PREDIKSI WAKTU KERUSAKAN MESIN DISTILASI MENGGUNAKAN MULTIPLE LINEAR REGRESSION, RANDOM FOREST REGRESSION, DAN LONG SHORT-TERM MEMORY

Gamaliel Joseptian Dhio, . (2022) PREDIKSI WAKTU KERUSAKAN MESIN DISTILASI MENGGUNAKAN MULTIPLE LINEAR REGRESSION, RANDOM FOREST REGRESSION, DAN LONG SHORT-TERM MEMORY. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (36kB)
[img] Text
AWAL.pdf
Download (573kB)
[img] Text
BAB 1.pdf
Download (123kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (381kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (216kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (1MB)
[img] Text
BAB 5.pdf
Download (29kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (42kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (82kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (1MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (11MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (377kB)

Abstract

The PPIC Laboratory of UPN Veteran Jakarta has a distillation machine that has not been used regularly for about two years, so maintenance activities for the distillation machine have not been properly scheduled. Previous research that attempted to solve this problem used the calculation of the machine failure time as a basis for scheduling maintenance. The researcher believes that the failure time calculation in previous research can be developed by increasing the amount of data and the number of independent variables that are likely to affect the failure time of the distillation machine, so that more accurate input can be obtained in determining the distillation machine maintenance schedule. To predict the failure time of the machine (the dependent variable) with several independent variables, it can be modelled with a machine learning approach using multiple linear regression, random forest regression, and long-short term memory (LSTM). Prediction of the breakdown time of the distillation machine using multiple linear regression resulted in RMSE and MAPE values of 6.0727 and 11.78% without overfitting or underfitting in the model. Prediction of the breakdown time of the distillation machine using random forest regression resulted in RMSE and MAPE values of 8.9238 and 16.27% with overfitting occurring in the model. Prediction of distillation machine breakdown time with long-short term memory produces RMSE and MAPE values of 30.0352 and 32.40% with underfitting occurring in the model.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 1910312044] [Pembimbing/Penguji 2: Yulizar Widiatama] [Penguji 1: Mohammad Rachman Waluyo] [Penguji Utama: Halim Mahfud]
Uncontrolled Keywords: Distillation Machine, Failure Time, Machine Learning
Subjects: Q Science > QA Mathematics > QA76 Computer software
T Technology > T Technology (General)
Divisions: Fakultas Teknik > Program Studi Teknik Industri (S1)
Depositing User: Gamaliel Joseptian Dhio
Date Deposited: 07 Feb 2023 03:02
Last Modified: 07 Feb 2023 03:02
URI: http://repository.upnvj.ac.id/id/eprint/22074

Actions (login required)

View Item View Item