Dengan Wavelet Transform Dan Radial Basis Function Neural Network (Rbfnn)

---

ABSTRACT
Faults in electrical transmission lines, especially short-circuit faults, can cause
power system instability and damage electrical equipment, making accurate
identification and classification methods essential. This study aims to develop a
fault detection method using Wavelet Transform (WT) for feature extraction and
Radial Basis Function Neural Network (RBFNN) for classification. The modeled
power system is the IEEE 30 Bus Test System, and fault simulations were conducted
using PSCAD. The generated fault signals were extracted using Discrete Wavelet
Transform (DWT) with variations of Mother Wavelets (Daubechies-4, Haar,
Symlet-4, and Coiflet-4). The extracted data were then used as input for training
and testing the RBFNN model, with evaluation based on Mean Squared Error
(MSE). The results show that Daubechies-4 (dB4) at decomposition level 3 provides
the best accuracy, with an MSE value below 10⁻⁵, indicating a very low error rate
in fault classification. Therefore, this method is recommended for detecting faults
in power systems. For future research, it is suggested to integrate this approach
with deep learning or machine learning techniques to improve classification
accuracy and efficiency.
Keywords: Transmission Lines, Wavelet Transform, Radial Basis Function Neural
Network, PSCAD.

---

Ketersediaan

Informasi Detail

Judul Seri

-

No. Panggil

2107112357

Penerbit

Pekanbaru : Universitas Riau – F.TEKNIK – Elektro., 2025

Deskripsi Fisik

-

Bahasa

Indonesia

ISBN/ISSN

-

Klasifikasi

2107112357

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

TEKNIK ELEKTRO

Info Detail Spesifik

-

Pernyataan Tanggungjawab

daus

Versi lain/terkait

Lampiran Berkas

Komentar

---

Anda harus masuk sebelum memberikan komentar