In-Process Monitoring and Control of Computer Numerical Control Machine Tool Operations
Lead Research Organisation:
CARDIFF UNIVERSITY
Department Name: Sch of Engineering
Abstract
This project will develop technology to create high-efficiency and reliability in Computer Numerical Control (CNC) machine operations using Acoustic Emission (AE), leading to an advanced tool control strategy.
Machine tools are subject to wear and possible failure during their operational life that can lead to poorly manufactured parts or scrapping of a component. The aim of this four year studentship is therefore to use Acoustic Emissions to monitor the tool during the CNC process to move from the current approach of periodic wear measurements to an 'as required' approach leading to high-efficiency and importantly prevent tool failure. This project will develop a detailed understanding of AE signatures associated with the CNC process, released by the tool and the component, in normal operations and during defect development. Using Machine Learning a data interrogation approach that can identify wear will be developed leading to a control system capable of detecting tool damage that will automatically adjust the CNC process during manufacture. This will aid efficiency by removing the need to periodically measure tool wear and importantly prevent tool failure.
Machine tools are subject to wear and possible failure during their operational life that can lead to poorly manufactured parts or scrapping of a component. The aim of this four year studentship is therefore to use Acoustic Emissions to monitor the tool during the CNC process to move from the current approach of periodic wear measurements to an 'as required' approach leading to high-efficiency and importantly prevent tool failure. This project will develop a detailed understanding of AE signatures associated with the CNC process, released by the tool and the component, in normal operations and during defect development. Using Machine Learning a data interrogation approach that can identify wear will be developed leading to a control system capable of detecting tool damage that will automatically adjust the CNC process during manufacture. This will aid efficiency by removing the need to periodically measure tool wear and importantly prevent tool failure.
People |
ORCID iD |
Rhys Pullin (Primary Supervisor) | |
Thomas Jessel (Student) |
Studentship Projects
Project Reference | Relationship | Related To | Start | End | Student Name |
---|---|---|---|---|---|
EP/W521978/1 | 01/10/2021 | 30/09/2026 | |||
2599318 | Studentship | EP/W521978/1 | 01/10/2021 | 30/09/2025 | Thomas Jessel |