Coal Pulverizer Prognostics Data Challenge in PHMAP 2017 and Suggestions for Future Studies
Pulverizers in a power plant are used to grind coal into the form of a fine powder for combustion in a power plant. To secure reliable operation, redundant pulverizers should be installed in power plants and monitored. Pulverizers can be operated and maintained in a cost-effective manner by correctly estimating the current health condition and remaining useful life of the pulverizer’s gearbox system. To this end, the Data Challenge Committee of the PHM Asian Pacific 2017 (PHMAP 2017) conference organized an open competition on the topic of coal pulverizer health estimation based on a real working power station. This paper presents the original problem and given facts, as well as the list of winners of the Data Challenge Competition. We anticipate that this paper can be used as a reference in the development of a prognostic method that can accurately predict the health conditions of coal pulverizers.
PHM, prognostic method, fault, Data Challenge, Pulverizer
Chow, T. W. S. and Tan, H. Z. (2000). HOS-based nonparametric and parametric methodologies for machine fault detection, IEEE Transactions on Industrial Electronics, vol. 47(5), pp. 1051-1059.
CWRU Bearing Data Center, https://csegroups.case.edu/bearingdatacenter/pages/welcome-case-western-reserve-university-bearing-data-center-website, Accessed on Dec. 16, 2017.
Korean Society for Prognostics and Health Management (KSPHM) Data Repository for PHMAP 2017 Data Challenge, http://www.phm.or.kr/info/board.php, Accessed on Apr. 11, 2018.
Lee, G., Kim, S., Song, J., and Kim, T. (2017). Failure prognosis of coal pulverizer gearbox using autocorrelation wavelet packet decomposition method. In Proceedings of the Asian Pacific Conference of the Prognostics and Health Management Society, July 12-15, Jeju, Korea.
Lee, J., Wu, F., Zhao, W., Ghaffari, M., Liao, L., and Siegel, D. (2014). Prognostics and health management design for rotary machinery systems—Reviews, methodology and applications, Mechanical Systems and Signal Processing, vol. 42(1-2), pp. 314-334.
NASA Prognostics Data Repository, https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository/, Accessed on December 16, 2017.
Park, J., Jeon, B., Park, J., Cui, J., Kim, M., and Youn, B.D. (2017) Failure prediction of a motor-driven gearbox in a pulverizer under external noise and disturbance. Smart Structures and System, in press.
PHM Society Data Challenge Competition, http://www.phmsociety.org/competition, Accessed on December 16, 2017.
Song, D., Ding, Y., and Lu, C. (2017). A prognostics approach for gearbox based on spectrogram and deep learning. International Journal of Prognostics and Health Management, in press.
Tian, J., Morillo, C., Azarian, M. H., and Pecht, M. (2016). Motor bearing fault detection using spectral kurtosis-based feature extraction coupled with k-nearest neighbor distance analysis, IEEE Transactions on Industrial Electronics, vol. 63(3), pp. 1793-1803.