Regression Methods for Detecting Anomalies in Flue Gas Desulphurization Installations in Coal-Fired Power Plants Based on Sensor Data Marek Moleda 1,2(B ) , Alina Momot 2 , and Dariusz Mrozek 2 1 TAURON Wytwarzanie S.A., Jaworzno, Poland marek.moleda@gmail.com 2 Silesian University of Technology, ul. Akademicka 16, 44-100 Gliwice, Poland dariusz.mrozek@polsl.pl Abstract. In the industrial world, the Internet of Things produces an enormous amount of data that we can use as a source for machine learn- ing algorithms to optimize the production process. One area of applica- tion of this kind of advanced analytics is Predictive Maintenance, which involves early detection of faults based on existing metering. In this paper, we present the concept of a portable solution for a real-time con- dition monitoring system allowing for early detection of failures based on sensor data retrieved from SCADA systems. Although the data processed in systems, such as SCADA, are not initially intended for purposes other than controlling the production process, new technologies on the edge of big data and IoT remove these limitations and provide new possibili- ties of using advanced analytics. This paper shows how regression-based techniques can be adapted to fault detection based on actual process data from the oxygenating compressors in the flue gas desulphurization installation in a coal-fired power plant. Keywords: Predictive maintenance · Power plant · SCADA · Anomaly detection 1 Introduction Operational Technology (OT) systems refer to hardware and software solutions that are capable of changing various industrial processes through the direct mon- itoring and controlling of physical devices, procedures, routes, and events in a This work was supported by the Polish Ministry of Science and Higher Education as part of the Implementation Doctorate program at the Silesian University of Technol- ogy, Gliwice, Poland (contract No 0053/DW/2018), and partially, by the professor- ship grant (02/020/RGPL9/0184) of the Rector of the Silesian University of Tech- nology, Gliwice, Poland, and partially, by Statutory Research funds of Department of Applied Informatics, Silesian University of Technology, Gliwice, Poland (grant No BK/SUBB/RAu7/2020 and grant No BKM/SUBB-MN/RAu7/2020). c  Springer Nature Switzerland AG 2020 V. V. Krzhizhanovskaya et al. (Eds.): ICCS 2020, LNCS 12141, pp. 316–329, 2020. https://doi.org/10.1007/978-3-030-50426-7_24