Claim Missing Document
Check
Articles

Found 5 Documents
Search

Flutter Framework Implementation for Over Current Relay and Ground Fault Relay Setting Applications in 20 kV Distribution Systems Sartika, Nike; Maulidan, Muhammad Akmal; Mulyana, Edi
Jurnal Pendidikan Multimedia (Edsence) Volume 6 No 2 (December 2024)
Publisher : Universitas Pendidikan Indonesia (UPI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17509/edsence.v6i2.76176

Abstract

In the distribution system, there are several faults such as blackouts due to errors in the coordination of the protection relay. To minimize excessive damage to the electrical system, components such as over current relays (OCR) are needed to overcome inter-phase faults and ground fault relays (GFR) to overcome phase-to-ground faults. The setting process that has been carried out so far is still ineffective, so a system is needed to simplify the setting process. Flutter is a development framework from Google that can release applications in the form of Android or iOS. This study aims to simplify the OCR and GFR setting process using a mobile application. Application development uses the waterfall method. The test results consisting of blackbox alpha, beta and manual calculations show that this application is running according to the expected functionality. In addition, the results of the settings that have been done are the OCR setting current of 400 A in zone 1 and 300 A in zone 2 with a Time Multiplier Setting (TMS) value of 0.2 in zone 1 and 0.05 in zone 2. While the GFR setting current is 80 A in zone 1 and 60 A in zone 2 with a TMS value of 0.175 in zone 1 and 0.05 in zone 2. From these setting values, the OCR time difference (Δt) value is then obtained around 0.6 seconds and 0.8 seconds for GFR. This shows that the OCR and GFR are in good condition.
DIAGNOSIS KEGAGALAN TRANSFORMATOR DAYA MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBORS DAN ARTIFICIAL NEURAL NETWORK BERBASIS DISSOLVED GAS ANALYSIS Hidayat, Rafi Maulana; Media, Galih; Sartika, Nike; Kamelia, Lia
Transmisi: Jurnal Ilmiah Teknik Elektro Vol 27, No 3 Juli (2025): TRANSMISI: Jurnal Ilmiah Teknik Elektro
Publisher : Departemen Teknik Elektro, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/transmisi.27.3.140-148

Abstract

Dissolved Gas Analysis (DGA) merupakan metode untuk mengidentifikasi jenis kegagalan pada transformator dengan menilai jumlah gas yang terkandung pada minyak isolasi transformator. DGA memiliki beberapa metode dalam menganalisis dan mengidentifikasi jenis kegagalan berdasarkan jenis gas yang terlarut. Tetapi, dalam jumlah data yang besar metode ini menjadi sulit dan memerlukan keahlian dalam mendeteksi kegagalan secara grafis. Penelitian ini bertujuan untuk meningkatkan akurasi diagnostik kegagalan transformator dengan mengimplementasikan serta membandingkan algoritma K-Nearest Neighbors (KNN) dengan algoritma Artificial Neural Network (ANN) pada setiap metode konvensional DGA yaitu Roger Ratio, Duval Triangle, Four Gases dan Duval pentagon dalam mengklasifikasikan jenis kegagalan. Sebanyak 822 sampel dataset digunakan untuk melatih dan memvalidasi model yang digunakan. Berdasarkan hasil penelitian diagnosis kegagalan transformator menunjukan bahwa metode grafis memberikan hasil yang paling efektif dalam mendiagnosis jenis kegagalan transformator dibandingkan dengan metode rasio. Selain itu penggunaan algoritma KNN memberikan hasil yang lebih baik dibandingkan dengan algoritma ANN dalam meningkatkan akurasi diagnostik dengan memperoleh akurasi tertinggi sebesar 98% pada duval triangle.
Design and Implementation a Web-Based Semester Learning Plan Management Information System Sartika, Nike; Sukmana, Yuda; Kholik, Iik Abdul; Ramelan, Agus
Journal of Electrical, Electronic, Information, and Communication Technology Vol 5, No 1 (2023): JOURNAL OF ELECTRICAL, ELECTRONIC, INFORMATION, AND COMMUNICATION TECHNOLOGY
Publisher : Universitas Sebelas Maret (UNS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20961/jeeict.5.1.72003

Abstract

This research designs and implements an information system to manage web-based Semester Learning Plan using cloud computing technology, software, computers, and repositories as well as a serverless architecture. So far, the preparation of Semester Learning Plan in Department of Electrical Engineering UIN Sunan Gunung Djati Bandung is still done manually using a template in Microsoft Excel format. This method is considered ineffective because filling in takes a long time and the output is sometimes not uniform, both between lecturers and between courses. Based on this background, the author proposed the idea of creating a web-based Semester Learning Plan management information system. The method used to develop this system is the waterfall method which consists of five stages, namely requirements analysis, system and software design, implementation, testing, operation and maintenance. This information system using cloud computing technology and serverless architecture. The result of this research is a web-based Semester Learning Plan management information system. Through this system, lecturers no longer type manually into doc or xls format, but lecturers can directly input into the system or the web. The output is that the Semester Learning Plan can be downloaded and is in accordance with the applicable format and is in pdf format. The existence of this system can increase the effectiveness of lecturers in managing Semester Learning Plan.
Grammatical Error Correction (GEC) of Indonesian Text Based on Neural Machine Translation (NMT) Sartika, Nike; Sukmana, Yuda
Journal of Electrical, Electronic, Information, and Communication Technology Vol 5, No 2 (2023): JOURNAL OF ELECTRICAL, ELECTRONIC, INFORMATION, AND COMMUNICATION TECHNOLOGY
Publisher : Universitas Sebelas Maret (UNS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20961/jeeict.5.2.78837

Abstract

Writing errors in Indonesian are often found in various writings made in educational, government and mass media environments. The most dominant error is in spelling. This research proposes a Grammatical Error Correction (GEC) for Indonesian using the Neural Machine Translation (NMT) method, namely seq2seq, which is popularly used for English and has achieved the best performance approaching human capabilities. The model developed is made into a web-based service that is easy for users to access. The datasets used in this experiment are artificial datasets sourced from several studies regarding error analysis in Indonesian. The research results show that with the help of currently available open-source tools such as OpenNMT-py, it is possible to simplify the training process of NMT-based GEC models. Unfortunately, the small number of datasets leads to poor predictions for random sentences.
Analysis of Ciheras Beach Wind Potential for Minimal Pollutant Electrical Energy Generation Nugraha, Adi; Ramelan, Agus; Sartika, Nike
Journal of Electrical, Electronic, Information, and Communication Technology Vol 5, No 2 (2023): JOURNAL OF ELECTRICAL, ELECTRONIC, INFORMATION, AND COMMUNICATION TECHNOLOGY
Publisher : Universitas Sebelas Maret (UNS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20961/jeeict.5.2.78883

Abstract

Pollutant is a serious problem today as the use of non-renewable energy sources is still a favorite, especially those sourced from coal and petroleum fuels. To anticipate dependence on coal-fired power plants, many studies have been conducted related to environmentally friendly power plants. One of the environmentally friendly power plants is wind power plants. Based on the criteria of wind turbines such as TSD-500, a wind speed of at least 3 m/s is required to start production. The purpose of this study is to find out how much potential clean energy is generated through wind energy generation on the coast of Ciheras. The research method in data collection used is qualitative descriptive. The results of the analysis found that the energy obtained from the process of converting wind energy into electrical energy can illuminate 9 houses, with each house consuming 70 Watts of power for 5 hours.