In the paper we describe the industrial process of hot rolling of steel. In cooperation with ArcelorMittal Poland we consider a specific fully automated production line. While it is equipped with a number of industrial sensors, the acquired data has only been analyzed on a basic statistical level, mainly for reporting. In the paper we outline opportunities for the use of AI methods in order to improve the process and possibly the quality of the resulting product. We report on preliminary results using selected methods of eXplainable AI.