Session: 35-04 Fan, Compressor and Engine Noise 1

Paper Number: 123839

123839 - Centrifugal Compressor Instrumentation for Developing an Anomaly Detection Method Using Vibration- and Acoustic Measurement Data 

In various industrial applications, acoustic measurement data is used for condition-based monitoring and predictive maintenance. These concepts enable the early detection of faulty machine behavior as well as the efficient planning of maintenance. Time-resolved measurements offer a promising approach for fault identification since every industrial process has a unique spectral fingerprint that allows for the differentiation between operating points as well as normal and faulty machine behavior. For this purpose, the acoustic reference state of the machine is determined and compared with measurement data obtained during operation to quantify the changes in the acoustic signal. This technique aims to identify even minor faults, which are not detectable by performance monitoring. Furthermore, the process is unaffected by measurement equipment because the microphones are positioned noninvasively on the outside of the machine. In the field of turbomachinery, however, this method is not yet widely used due to the complexity of the process and the high overall noise level.

In this paper, a test rig for developing an anomaly detection method using vibration and acoustic measurement data is presented. A single-stage centrifugal compressor is equipped with high-frequency accelerometers and free-field microphones in addition to conventional process data instruments. Spectral evaluation methods are discussed and used to differentiate between operating points. Additionally, the reference state of the compressor and the influence of compressor reassembly on the measurement results are determined.

Presenting Author: Nick Linnemann University of Duisburg-Essen

Presenting Author Biography: Studied at the University of Duisburg-Essen from 2015 to 2022, graduating with a bachelor's and master's degree in mechanical engineering. Working as Scientific Researcher and doctoral student at the Chair of Turbomachinery, University of Duisburg-Essen since August 2022.

Authors:

Nick Linnemann University of Duisburg-Essen
Bastian Dolle University of Duisburg-Essen
Dieter Brillert University of Duisburg-Essen