Detail A Review on Machine Learning Techniques for Predictive Maintenance in Industry 4.0 Bibliografi Author: Sisode, Megha ; Devare, Manoj Topik: Machine learning; predictive maintenance; manufacturing equipment; Industry 4.0; failure prediction Bahasa: (EN )    Edisi: ICAMIDA 2022, ACSR 105     Penerbit: Atlantis Press     Tahun Terbit: 2023     Jenis: Article - diterbitkan di jurnal ilmiah internasional Fulltext: Predictive Maintenance in Industry 4.0.pdf (552.97KB; 0 download) Abstract Predictive maintenance is the process of continuously monitoring a system to prevent it from breaking down. Along with the traditional equipment maintenance which uses a periodic schedule instead of reacting to equipment failures, predictive maintenance predicts failure of an equipment. Adopting a suitable and reliable predictive maintenance strategy for equipment like automobile part manufacturing machines has remained a dif?culty for industry. To minimize the unplanned downtime of a machine caused by its failure in highly automated production line is very challenging piece of predictive maintenance. Recently the Industry 4.0 concept is becoming more widely adopted in manufacturing around the world. The survey emphases on different methods available for predictive maintenance and the various data used in the researches. Machine learning promises the better solutions over the traditional maintenance problem. In this research, intelligent approach is presented which is to be used to design proposed PdM planning model. To predict the failure state with respect to down time a weight optimized GRU model is proposed. And Whale Optimization with Seagull Algorithm has to be used to optimize the weight in GRU based learning. Thus the results are wellsuited for PdM planning and capable of accurately predicting future components for Mechanical part making machine. Opini Anda Klik untuk menuliskan opini Anda tentang koleksi ini! Lihat Sejarah Pengadaan  Konversi Metadata   Kembali

Copyright © 2006, 2007 Unika Atma Jaya, all rights reserved