Data-driven fault diagnosis based on coal-fired power plant operating data
- PDF / 972,751 Bytes
- 6 Pages / 595.22 x 842 pts (A4) Page_size
- 95 Downloads / 230 Views
DOI 10.1007/s12206-020-2202-0
Journal of Mechanical Science and Technology 34 (0) 2020 Original Article DOI 10.1007/s12206-020-2202-0 Keywords: · Coal-fired power plants · Data-driven · Early detection · Mahalanobis distance · Sequential probability ratio test · Tube leakage
Correspondence to: Daeil Kwon [email protected]
Citation: Choi, H., Kim, C.-W., Kwon, D. (2020). Data-driven fault diagnosis based on coalfired power plant operating data. Journal of Mechanical Science and Technology 34 (0) (2020) ?~?. http://doi.org/10.1007/s12206-020-2202-0
Received April 20th, 2020 Revised
May 12th, 2020
Accepted May 12th, 2020 † This paper was presented at ICMR2019, Maison Glad Jeju, Jeju, Korea, November 27-29, 2019. Recommended by Guest Editor Insu Jeon
© The Korean Society of Mechanical Engineers and Springer-Verlag GmbH Germany, part of Springer Nature 2020
Data-driven fault diagnosis based on coal-fired power plant operating data Hongjun Choi1, Chang-Wan Kim2 and Daeil Kwon3 1
Graduate School of Mechanical Design & Production Engineering, Konkuk University, Seoul 05029, 2 3 Korea, School of Mechanical Engineering, Konkuk University, Seoul 05029, Korea, Department of Systems Management Engineering, Sungkyunkwan University, Suwon 16419, Korea
Abstract
This paper discusses data-driven fault diagnosis of the power plant reheater tube leakage based on their operating data. From the temperature sensors, fault data and normal data are measured. Mahalanobis distance (MD) analysis was performed to quantitatively analyze whether the distribution of fault data differed from that of the normal data. Then, sequential probability ratio test (SPRT) was performed to determine the time to anomalies (TTAs). To verify detected TTAs, power-generation data was used. This paper demonstrated the feasibility of the proposed approach to detect reheater tube leakage prior to the failure.
1. Introduction A coal-fired power plant consists of multiple facilities, including boilers, pumps, fans, and turbines. Each facility is designed to perform under specific operating parameters, such as temperatures, pressure levels, and flow rates. During the operation of power plants, facilities are consistently exposed to high temperature and pressure levels, resulting in accelerated component aging and unexpected component faults, e.g., leakage of a boiler tube. Under these adverse operating conditions, the operating parameters may deviate from their acceptable ranges. For example, when dirt or scale builds up on a boiler-tube wall, the fluid flow path across the tube narrows; thus, the fluid pressure increases. Changes in operating parameters may adversely affect the stability of electricity production of a power plant and can eventually cause unplanned plant shutdown. The cost of damage to the manufacturing industry due to an hour of electricity outage in Austria was estimated to be €7 billion [1]. Continuous monitoring and diagnosis of power-plant anomalies can serve as a means to prevent such consequences. Prognostics and health management (PHM
Data Loading...
