Machines and equipment in the manufacturing industry and power systems are usually maintained on specific time intervals or in a reactive way after they have been damaged. This lead to decreased life length of equipment and production stops. New methods utilizing machine learning allows moving towards a proactive approach, maintaining the equipment when needed the most. This would lead to more streamlined systems, longer lasting equipment and increased energy efficiency - working towards Sustainable Development Goals 7 (Affordable and clean energy) and 9 (Industry, innovation and infrastructure).
The Chalmers based startup Eneryield has developed new methods based on state-of-the-art machine learning, which could be used to have a proactive approach to maintenance.
Scope of the thesis
Eneryield’s technology is based on several years of research, and ready to be tested in a real setting. However, there is a need to further investigate the market landscape. Hence, more market verification needs to be conducted.
Perform a thorough analysis of the predictive maintenance market.
- Map out current actors and the methods they use
- Investigate the customers and their needs
- Suggest a potential business model
The candidate is currently studying Industrial Engineering and Management or Business administration. Moreover, the candidate is interested in working with new technology together with a brand new startup, and from that provide real value for the climate and society at large.
Please send a short motivation and your CV to email@example.com before 2019-12-15. If you have questions about the thesis, don’t hesitate to contact Johan Rådemar on +46703240310.
About the team
Eneryield is an early-stage startup developing methods for intelligent energy analytics based on machine learning. We are three business developers and two researchers and the company started as an innovation project at Chalmers School of Entrepreneurship.