Abstract
While machining processes are typically leveraged to establish geometric features, many functional characteristics of advanced materials are directly determined by their machining-induced quality, i.e. surface integrity. Current modeling approaches struggle to predict surface integrity, and typically neglect the effects of progressive tool-wear, resulting in inefficient ‘static’ process parameters. We present a novel integrated approach based on model-informed artificial intelligence (AI), which quickly and efficiently optimizes ‘dynamic’ process parameters. By maximizing the useful life of a cutting tool over which required quality parameters can be maintained, our paradigm will enable significantly more efficient processing of next-generation materials and components.
| Original language | English |
|---|---|
| Pages (from-to) | 42-46 |
| Number of pages | 5 |
| Journal | Manufacturing Letters |
| Volume | 29 |
| DOIs | |
| State | Published - Aug 2021 |
Bibliographical note
Publisher Copyright:© 2021 Society of Manufacturing Engineers (SME)
Funding
This material is based upon work supported by the U.S. Department of Energy’s Office of Energy Efficiency and Renewable Energy (EERE) under the Advanced Manufacturing Office’s (AMO) DE-FOA-0001980, Award Number DE-EE0009121/0000, project title “AI-Enabled Discovery and Physics Based Optimization of Energy Efficient Processing Strategies for Advanced Turbine Alloys”.
| Funders | Funder number |
|---|---|
| U.S. Department of Energy EPSCoR | |
| DOE Advanced Manufacturing Office and Advanced Materials & Manufacturing Technologies Office | DE-EE0009121/0000, DE-FOA-0001980 |
| Office of Energy Efficiency and Renewable Energy |
Keywords
- Machining
- Process modeling
- Reinforcement learning
- Smart manufacturing
- Surface integrity
ASJC Scopus subject areas
- Mechanics of Materials
- Industrial and Manufacturing Engineering