Article Per Year (5 Year)
p-Index From 2020 - 2025
0.659
P-Index
This Author published in this journals
All Journal JOIV : International Journal on Informatics Visualization JTAM (Jurnal Teori dan Aplikasi Matematika) Jurnal Nasional Pendidikan Teknik Informatika (JANAPATI)
Santosa, Petrus Priyo
Unknown Affiliation
Computer Science & IT Education Engineering Mathematics

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Learning Algorithms of SVR, DTR, RFR, and XGBoost (Case Study: Predictive Maintenance of Fuel Consumption) Parhusip, Hanna Arini; Lea, Lea; Trihandaru, Suryasatriya; Nugroho, Didit Budi; Santosa, Petrus Priyo; Hariadi, Adrianus Herry
Jurnal Nasional Pendidikan Teknik Informatika: JANAPATI Vol. 14 No. 2 (2025)
Publisher : Prodi Pendidikan Teknik Informatika Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/janapati.v14i2.85657

Abstract

The most complex aspect of predictive maintenance (PdM) for heavy vehicles is accurately forecasting fuel consumption as it is both critical and challenging to achieve optimal efficiency while minimizing expenses. Overfitting and failure to capture the existing data's linear relationships seem to remain the most persistent issues with traditional methods. In order to achieve this, the following techniques were analyzed to choose the best fuel consumption forecaster: Support Vector Regression (SVR), Decision Tree Regression (DTR), Random Forest Regression (RFT), and XGBoost. The models were implemented and their performance measured using Mean Squared Error (MSE). The analysis revealed that SVR surpassed the others with a linear kernel (C=10) achieving the lowest MSE rates of 0.26, while DTR, RFR, and XGBoost earned significantly higher 3.375, 2.857, and 3.857 (MSEs). The other models lagged behind SVR because SVR was more effective in capturing linear relations and managing overfitting, a dominating issue with decision-tree based models. This points out another important aspect of predictive maintenance (PdM) : the appropriate machine learning technique plays a very important role in accurately predicting fuel consumption of heavy trucks, which improves precision and fuel efficiency.
Selection Dominant Features Using Principal Component Analysis for Predictive Maintenance of Heave Engines Trihandaru, Suryasatriya; Parhusip, Hanna Arini; Heriadi, Adrianus Herry; Santosa, Petrus Priyo; Sardjono, Yohanes; Lea, Lea
JTAM (Jurnal Teori dan Aplikasi Matematika) Vol 8, No 4 (2024): October
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/jtam.v8i4.22854

Abstract

This article aims to identify the dominant features that have a significant impact on the health of a heavy machine that relates to the digital infrastructure of a company. The importance of this research is that the authors define predictive maintenance based on Principal Component Analysis (PCA), which is the novelty of this article. The novel contribution of this research lies in the application of Principal Component Analysis (PCA) for predictive maintenance of heavy machinery, which has not been integrated into the Scheduled Oil Sampling (SOS) procedures. The recorded data are called Scheduled Oil Sampling (SOS) and historical data from an equipment called CoreDataQ, which works for recording many features from heavy machine activities. The data contain two sets data. The method is Principal Component Analysis (PCA). This method leads to obtain a maximum of 20 significant features on data based on SOS. The results have been confirmed and agreed upon by the manager who owned CoreDataQ to consider the selected dominant features for further related maintenance. 
Data Exploration Using Tableau and Principal Component Analysis Parhusip, Hanna Arini; Trihandaru, Suryasatriya; Heriadi, Adrianus Herry; Santosa, Petrus Priyo; Puspasari, Magdalena Dwi
JOIV : International Journal on Informatics Visualization Vol 6, No 4 (2022)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30630/joiv.6.4.952

Abstract

This study aims to determine the dominant chemical elements that may improve the monitoring of the productivity and efficiency of heavy engines in 2015-2021 in the company. The method used is usually Scheduled Oil Sampling. This article proposes a new approach. The research problems are analyzing the recorded chemical elements that are produced by heavy engines and visualizing them through the Tableau program. The basic design of the study is learning the given data after visualization and using the Principal Component Analysis. This method is to obtain chemical elements that affect engine wear during each engine's use in the 2015-2021 period. Because there are three categories in each element in the oil sample, namely wear metals, contaminants, and oil additives, a technique is needed to obtain these elements using Principal Component Analysis. Therefore, Oil Sampling Analysis through data exploration using Tableau resulted in a new approach to data analysis of elements recorded by heavy vehicles. The main findings as a result of the analysis are given by the visualization of Tableau, in which there are five machines analyzed to obtain the main components that cause engine wear. From the visualization results, it is shown that there is one engine coded MSD 012 that experienced wear and tear in 2018 and 2019. This shows where two main components, Ca and Mg, dominate engine wear. These results have been confirmed with the related companies. The company then carried out further studies on the machine to get special treatment because of these results.
Co-Authors Didit Budi Nugroho Hanna Arini Parhusip Hariadi, Adrianus Herry Heriadi, Adrianus Herry Lea, Lea Puspasari, Magdalena Dwi Suryasatriya Trihandaru Yohanes Sardjono, Yohanes