AI optimization of the running of sewage pumpstations
| Reference number | |
| Coordinator | Kungälvs kommun - VA teknik |
| Funding from Vinnova | SEK 500 000 |
| Project duration | April 2020 - December 2020 |
| Status | Completed |
| Venture | AI - Competence, ability and application |
| Call | Start your AI-journey! For public organizations |
Important results from the project
The project has created a digital twin over the eight of Kungälv´s pumping stations that are closest to the treatment plant. The twin is a hybrid of AI and physical modeling and was used to create a forecast for future sewage flows and to reduce the risk of overflow through optimized pump control. Input to the model is data from the pumping stations and precipitation information. The project result shows that it is possible to build an AI model over the wastewater network and use it to optimize the pump control for reduced overflow.
Expected long term effects
The project result shows that it is possible to build an AI model over the wastewater network and use it to optimize the pump control for reduced overflow.
Approach and implementation
The municipality of Kungälv has investigated the possibilities of using AI to reduce the flooding in its wastewater network. For this, the consulting companies SWECO and Calejo were hired to gain expertise in VA modeling and AI optimization.