Self-predicting and inter-communicating electric drives for industrial process optimisation
| Reference number | |
| Coordinator | Kungliga Tekniska Högskolan - DEPARTMENT OF NETWORK AND SYSTEMS ENGINEERING |
| Funding from Vinnova | SEK 2 917 800 |
| Project duration | September 2018 - August 2021 |
| Status | Completed |
| Venture | The strategic innovation programme Electronic Components and Systems: |
Purpose and goal
The objective of the project was to create a proof of concept of a new way of achieving industrial process reliability, flexibility and optimization through smart electric drives forming an edge cloud. The project successfully demonstrated most of the key elements of this concept, completing a testbed for high-frequency sampling based status monitoring, a wireless communication infrastructure for real-time data collection, and ML based fault detection and health prediction.
Expected results and effects
The results of the project demonstrate the potential of the vision of collaborating smart electric drives, supported by advanced networking and data science approaches. Considering the contribution of the industrial partners, the project demonstrated that novel wireless mesh technology can bring the benefits of replacing wires and still obtain reliability even in harsh industrial environments. We have also shown that machine learning techniques could be used as a tool in predictive maintenance with the promise to apply the same principles to different machinery.
Planned approach and implementation
The project was formed by KTH, ABB Corporate research, Imagimob, LumenRadio and Ericsson, with expertise in electric machines at KTH and ABB, machine learning and embedded AI at Imagimob, and wireless communication and networking at KTH, LumenRadio and Ericsson. The partners were very well suited for the project and benefited from the interdisciplinary objectives. The project required extensive experimental work, which was unfortunately hindered by the ongoing pandemics.