RANCANG BANGUN MODEL DEEP LEARNING UNTUK MEMPREDIKSI KETIDAKSEIMBANGAN PADA ROTOR MOTOR INDUKSI 3 PHASA BERBASIS SINYAL AKUSTIK

Abdulloh, Umar (2026) RANCANG BANGUN MODEL DEEP LEARNING UNTUK MEMPREDIKSI KETIDAKSEIMBANGAN PADA ROTOR MOTOR INDUKSI 3 PHASA BERBASIS SINYAL AKUSTIK. Bachelor thesis, Institut Teknologi Kalimantan.

	Text 04211084_enclosure.pdf Restricted to Repository staff only until 10 April 2028. Download (4MB) | Request a copy
	Text 04211084_statment_of_authenticty.pdf Restricted to Repository staff only until 10 April 2028. Download (52kB) | Request a copy
	Text 04211084_publishing_agreement.pdf Restricted to Repository staff only until 10 April 2028. Download (67kB) | Request a copy
	Text 04211084_Form. TA-20.pdf Restricted to Repository staff only until 10 April 2028. Download (103kB) | Request a copy
	Text 04211084_paper.pdf Restricted to Repository staff only until 10 April 2028. Download (1MB) | Request a copy
	Text 04211084_bibliography.pdf Restricted to Repository staff only until 10 April 2028. Download (189kB) | Request a copy
	Text 04211084_conclusions.pdf Restricted to Repository staff only until 10 April 2028. Download (258kB) | Request a copy
	Text 04211084_chapter_4.pdf Restricted to Repository staff only until 10 April 2028. Download (990kB) | Request a copy
	Text 04211084_chapter_3.pdf Restricted to Repository staff only until 10 April 2028. Download (4MB) | Request a copy
	Text 04211084_chapter_2.pdf Restricted to Repository staff only until 10 April 2028. Download (728kB) | Request a copy
	Text 04211084_chapter 1.pdf Restricted to Repository staff only until 10 April 2028. Download (287kB) | Request a copy
	Text 04211084_notation.pdf Restricted to Repository staff only until 10 April 2028. Download (167kB) | Request a copy
	Text 04211084_tables.pdf Restricted to Repository staff only until 10 April 2028. Download (120kB) | Request a copy
	Text 04211084_illustration.pdf Restricted to Repository staff only until 10 April 2028. Download (129kB) | Request a copy
	Text 04211084_Table_of_content.pdf Restricted to Repository staff only until 10 April 2028. Download (225kB) | Request a copy
	Text 04211084_abstract_en.pdf Restricted to Repository staff only until 10 April 2028. Download (223kB) | Request a copy
	Text 04211084_abstract_id.pdf Restricted to Repository staff only until 10 April 2028. Download (121kB) | Request a copy
	Text 04211084_Preface.pdf Restricted to Repository staff only until 10 April 2028. Download (162kB) | Request a copy
	Text 04211084_Cover.pdf Restricted to Repository staff only until 10 April 2028. Download (437kB) | Request a copy
	Text 04211084_Presentation.pdf Restricted to Repository staff only until 10 April 2028. Download (640kB) | Request a copy
	Text 04211084_approval_sheet.pdf Restricted to Repository staff only until 10 April 2028. Download (46kB) | Request a copy

Abstract

Three-phase induction motors are widely used in industry due to their reliability and efficiency. However, rotor imbalance can degrade motor performance and accelerate mechanical damage if not detected early. This study proposes a deep learning-based approach to predict rotor imbalance in three-phase induction motors using acoustic signals. Motor sound data were collected under various imbalance conditions, ranging from normal operation to 30 grams. The acoustic signals were processed using Mel-Frequency Cepstral Coefficients (MFCC) as input features. Long Short-Term Memory (LSTM) and Artificial Neural Network (ANN) models were employed to perform regression-based prediction of rotor imbalance. Model performance was evaluated using Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and the coefficient of determination (R²). The results indicate that the LSTM model outperforms ANN in handling time-series data, achieving an RMSE of 6.62 grams and an R² value of 0.64. These results show that acoustic-based deep learning has potential for non-invasive condition monitoring of induction motors. Keywords : Induction Motor, Imbalance Rotor, MFCC, LSTM, ANN, Deep Learning

Item Type:	Thesis (Bachelor)
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions:	Jurusan Teknologi Industri dan Proses > Teknik Elektro
Depositing User:	Umar Abdulloh
Date Deposited:	13 Jan 2026 07:46
Last Modified:	13 Jan 2026 07:46
URI:	http://repository.itk.ac.id/id/eprint/25326

Actions (login required)

View Item