Deep process learning
| Reference number | |
| Coordinator | SICS Swedish ICT Västerås AB |
| Funding from Vinnova | SEK 490 940 |
| Project duration | September 2016 - March 2017 |
| Status | Completed |
Important results from the project
The goal was to identify an area where Deep Learning can increase our understanding on the connections there is between different parts of the industrial processes that affect how the plant can be run in a in optimal way. The project has succeeded in describing a use case in the pulp and paper industry, namely, predicting the running speed of a paper machine and paper qualities adjusted to particular fibre characteristics.
Expected long term effects
The project has resulted in a project proposal and consortium for the next phase. The proposed project will aim to show how deep learning can be used to introduce a big leap for automation in process industry . This in turn will inspire the Swedish industry how big data analytics can enable a new phase in process optimization. The proposed approach will take advantage of the data already gathered in the process control system and use that to suggest the needed action to improve the desired KPI.
Approach and implementation
The project was implemented with the following activities: A1: Initialization. The project created consensus among all stakeholders. A2: Use-Case generation. The project built a case that can demonstrate the potential of deep learning in the process industry. A3: System view and end users. The project identified systems that will be included in the case and the role of the end user. A4: Overall suggestions. With a use case a proposal was defined that leads to the expected results, konsortiedeltagare, financing and scheduling. A5: The proposal for a "Spjutspetsprojekt".