Data analytics for leak detection in a subcritical boiler

For decades, boiler leaks have been the leading cause of forced outages in the coal-fired unit. The leak occurrences are currently escalating since the existing plants must satisfy faster-ramping rates to support grid operation. Data analytics including Principal Component Analysis (PCA), Canonical...

Full description

Saved in:
Bibliographic Details
Published in:Energy (Oxford) 2021-04, Vol.220, p.119667, Article 119667
Main Authors: Indrawan, Natarianto, Shadle, Lawrence J., Breault, Ronald W., Panday, Rupendranath, Chitnis, Umesh K.
Format: Article
Language:English
Subjects:
Coal
Coal-fired power plants
CV-FDA
Data analysis
Discriminant analysis
Electric power generation
Leak detection
PCA
Power plants
Principal components analysis
Process variables
Subcritical boiler
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:For decades, boiler leaks have been the leading cause of forced outages in the coal-fired unit. The leak occurrences are currently escalating since the existing plants must satisfy faster-ramping rates to support grid operation. Data analytics including Principal Component Analysis (PCA), Canonical Variate, and Fisher Discriminant Analysis (CV-FDA) were combined for detecting and characterizing the leak in a commercial 650 MW subcritical coal-fired power plant. The combined approach was shown to be highly effective in the fault investigation that would not have been easily achieved by an individual technique. The variability in both training and validation datasets was first evaluated using PCA. Then, the CV-FDA was employed to discriminate among faults, and to categorize the processed data into two main groups: no-leak (0) and leak (1), providing the timeframe and location of the leak occurrence. About 8,014 observations from 81 process variables were initially included in the calculation, while the variable count was reduced to 4 with less than 1% misclassification rate in total observations. Finally, the leak was isolated in the waterwall section. Thus, the outcome of this research may provide early detection and isolation of faulty operations in the coal-fired power plant that involves a considerable number of process variables. •Data analytics was applied to analyze boiler leaks in a commercial power plant.•Multivariate statistical techniques (PCA, CVA, and FDA) were applied.•About 8014 observations with 81 process variables were included.•Less than 1% of total observations were misclassified.•The leaks were at the waterwall with a strong correlation to condenser operation.
ISSN:0360-5442
1873-6785
DOI:10.1016/j.energy.2020.119667