Knüttel, Daniel and Baraldo, Stefano and Valente, Anna and Wegener, Konrad and Carpanzano, Emanuele (2021) Model based learning for efficient modelling of heat transfer dynamics. In: 18th CIRP Conference on Modeling of Machining Operations.
![[img]](http://repository.supsi.ch/style/images/fileicons/text.png) |
Text
2021_Knüttel_Model based learning for efficient modelling of heat transfer dynamics.pdf - Published Version Restricted to Registered users only Download (879kB) |
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.
| Item Type: | Article in conference proceedings or Presentation at a conference (Paper) |
|---|---|
| Subjects: | Engineering > Production & manufacturing engineering Engineering > Production & manufacturing engineering > Manufacturing systems engineering Engineering > Production & manufacturing engineering > Manufacturing systems engineering > Production processes |
| Department/unit: | Dipartimento tecnologie innovative > Istituto sistemi e tecnologie per la produzione sostenibile |
| Depositing User: | Anneke Katharina Orlandini |
| Date Deposited: | 16 Mar 2023 08:06 |
| Last Modified: | 16 Mar 2023 08:10 |
| URI: | http://repository.supsi.ch/id/eprint/13793 |
Actions (login required)
 |
View Item |