Data driven weighted estimation error benchmarking for estimators and condition monitoring systems

2004 ◽  
Vol 151 (4) ◽  
pp. 511-521 ◽  
Author(s):  
M.J. Grimble
2018 ◽  
Vol 12 (3-4) ◽  
pp. 525-533 ◽  
Author(s):  
Dominik Kißkalt ◽  
Hans Fleischmann ◽  
Sven Kreitlein ◽  
Manuel Knott ◽  
Jörg Franke

Author(s):  
Raghul Manosh Kumar ◽  
Benjamin Peters ◽  
Benjamin Emerson ◽  
Kamran Paynabar ◽  
Nagi Gebraeel ◽  
...  

Abstract This paper introduces a data-driven framework for combustor-focused, performance-based condition monitoring of gas turbines. Commercial condition monitoring systems typically generate huge amounts of data that make efficient onboard monitoring challenging. This paper focuses on quantifying combustor component degradation, using premixer centerbody degradation in a swirl stabilized combustor as a case study. The input for these analyses is acoustic pressure measurements acquired at various locations on the combustor. The diagnosis methodology is based on a classification framework and consists of 3 steps: 1) Data curation, 2) Feature Engineering, and 3) Diagnosis. Data curation ensures good quality of the data that is passed through the algorithm. Feature engineering deals with the extraction of the most informative features, from the most informative sensors, that can accurately capture the introduced fault. To perform diagnosis, the classification model is trained using experimentally acquired data and is then tested on a separate data set. The framework was able to achieve high classification accuracy (>99%) for training size as low as 30% of the total recorded observations. The low number of features required to achieve this accuracy suggests high potential for integration into existing onboard condition monitoring systems.


Author(s):  
Bogdan Leu ◽  
Bogdan-Adrian Enache ◽  
Florin-Ciprian Argatu ◽  
Marilena Stanculescu

2014 ◽  
Vol 971-973 ◽  
pp. 1045-1050
Author(s):  
Wen Xing Sun ◽  
Zhao Hui Li ◽  
Shi Jie Cheng

Many successful applications for the online monitoring of the insulation condition for electric power transformers have been reported over last thirty years. However, false or unsolved alarms have been quite frequently generated by those condition monitoring systems. Failures and some occasionally catastrophic accidents involving transformers have still occurred. A highly reliable insulation condition online monitoring and real-time alarm system has been developed, to help resolve these problems. An electric power transformer has strongly linked mechanical, electrical, magnetic, chemical and thermal characteristics, and is also directly linked to circuit breakers and generators. Team Intelligence (TI) was employed to integrate all the monitoring modules of the various different aspects of the transformer into one unique system. This system could also be integrate with the condition monitoring systems of various linked facilities, such as the monitoring systems of the turbine and the generator in a Optimal Maintenance Information System for Hydropower Plant (HOMIS). Highly reliable monitoring and real-time alarms of transformer insulation condition could be achieved, due to highly coordinated and rapid response features. This system has been deployed in several hydropower plants. The industrial application examples are demonstrated.


Sign in / Sign up

Export Citation Format

Share Document