Article Per Year (5 Year)
p-Index From 2020 - 2025
0
P-Index
This Author published in this journals
All Journal IPTEK Journal of Proceedings Series
Dewanto, Nurcahyo Herwin
Technical Department, West Maintenance Service Unit, Pembangkitan Jawa Bali Company
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Prediction of Gas Turbine Blade Lifetime Using Artificial Neural Network Dewanto, Nurcahyo Herwin; Suwarno, Suwarno
IPTEK Journal of Proceedings Series No 1 (2019): 4th International Seminar on Science and Technology 2018 (ISST 2018)
Publisher : Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j23546026.y2019i1.5122

Abstract

Turbine blade is a critical component in a gas turbine that converts combustion energy into electricity. Due to its high temperature and pressure operation, maintenance of this component is crucial. The manufacturer normally has guidance of maintenance, i.e. different type of maintenance scheme is performed so-called A-B-A-C scheme which is performed every 6,000 equivalent operation hour (EOH). In A and B type inspection, visual inspection is done to turbine blade, and monitoring in next inspection is done if damages found. Turbine blade is replaced at C-Inspection (24,000 EOH) due to availability of power plant. The first stage turbine blade is made of nickel-based superalloy, and damages like missing material, crack, hole, coating spallation found during inspection. Accurate life prediction is need to ensure safety of gas turbine operations. In this paper lifetime prediction using ANN (Artificial Neural Network) used to predict the lifetime of gas turbine blade 145 MW Muara Tawar Power Plant. For input variable we use operation data and for target we use the amount of defect. After several times of training and testing show that network model with 8 inputs, 20 neurons, and 7 targets with MSE (Mean Square Error) 5.42E-02 and R (Regression) 9.85E-01 is able to predict defect as consideration that lifetime of turbine blade will reach one operation cycle
Co-Authors Suwarno, Suwarno