Leakage Detection of Steam Boiler Tube in Thermal Power Plant Using Principal Component Analysis

Jungwon Yu, Jaeyel Jang, Jaeyeong Yoo, June Ho Park, and Sungshin Kim
Submission Type: 
Full Paper
AttachmentSizeTimestamp
phmc_16_011.pdf745.19 KBSeptember 6, 2016 - 7:51pm

Tube leakage of steam boiler can decrease the whole efficiency of power plant cycle, and eventually cause an unscheduled shutdown. In this paper, we propose a leakage detection method for steam boiler tubes in thermal power plant (TPP) using principal component analysis. To determine the number of principal components, the cumulative percent variance technique is employed, and the Q statistic is used as detection index. If the Q statistic of an unseen sample is larger than a predefined threshold value, the sample is detected as a fault sample and an alarm signal is generated. The weighted moving average is used to reduce false alarms. To demonstrate the performance, we apply the proposed method to an unplanned shutdown case due to boiler tube leakage, which is collected from distributed control systems of 250 MW coal-fired TPP. The experiment results show that the proposed method can detect failure symptoms of the case successfully.

Publication Year: 
2016
Publication Volume: 
7
Publication Control Number: 
011
Page Count: 
8
Submission Topic Areas: 
Data-driven methods for fault detection, diagnosis, and prognosis
Submitted by: 
  
 
 
 

follow us

PHM Society on Facebook Follow PHM Society on Twitter PHM Society on LinkedIn PHM Society RSS News Feed