Sistem Deteksi Kesalahan Air Gap Pada Synchronous Hydro Generator Menggunakan Similarity Based Model

Akbar, Gilang Rahmat (2024) Sistem Deteksi Kesalahan Air Gap Pada Synchronous Hydro Generator Menggunakan Similarity Based Model. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 02311940000043-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2026. Download (5MB) | Request a copy

Abstract

Dengan pertumbuhan populasi dan perkembangan industri, kebutuhan akan listrik terus meningkat di Indonesia. Hydroelectric energy dianggap sebagai solusi yang andal dengan kelebihan kapasitas beban besar, fluktuasi daya minimal, dan dampak lingkungan rendah. Namun, untuk meningkatkan kinerja generator agar terus dapat beroperasi normal perlu meminimalkan terjadinya kesalahan. Sehingga diperlukan sebuah sistem deteksi kesalahan yang efektif. Kerusakan pada generator, seperti overheating kumparan dan berubahnya jarak pada sisi air gap, dapat mengganggu performa dan memicu ketidakseimbangan air gap. Pada penelitian ini, peneliti membuat sistem deteksi kesalahan pada synchronous hydrogenator yang akan mendeteksi dua jenis kesalahan, yaitu kesalahan insulasi pada stator yang akan mengakibatkan pengurangan luas area penampang pada winding dan juga kesalahan ketidakseimbangan pada air gap. Kesalahan akan disimulasikan dengan pemodelan state space untuk melihat perubahan respon dari sistem. Similarity Based Model disini akan digunakan untuk melakukan klasifikasi dari data arus keluaran dari armature stator yang akan dianalisa pada domain waktu. Kemudian framework Support Vector Machine (SVM) akan digunakan sebagai model yang akan mengklasifikasikan pada tiga kondisi yaitu normal, kesalahan insulasi dan kesalahan air gap eccentricity. Didapatkan hasil bahwa model dapat memberikan nilai akurasi yang tinggi dengan nilai 92.3% dan nilai recall sebesar 94.3%. Kesimpulan yang didapatkan adalah sistem deteksi kesalahan yang dibangun dengan menggunakan Similarity Based Model dapat mendeteksi kesalahan dengan baik.
=================================================================================================================================
With population growth and industrial development, the demand for electricity continues to increase in Indonesia. Hydroelectric energy is considered a reliable solution with large overload capacity, minimal power fluctuation, and low environmental impact. However, to improve generator efficiency, an effective fault detection system is required. Damage to the generator, such as overheating of the coils and changing the distance on the air gap side, can impair performance and trigger air gap imbalance. In this research, need to create a fault detection system for the synchronous hydrogenator that will detect two types of faults, namely insulation faults in the stator winding that will result in a reduction in the cross-sectional area of the winding and also imbalance faults in the air gap. The faults will be simulated with state space modeling to see changes in the response of the system. Similarity Based Model here will be used to classify the output current data from the armature stator which will be analyzed in the time domain and then the signal feature value will be calculated. Furthermore, all signal characteristics will be included in the candidate features of the classifier model. The Support Vector Machine (SVM) framework will be used as a model that will classify three conditions, namely normal, insulation fault and air gap eccentricity fault. It is found that the model can provide a high accuracy value with a value of 92.3% and a recall value of 94.3%. The conclusion obtained is that the error detection system built using Similarity Based Model can detect errors well.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	air gap, fault, insulation, Similarity Based Model, SVM, synchronous generator
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK1007 Electric power systems control T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK531 Current and voltage waveforms T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7870.23 Reliability. Failures
Divisions:	Faculty of Industrial Technology and Systems Engineering (INDSYS) > Physics Engineering > 30201-(S1) Undergraduate Thesis
Depositing User:	Gilang Rahmat Akbar
Date Deposited:	06 Feb 2024 03:30
Last Modified:	06 Feb 2024 03:30
URI:	http://repository.its.ac.id/id/eprint/106159

Actions (login required)

View Item