IPB University Logo

SCIENTIFIC REPOSITORY

IPB University Scientific Repository collects, disseminates, and provides persistent and reliable access to the research and scholarship of faculty, staff, and students at IPB University

AI Repository
 
Building and Categories


      View Item 
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - School of Data Science, Mathematic and Informatics
      • UF - Computer Science
      • View Item
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - School of Data Science, Mathematic and Informatics
      • UF - Computer Science
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Perbandingan Kinerja Model Regresi untuk Prediksi Waktu Kerusakan Ulang Alat Berat PT XYZ

      Thumbnail
      View/Open
      Cover (371.8Kb)
      Fulltext (1.192Mb)
      Lampiran (848.4Kb)
      Date
      2026
      Jenis/Type
      Skripsi
      Subtype
      Undergraduate Theses
      Author
      RIZKI, MUHAMMAD HAFIDZ
      Mushthofa
      Metadata
      Show full item record
      Abstract
      Kerusakan alat berat yang tidak direncanakan dapat mengganggu operasional dan meningkatkan kebutuhan pemeliharaan. Penelitian ini membandingkan Linear Regression, Generalized Linear Model, dan Random Forest untuk memprediksi waktu kerusakan ulang alat berat PT XYZ. Data terdiri atas 8.768 catatan pemeliharaan tahun 2024-2025. Catatan pada alat yang sama dengan selang waktu tidak lebih dari 24 jam digabungkan menjadi satu event, menghasilkan 7.171 event. Target berupa selang waktu dari akhir event saat ini hingga awal event berikutnya pada alat yang sama. Sebanyak 7.060 event bertarget valid dibagi menjadi 70% data latih dan 30% data uji. Fitur kategorik ditransformasikan dengan one-hot encoding untuk Linear Regression dan Generalized Linear Model, serta out-of-fold median target encoding untuk Random Forest. Model akhir menambahkan event_duration_hours, sedangkan tuning diterapkan pada Generalized Linear Model dan Random Forest. Random Forest memberikan hasil terbaik dengan MAE 1,17 hari, RMSE 1,96 hari, R² 0,84, dan MAPE 30,08%.
       
      Unplanned heavy equipment failures can disrupt operations and increase maintenance requirements. This study compared Linear Regression, Generalized Linear Model, and Random Forest for predicting the time to recurrent failure of heavy equipment at PT XYZ. The data comprised 8,768 maintenance records from 2024–2025. Records from the same equipment separated by no more than 24 hours were merged into one event, yielding 7,171 events. The target was the interval from the end of the current event to the start of the next event on the same equipment. A total of 7,060 events with valid targets were divided into 70% training data and 30% test data. Categorical features were transformed using one-hot encoding for Linear Regression and Generalized Linear Model, and out-of-fold median target encoding for Random Forest. The final models included event_duration_hours, while tuning was applied to Generalized Linear Model and Random Forest. Random Forest achieved the best performance, with an MAE of 1.17 days, RMSE of 1.96 days, R² of 0.84, and MAPE of 30.08%.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/176859
      Collections
      • UF - Computer Science [164]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository