LSTM water prediction for feedforward control of moulding sand compressibility
- This paper presents a databased approach for improving the precision of the moulding sand compressibility in the moulding sand mixer of a foundry. In this approach, the deviation between the measured and the target compressibility is reduced by controlling the water addition. The complex dynamic behaviour of the process variables and their influence on the water addition is modelled with a long short-term memory (LSTM) network. Another LSTM network as control path simulates the impact of the water addition on the compressibility. Simulation and experimental results with the applied model for water prediction in a feedforward control yield relevant improvements of the moulding sand compressibility.
| Author: | Alexander RoseORCiD, Alexander Seel, Bennett Luck, Martin GrotjahnORCiDGND |
|---|---|
| URN: | urn:nbn:de:bsz:960-opus4-19276 |
| DOI: | https://doi.org/10.25968/opus-1927 |
| DOI original: | https://doi.org/10.1016/j.ifacol.2020.12.2782 |
| Parent Title (English): | IFAC-PapersOnLine |
| Document Type: | Article |
| Language: | English |
| Year of Completion: | 2020 |
| Publishing Institution: | Hochschule Hannover |
| Release Date: | 2021/05/18 |
| Tag: | batch control; feedforward control; industrial production system; intelligent control; neural control; neural network model; prediction methods; target control |
| Volume: | 53 |
| Issue: | 2 |
| First Page: | 10417 |
| Last Page: | 10422 |
| Link to catalogue: | 1770452761 |
| Institutes: | Fakultät II - Maschinenbau und Bioverfahrenstechnik |
| DDC classes: | 620 Ingenieurwissenschaften und Maschinenbau |
| Licence (German): |  Creative Commons - CC BY-NC-ND - Namensnennung - Nicht kommerziell - Keine Bearbeitungen 4.0 International |
