Abstract
The present paper considers a multi-criteria analysis algorithm of turbo generator fluid-film bearing operability and its connection with rotor machine monitoring system data. It is substantiated that implementation of predictive analysis of load capacity, locus curves and dynamic displacements allows prognosis of useful life of a fluid-film bearings and improvement of reliability of a rotor machine.
Highlights
One of the key components of a power plant is a turbogenerator
These systems are a natural evolution of existing monitoring and diagnostic systems, based on the development of the Internet of things, artificial neural networks and machine learning
If the current load capacity is sufficient, and the friction moment is high, we are talking about the wear of the antifriction layer, and if the load capacity is insufficient and the friction moment is high, it is logical to assume the operation in the semi-fluid friction mode
Summary
One of the key components of a power plant is a turbogenerator. Ensuring its reliable and safe operation is a priority, the downtime of such equipment leads to significant costs and underproduction of energy. A turbogenerator is a complex multi-parameter system (Fig. 1) in which interconnected electromagnetic, thermal, hydrodynamic, mechanical processes take place, for example, in a gas turbine unit GE LM6000, more than 6000 parameters are simultaneously controlled [11] Such an analysis is not always effective, since the process of the controlled parameters going beyond the set limits means the beginning of the emergency process of the technical system, followed by a stop and the subsequent determination of the causes of failures and their exclusion during repair work. An exception is the system of intelligent forecasting of a healthy state based on multivariate statistical analysis using machine learning methods, for example: Predictive system PRANA [12]; Plant Monitor – Siemens [13]; Predix – GE [14] These systems are a natural evolution of existing monitoring and diagnostic systems, based on the development of the Internet of things, artificial neural networks and machine learning.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
