Machine Learning-Based Prediction of EDM Material Removal Rate and Surface Roughness
Problem
Predicting material removal rate and surface roughness in electrical discharge machining (EDM) is difficult because of complex physical events in the electrode gaps.
Why it matters
Accurate prediction reduces costly trial-and-error in precision manufacturing.
What the AI did
Multiple machine learning models were trained on experimental EDM data to map process parameters to responses; GPR performed best.
Results
GPR achieved average RMSE of 0.9234 (MRR) and 3.0216 (Sa), outperforming other ML models across materials.
Impact
The evidence supports ML as an effective tool for modeling EDM performance, though deployment is only proposed.
Record
| Venue | Journal of Manufacturing and Materials Processing |
|---|---|
| Published | 2025 |
| Work type | article |
| Authors | Isam Qasem, Amjad Alsakarneh |
| Citations | 11 (OpenAlex, at import time) |
| References | 34 |
| Model or method | GPR (Gaussian Process Regression) among multiple ML models |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3390/jmmp9080274 |
| Open access | gold |
| Keywords | EDM, machine learning, GPR, material removal rate, surface roughness |
Importance rating
real but narrower advance
Accurate EDM prediction reduces costly trial-and-error in precision manufacturing; a real but narrow process-modeling advance with no stated scale of impact.
More in Engineering & Materials
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Scaling deep learning for materials discovery | 2023 | 1,471 |
8
|
| 2 | Application of Machine Learning in Material Synthesis and Property Prediction | 2023 | 165 |
7
|
| 3 | Machine learning-guided discovery of ionic polymer electrolytes for lithium metal batteries | 2023 | 115 |
7
|
| 4 | Machine Learning for Structural Health Monitoring of Aerospace Structures: A Review | 2025 | 44 |
7
|
| 5 | Power System Transient Stability Assessment Based on Machine Learning Algorithms and Grid Topology | 2023 | 42 |
7
|