Comparison of Machine Learning Techniques in Prognostic Maintenance of Hydropower plant Subsystem

  • Nayab Khan Department of Computer Systems Engineering, University of Engineering and Technology, Peshawar, KPK, Pakistan.
  • Laiq Hassan Department of Computer Systems Engineering, University of Engineering and Technology, Peshawar, KPK, Pakistan.
  • Yasir Afridi Department of Computer Systems Engineering, University of Engineering and Technology, Peshawar, KPK, Pakistan.
  • Azaz Rashid Department of Computer Systems Engineering, University of Engineering and Technology, Peshawar, KPK, Pakistan.

Abstract

With the advent of time, automation is becoming an inevitable component of human lives. Our homes, industries,
offices, market areas, etc. are being mechanized and human power is slowly being replaced by machines. Although
it has increased the system efficiency manifold, but the probability of system breakdowns has also increased,
since machines are more susceptible to faults. Hence, a continuous monitoring system is therefore required. Many
techniques have since been devised for better maintenance of machines throughout their operation so as to increase
their useful life. This paper presents the use and comparison of two different machine learning techniques for fault
sensing ahead of time and prognostic maintenance of a turbine System. The data is acquired from the turbine of
a hydro power plant installed in Dargai, Malakand Agency, Pakistan. The machine learning techniques compared
in this paper for fault sensing and prognostic maintenance of a turbine system are support vector machines and
artificial neural networks.

Published
2020-03-10
How to Cite
Khan, N., Hassan, L., Afridi, Y., & Rashid, A. (2020). Comparison of Machine Learning Techniques in Prognostic Maintenance of Hydropower plant Subsystem. Quaid-E-Awam University Research Journal of Engineering, Science & Technology, Nawabshah., 17(2), 31-37. Retrieved from http://publications.quest.edu.pk/ojs-3.1.1-4/index.php/qrj/article/view/105