Hybrid Machine Learning for CNC Process Monitoring
The transition to highly customized, one-off production in modern manufacturing necessitates sophisticated process monitoring to reduce waste, minimize downtime, and alleviate operator burden. Computer Numerically Controlled (CNC) axes represent a fundamental component of automated manufacturing and...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11015456/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The transition to highly customized, one-off production in modern manufacturing necessitates sophisticated process monitoring to reduce waste, minimize downtime, and alleviate operator burden. Computer Numerically Controlled (CNC) axes represent a fundamental component of automated manufacturing and offer a universal and accessible monitoring option through power supply data. By accurately predicting reference signals and comparing them with real-time measurements, deviations can be used for effective model-based process monitoring and anomaly detection. This study explores the efficacy of hybrid machine learning (ML) models in predicting reference signals for CNC axes using features derived from a physical model. Furthermore, relevant but difficult-to-measure features such as process forces and material removal rate (MRR) were made accessible through soft sensors. Various ML models were evaluated, including tree-based models (e.g. random forest (RF) and gradient boosting (GB)) and deep learning (DL) models (e.g. feed-forward neural networks (FNN), long short-term memory (LSTM) and transformers-based models (TF)). A feature importance analysis was performed to gain a better understanding of the influencing factors, which revealed that velocity, acceleration, process forces, spindle torque, and MRR are relevant. Tree-based models, particularly RF and GB, have been shown to be more accurate and robust than DL approaches, particularly when data is sparse and processes are complex. Although DL models improved with larger data sets, their performance remained inferior to that of tree-based methods. This study emphasizes the advantages of incorporating physical knowledge into hybrid ML models to improve model-based process monitoring. |
|---|---|
| ISSN: | 2169-3536 |