可靠性工程
燃气轮机
工作(物理)
计算机科学
任务(项目管理)
涡轮机
组分(热力学)
汽车工程
功率(物理)
风险分析(工程)
系统工程
工程类
机械工程
热力学
物理
医学
量子力学
作者
Samar TAHA,Firas Basim Ismail,Sivadass Thiruchelvam
摘要
Gas turbines efficiently produce high amounts of electrical power hence they have been widely deployed as dependable power generators. It has been detected that the performance of gas turbines is a function of plenty of operational parameters and environmental variables. The impacts of those variables on the said performance can be mitigated using powerful monitoring techniques. Thus, extra maintenance costs, component defect costs, and manpower costs can be illuminated. This paper has enlisted the factors impacting gas turbine efficiency. It has also reviewed multiple monitoring solutions for the said impacting factors, It has been concluded that all types of sensors have ignored errors in their work, which may exacerbate the problems of malfunctions in gas turbines due to the critical environment in which they operate (heat, fumes, etc.); however, the machine learning-based monitoring systems excel in addressing such problems. The most cost-effective and accurate monitoring task can be achieved by using machine learning and deep learning tools.
科研通智能强力驱动
Strongly Powered by AbleSci AI