Back to Search
Start Over
Model based learning for efficient modelling of heat transfer dynamics
- Source :
- Procedia CIRP, 102, 18th CIRP Conference on Modeling of Machining Operations (CMMO)
- Publication Year :
- 2021
- Publisher :
- Elsevier BV, 2021.
-
Abstract
- Predictive models are crucially relevant for the design and control of manufacturing processes, particularly when process quality is highly sensitive to unknown physical parameters. This paper describes a method to model industrial processes using neural networks and physical prior knowledge. The approach is applied to heat transfer problems, particularly relevant for additive manufacturing processes, and the results are compared to alternative methodologies. Obtained results show that the integration of partial differential equations in the neural network model leads to reduced amounts of required training data and increases the model stability. Such outcomes represent promising characteristics for novel model predictive control strategies.<br />Procedia CIRP, 102<br />ISSN:2212-8271<br />18th CIRP Conference on Modeling of Machining Operations (CMMO)
- Subjects :
- Process quality
Physics informed neural networks
Partial differential equation
Model based learning
Artificial neural network
Neural networks
Additive manufacturing
Computer science
Dynamics (mechanics)
Stability (learning theory)
Control engineering
Model predictive control
Heat transfer
General Earth and Planetary Sciences
General Environmental Science
Subjects
Details
- ISSN :
- 22128271
- Volume :
- 102
- Database :
- OpenAIRE
- Journal :
- Procedia CIRP
- Accession number :
- edsair.doi.dedup.....0bc07cb98ed3afc865d130e9254e95d2