Optimasi Random Forest Untuk Predictive Maintenance Dengan Random Search Dan Multiclass One-vs-Rest

Manalu, Daniel (2025) Optimasi Random Forest Untuk Predictive Maintenance Dengan Random Search Dan Multiclass One-vs-Rest. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 21081010189-cover.pdf Download (3MB)
	Text (Bab 1) 21081010189-bab1.pdf Download (229kB)
	Text (Bab 2) 21081010189-bab2.pdf Restricted to Repository staff only until 18 June 2027. Download (425kB)
	Text (Bab 3) 21081010189-bab3.pdf Restricted to Repository staff only until 18 June 2027. Download (1MB)
	Text (Bab 4) 21081010189-bab4.pdf Restricted to Repository staff only until 18 June 2027. Download (677kB)
	Text (Bab 5) 21081010189-bab5.pdf Download (221kB)
	Text (Daftar Pustaka) 21081010189-daftarpustaka.pdf Download (165kB)
	Text (Lampiran) 21081010189-lampiran.pdf Restricted to Repository staff only Download (346kB)

Abstract

This study aims to develop an optimized Random Forest model for predictive maintenance by integrating Random Search for hyperparameter tuning and a multiclass One-vs-Rest (OvR) classification approach. The research focuses on predicting six types of machine failures (Tool Wear Failure, Heat Dissipation Failure, Power Failure, Overstrain Failure, Random Failure, and No Failure) using synthetic vehicle sensor data from the Predictive Maintenance Dataset (AI4I 2020). The methodology includes data preprocessing (normalization, feature engineering), Random Search for optimizing hyperparameters (e.g., n_estimators, max_depth), and OvR to handle class imbalance. Evaluation metrics such as accuracy, precision, recall, F1-score, ROC-AUC, and Matthews Correlation Coefficient (MCC) were used. Results show that the optimized model achieved 99.1% accuracy with MCC 0.86, outperforming the baseline. However, challenges remain in detecting minority classes (e.g., Random Failure). This research contributes to industrial applications by enhancing maintenance efficiency through data-driven failure prediction.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Puspaningrum, Eva Yulia	NIDN0005078908	evapuspaningrum.if@upnjatim.ac.id
Thesis advisor	Putra, Chrystia Aji	NIDN0008108605	ajiputra@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)
T Technology > T Technology (General) > T385 Computer Graphics
T Technology > T Technology (General) > T55.4-60.8 Industrial engineering. Management engineering
T Technology > TE Highway engineering. Roads and pavements
T Technology > TF Railroad engineering and operation

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Daniel Manalu

Date Deposited:

19 Jun 2025 02:13

Last Modified:

19 Jun 2025 02:13

URI:

https://repository.upnjatim.ac.id/id/eprint/38532