Fault detection for sliding bearings using acoustic emission signals and machine learning methods
Florian König, Georg Jacobs, Andreas Stratmann, Daniel Cornel
Abstract
Abstract Driven by the potential application of sliding bearings under wear-and fatigue-critical operating conditions, i.e. in planetary gearboxes for wind turbines or automotive engines with start-stop systems, the reliability and lifetime prognosis of heavy loaded sliding bearings under low rotational speeds is an emerging field of research. The application of machine learning (ML) offers a great potential for all kinds of engineering applications when physical models are not feasible due to their complexity. This study showcases the application of ML to wear and fatigue fault detection and lifetime prognosis for sliding bearings using acoustic emission signals.
Topics & Concepts
Bearing (navigation)Reliability (semiconductor)Acoustic emissionAutomotive engineeringFault detection and isolationFault (geology)Wind powerAutomotive industryField (mathematics)Condition monitoringComputer scienceEngineeringMaterials scienceArtificial intelligencePower (physics)Aerospace engineeringGeologyElectrical engineeringComposite materialPhysicsSeismologyMathematicsPure mathematicsQuantum mechanicsActuatorMachine Fault Diagnosis TechniquesGear and Bearing Dynamics AnalysisLubricants and Their Additives