Scheduling Maintenance of Cooling System based on Risk Priority Number (RPN) using Adaptive Neural Network
Bustani1, Rusdiansyah2, Mohammad Zainuddin3, Supriadi4
1Bustani, Department of Electrical Engineering, State Polytechnic of Samarinda, East Kalimantan, Indonesia.
2Rusdiansyah, Department of Electrical Engineering, State Polytechnic of Samarinda, East Kalimantan, Indonesia.
3Mohammad Zainuddin, Department of Information Technology, State Polytechnic of Samarinda, East Kalimantan, Indonesia.
4Supriadi, Department of Information Technology, State Polytechnic of Samarinda, East Kalimantan, Indonesia.
Manuscript received on 13 September 2019 | Revised Manuscript received on 22 September 2019 | Manuscript Published on 11 October 2019 | PP: 807-812 | Volume-8 Issue-11S September 2019 | Retrieval Number: K114309811S19/2019©BEIESP | DOI: 10.35940/ijitee.K1143.09811S19
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Power outages caused by factors outside the established policy will have an impact on the decline in electricity supply services and other cost related impacts. The reliability of the power plant feeder, in this case, is very important to monitor and maintain. The performance of power plant feeder can be reviewed based on the variable duration of power outage and power which fails to distribute. In this study, 1st order FTS (Fuzzy Time Series) is used to predict the feeder’s performance through the predictive activity of both those variables in the actual year and the following year. The prediction results state that in 2017 there was a 20.54% decrease in performance.
Keywords: Feeder, power outages, undistributed power, 1st order FTS.
Scope of the Article: Network Architectures