Abstract
Machining of stainless steels is characterized by rapid tool wear due to the formation of built-up edge (BUE) at the tool-chip interface. In this study, an acoustic emission (AE) technique is implemented with 231 sets of turning experimental trials to monitor BUE formation during dry turning of AISI 304 stainless steel. AE and cutting force signals are analyzed in both the time and frequency domains during the machining process. Correlation of various extracted features with BUE formation is established. Furthermore, two model-based approaches for BUE height monitoring are presented on the basis of artificial intelligence technologies. To this end, various inputs single-output (BUE height) models are developed and tested on the basis of artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) models. Finally, the developed monitoring system is implemented to classify the state of BUE during the machining process.
| Original language | English |
|---|---|
| Pages (from-to) | 2257-2276 |
| Number of pages | 20 |
| Journal | International Journal of Advanced Manufacturing Technology |
| Volume | 103 |
| Issue number | 5-8 |
| DOIs | |
| State | Published - 19 Aug 2019 |
| Externally published | Yes |
Bibliographical note
Publisher Copyright:© 2019, Springer-Verlag London Ltd., part of Springer Nature.
Keywords
- ANFIS
- ANN
- Acoustic emission
- Built-up edge
- Machining
- Monitoring
ASJC Scopus subject areas
- Control and Systems Engineering
- Software
- Mechanical Engineering
- Computer Science Applications
- Industrial and Manufacturing Engineering