Data Driven Condition Monitoring Based on a Digital Twin for a Linear Actuator Realized As a Closed Hydraulic System

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Oct 28, 2022
Kurt Pichler Paul Foschum Rainer Haas Johannes Schwacke

Abstract

Linear actuators, implemented as closed hydraulic systems, without external piping, are a state of the art drive concept, see (Gannon, 2017). Collecting data, used to train a condition monitoring (CM) for such drives, running 24/7, is cumbersome or even not possible. To gain training data, containing valid and invalid system states, we developed a simulation model, consisting of the most relevant physical effects. The simulated data are evaluated by a one-step feature approach and additionally with a two-step approach using two less complex fault state separation methods. In the end, the two-step method showed to be slightly better. The condition monitoring is not only used to recognize, but also to distinguish between accumulator and pump faults.

How to Cite

Pichler, K., Foschum, P., Haas, R., & Schwacke, J. (2022). Data Driven Condition Monitoring Based on a Digital Twin for a Linear Actuator Realized As a Closed Hydraulic System. Annual Conference of the PHM Society, 14(1). https://doi.org/10.36001/phmconf.2022.v14i1.3174
Abstract 25 | PDF Downloads 18

##plugins.themes.bootstrap3.article.details##

Keywords

Hydraulics, Linear Actuator, Fault Diagnosis, Digital Twin, Machine Learning

Section
Poster Presentations