cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kota surabaya,
Jawa timur
INDONESIA
IPTEK The Journal for Technology and Science
Published by Institut Teknologi Sepuluh Nopember Surabaya
ISSN : 08534098     EISSN : 20882033     DOI : -
Core Subject : Science,
Computer Science & IT
IPTEK The Journal for Technology and Science (eISSN: 2088-2033; Print ISSN:0853-4098), is an academic journal on the issued related to natural science and technology. The journal initially published four issues every year, i.e. February, May, August, and November. From 2014, IPTEK the Journal for Technology and Science publish three times a year, they are in April, August and December in online version.
Arjuna Subject : -
Articles 1 Documents
 1 
Search results for , issue "Vol 36, No 1 (2025)" : 1 Documents clear
Predicting Failure using Machine Learning and Statistical Based Method: a Production Machine Case Study Latiffianti, Effi; Wiratno, Stefanus Eko; Christianta, Samuel Aditya
IPTEK The Journal for Technology and Science Vol 36, No 1 (2025)
Publisher : IPTEK, DRPM, Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j20882033.v36i1.22501

Abstract

This research investigates the applicability of failure detection models based on machine learning and statistical approaches to reduce unplanned downtime in a food production company. Sensor data is utilized to for identifying early failure symptoms. To capture temporal and sequential dependencies in time-series data, we employ one of potential network based method so called the Long Short Term Memory (LSTM) Autoencoder. Furthermore, we contrast the performance of the result with the traditional statistical method, the multivariate Exponentially Weighted Moving Average (EWMA). While both models successfully detected all failures, LSTM-AE demonstrated superior performance by reducing false alarms and providing true alarms with a longer time-to-failure. The findings highlight the potential of leveraging limited data for failure prediction, demonstrating the effectiveness of both models in detecting anomalies while emphasizing their role in enhancing productivity through early failure detection.

Page 1 of 1 | Total Record : 1

 1 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol 36, No 1 (2025) Vol 35, No 3 (2024) Vol 35, No 2 (2024) Vol 35, No 1 (2024) Vol 34, No 3 (2023) Vol 34, No 2 (2023) Vol 34, No 1 (2023) Vol 33, No 3 (2022) Vol 33, No 2 (2022) Vol 33, No 1 (2022) Vol 32, No 3 (2021) Vol 32, No 2 (2021) Vol 32, No 1 (2021) Vol 31, No 3 (2020): In-Press Vol 31, No 3 (2020) Vol 31, No 2 (2020) Vol 31, No 1 (2020) Vol 30, No 3 (2019) Vol 30, No 2 (2019) Vol 30, No 1 (2019) Vol 29, No 3 (2018) Vol 29, No 2 (2018) Vol 29, No 1 (2018) Vol 28, No 3 (2017) Vol 28, No 2 (2017) Vol 28, No 1 (2017) Vol 27, No 3 (2016) Vol 27, No 2 (2016) Vol 27, No 1 (2016) Vol 26, No 2 (2015) Vol 26, No 1 (2015) Vol 25, No 3 (2014) Vol 25, No 2 (2014) Vol 25, No 1 (2014) Vol 24, No 3 (2013) Vol 24, No 2 (2013) Vol 24, No 1 (2013) Vol 23, No 4 (2012) Vol 23, No 3 (2012) Vol 23, No 2 (2012) Vol 23, No 1 (2012) Vol 22, No 4 (2011) Vol 22, No 3 (2011) Vol 22, No 2 (2011) Vol 22, No 1 (2011) Vol 21, No 4 (2010) Vol 21, No 3 (2010) Vol 21, No 2 (2010) Vol 21, No 1 (2010) Vol 20, No 4 (2009) Vol 20, No 3 (2009) Vol 20, No 2 (2009) Vol 20, No 1 (2009) Vol 19, No 4 (2008) Vol 19, No 3 (2008) Vol 19, No 2 (2008) Vol 19, No 1 (2008) Vol 18, No 4 (2007) Vol 18, No 3 (2007) Vol 18, No 2 (2007) Vol 18, No 1 (2007) More Issue