Abstract
Boiler waterwall tube leakage is the most probable cause of failure in steam power plants (SPPs). The development of an intelligent tube leak detection system can increase the efficiency and reliability of modern power plants. The idea of e-maintenance based on multivariate algorithms was recently introduced for intelligent fault detection and diagnosis in SPPs. However, these multivariate algorithms are highly dependent on the number of input process variables (sensors). Therefore, this work proposes a machine learning-based model integrated with an optimal sensor selection scheme to analyze boiler waterwall tube leakage. Finally, a real SPP test case is employed to validate the proposed model’s effectiveness. The results indicate that the proposed model can successfully detect waterwall tube leakage with improved accuracy vs. other comparable models.
Highlights
Given the growing demand for electricity, the operation of modern power plants must be ever more efficient and reliable [1]
The idea of e-maintenance based on multivariate algorithms [11] was recently introduced for intelligent fault detection and diagnosis in steam power plant (SPP)
This study utilizes the data from 38 sensitive sensors in a SPP: these sensors provide data on the inlet and outlet header temperatures; the tube metal temperature, which is collected from thermocouples mounted on the superheaters (SHI, SHII, and SHIII) and reheaters (RHI and RHII); and the active power of the corresponding generator
Summary
Given the growing demand for electricity, the operation of modern power plants must be ever more efficient and reliable [1]. These techniques can be employed to eliminate the need for additional tasks and can assist in efficient monitoring of the status of SPPs [12] These approaches utilize the operators’ knowledge with rich industrial experiences and use the process control variables (sensors) selected by the experts in power plants for intelligent fault diagnosis. Zhang et al [15] developed a three-dimensional algorithm based on a time delay of arrival (TDOA) approach that utilizes acoustic emission technology to detect furnace waterwall tube leakage and localize leaks in a 600 MW power plant. This approach requires the installation of expensive devices (acoustic sensors), and it is not effective at detecting small tube leaks. Plantwaterwall boiler waterwall tube leak scenario to validate the proposed model’s effectiveness
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
