Rough sets-based prediction model for increasing safety of thermal power plants

ABSTRACT

This paper presents a model based on the rough sets theory for the prediction of a feed pump failure on a steam block of thermal power plant. There are many parameters that can cause pump failure, and this model enables extraction of the most significant ones. Model creation is based on the empirical data collected during the operation of thermal power plant, which is a part of the largest system for electricity production in Serbia. The model provided an insight into the parameters that have the greatest influence on the operation of the feed pump, and can be applied to other elements of the thermal power plant and affect the overall increase in the safety of thermal power plant operation. The goal of implementation of a new model is to increase system reliability by reducing the number of failures, thus increasing operational safety of thermal power plants. This is in accordance with the provision of energy security by applying measures of Directive 2005/89/EU. According to the directive, it is necessary to ensure: a reliable, safe, efficient and quality power supply.

KEYWORDS:

• Thermal power plant
• safety
• feed pump
• failure
• rough set model

Acknowledgments

This research is financially supported by Ministry of Education and Science of the Republic of Serbia under the project number TR32044 “The development of software tools for business process analysis and improvement,” 2011–2018, and under the project number TR34028 “Research and optimization of technological and functional performance of ventilation mill Kostolac B,” 2011–2018.