AI-Based Prediction Platform of Replacement Cycle for Inspection Equipment 


Vol. 49,  No. 4, pp. 636-644, Apr.  2024
10.7840/kics.2024.49.4.636


PDF
  Abstract

Recently, with the rise of smart factories, the aging of process equipment and maintenance costs are increasing. As a result, there is an increasing need for technology to predict the lifespan of production equipment. A brief shutdown of an automated production line can result in significant financial losses. Therefore, equipment condition monitoring and real-time failure prediction technology are indispensable. Productivity can be increased with PdM (Predictive Maintenance), which predicts malfunction cycles, rather than PM (Preventive Maintenance), which repairs equipment regardless of failure. In this paper, we developed AI (Artificial Intelligence)-based PdM technology to be applied to SCU (Shift-by-wire Control Unit) inspection equipment. The platform developed performs real-time equipment condition prediction. In order to predict equipment failure, a data set of voltage and frequency for SCU inspection equipment was created through simulation. Then, this data was applied to three models: RNN (Recurrent Neural Network), LSTM (Long Short-Term Memory), and GRU (Gated Recurrent Unit), and their performance was compared. Through the simulation results, the GRU model achieved optimal prediction speed and accuracy, with an R2-score of 0.992. Based on these results, a PdM platform using GRU was developed. The developed platform has a function that predicts daily cycle data based on real-time data input.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Related Articles
  Cite this article

[IEEE Style]

S. Kang, S. Oh, J. Kim, "AI-Based Prediction Platform of Replacement Cycle for Inspection Equipment," The Journal of Korean Institute of Communications and Information Sciences, vol. 49, no. 4, pp. 636-644, 2024. DOI: 10.7840/kics.2024.49.4.636.

[ACM Style]

Seon-Woo Kang, Sung-Hyun Oh, and Jeong-Gon Kim. 2024. AI-Based Prediction Platform of Replacement Cycle for Inspection Equipment. The Journal of Korean Institute of Communications and Information Sciences, 49, 4, (2024), 636-644. DOI: 10.7840/kics.2024.49.4.636.

[KICS Style]

Seon-Woo Kang, Sung-Hyun Oh, Jeong-Gon Kim, "AI-Based Prediction Platform of Replacement Cycle for Inspection Equipment," The Journal of Korean Institute of Communications and Information Sciences, vol. 49, no. 4, pp. 636-644, 4. 2024. (https://doi.org/10.7840/kics.2024.49.4.636)
Vol. 49, No. 4 Index

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880