In the last decade, the development of machine connectivity has made possible early fault detection with remote analysis of operating data. Solutions aiming to reduce maintenance costs and production losses due to unplanned downtimes were brought to market. These solutions provide with a model of the equipment in healthy conditions using machine learning techniques applied on historical data. During operation a warning is issued when expected and actual measurements do not match.

Although these solutions have proven their value to detect abnormal behaviors, they generate a large number of alarms that require resource to be analyzed. Moreover these solutions rely on a large number of sensors that need to work correctly both for the learning and the monitoring phase. This generates additional maintenance even though these sensors are often not essential to operate the machine. Lastly the solutions are expensive : their application is usually limited to critical machines with risks of production loss. Indeed they are not economic for a Transmission System Operator that has ensured the availability of its network with redundancy.

The objective of the authors was to focus on the monitoring of radial vibrations of centrifugal compressors. Experience proves this is one of the most critical data for early fault detection. The goal was to develop a smart modelling based on historical data using essential parameters influencing rotor-dynamics. As a result, a clear correlation was found between the operating point and the vibration level, that can be easily shown on a centrifugal compressor map.

A second-degree polynomial equation was successfully tested. The model equation relies only on two compressor physics parameters : flow coefficient and speed. We discuss in the paper the impact of other essential parameters. The method has been applied on different type of centrifugal compressors, with different bearing technology (magnetic...) or shaft driving equipment (gas turbine, EMD).

A fault detection case study using this method is described, eg: vibration variation due to abnormal opening of an anti-surge control valve.

In conclusion this method is a simple alternative to usual condition monitoring solutions. Similarly to what was described in the GT2014-25242 for a Predictive Emission Monitoring System, equations based on physical parameters prove to be an efficient modelling technique. Moreover it helps monitoring teams to better understand the underlying relation between parameters. Indeed to achieve a complete monitoring of a centrifugal compressor health, this method can be combined with first-principle performance models that use the same physical parameters.


A Comprehensive Modeling of Centrifugal Compressor Vibrations for Early Fault Detection

Division / Sponsor:
International Gas Turbine Institute (IGTI)

Paper Proceedings: https://asmedigitalcollection.asme.org/GT/GT2020/volume/84058

Turbo Expo - Virtual Conference

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.