eprintid: 19618
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/01/96/18
datestamp: 2024-06-04 14:19:21
lastmod: 2024-06-04 14:19:21
status_changed: 2024-06-04 14:15:26
type: article
metadata_visibility: show
creators_name: Bahashwan, A.A.
creators_name: Ibrahim, R.
creators_name: Omar, M.
creators_name: Amosa, T.I.
title: Supervised learning-based multi-site lean blowout prediction for dry low emission gas turbine
ispublished: pub
keywords: Adaptive boosting; Blowouts; Competition; Environmental regulations; Error detection; Forecasting; Gas emissions; Gas plants; Losses; Nanocomposites; Nitrogen oxides; Support vector machines; System stability, Adaptive boosting linear support vector machine; Data driven; Data-driven prediction; Dry low emission gas turbine; Dry low emissions; Emission gas; Lean blow out; Lean blowout prediction; Lean premixed combustion; Linear Support Vector Machines; Multi-site; Multi-site prediction, Gas turbines
note: cited By 2
abstract: Current dry low emission (DLE) gas turbines have extremely low nitrogen oxides (NOx) emissions, allowing them to comply with stringent environmental regulations. The ultra-low temperatures required to achieve such low emissions also increase the risk of a lean blowout (LBO). DLE gas turbines are particularly vulnerable to LBO, which can lead to system instability, higher carbon oxides (CO) emissions, damaged components, substantial financial losses and environmental damages. In this regard, this current study proposes a novel supervised learning-based prediction technique with efficient performance on out-of-distribution data from multiple DLE gas turbine plants (multi-site). The proposed prediction approach exploits the competitive advantages of both adaptive boosting (AdaBoost) and Linear support vector machine (LSVM) to improve the generalization capability as well as prediction accuracy. The proposed algorithm was trained and tested using a real-world DLE gas turbine dataset from six different sites. The result indicates that the proposed model consistently achieving LBO prediction accuracy rates above 99.9 and Mathew's correlation coefficient (MCC) score above 0.9 across all datasets. All lean-premixed gas turbines could benefit from the developed Ada-LSVM, as it is an accurate model with a high generalization performance that can be used across multiple sites. © 2023 Elsevier Ltd
date: 2024
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85181681826&doi=10.1016%2fj.eswa.2023.123035&partnerID=40&md5=285b97fd49a128160150a91a99762ab3
id_number: 10.1016/j.eswa.2023.123035
full_text_status: none
publication: Expert Systems with Applications
volume: 244
refereed: TRUE
citation:   Bahashwan, A.A. and Ibrahim, R. and Omar, M. and Amosa, T.I.  (2024) Supervised learning-based multi-site lean blowout prediction for dry low emission gas turbine.  Expert Systems with Applications, 244.