Application of the REx5 Expert System to Condition Monitoring of the Simple Liquid Flow Process Control Trainer Sebastian Rzydzik, Krzysztof Psiuk, Marcin Amarowicz and Tomasz Rogala Abstract This work deals with the problems that are related to the condition monitoring of the selected technical object. For this purpose, specialized software called REx5 was developed. The REx5 is a modular expert system. Inference module of this system allows to conduct the inference process for two types of knowledge representation: the intuitionistic and Bayesian statement networks. All data required for the inference processes are stored in especially designed OPC UA Server with archive database of process data. Another module, designed to manage diagnostic tasks, allows to congure the parameters for condition monitoring of observed technical object. The simple liquid ow process control trainer is the studied object. This trainer allows for various control functions, like the control of the medium level in the tank, control of the ow rate, or control of the medium temperature. Additionally, the trainer is equipped with a data acquisition subsystem. The purpose of this subsystem is the acquisition values of the selected process signals and sharing these data for external systems used by OPC UA Server. Keywords Diagnostic system Expert system Diagnostic inference Intuitionistic network Bayesian network S. Rzydzik (&) K. Psiuk M. Amarowicz T. Rogala Institute of Fundamentals of Machinery Design, Faculty of Mechanical Engineering, Silesian University of Technology, 18A Konarskiego Str, 44-100 Gliwice, Poland e-mail: sebastian.rzydzik@polsl.pl K. Psiuk e-mail: krzysztof.psiuk@polsl.pl M. Amarowicz e-mail: marcin.amarowicz@gmail.com T. Rogala e-mail: tomasz.rogala@polsl.pl © Springer International Publishing AG 2018 A. Timoejczuk et al. (eds.), Advances in Technical Diagnostics, Applied Condition Monitoring 10, DOI 10.1007/978-3-319-62042-8_29 323