On-going projects

ESTV

Anouar Belahcen and Alex Jung from Aalto University, Janne Keränen from VTT Technical Research Centre of Finland Ltd and Tatiana Minav from Tampere University have formed a consortium to develop modern AI-based methods for condition monitoring of electromechanical energy conversion systems, or powertrains. In order to ensure the safe and efficient functioning of these powertrains, it is important to predict their incipient faults at an early stage.

Impact

The project will produce synthetic augmented data to be used to train the AI algorithms. The algorithms will also combine data from different application domains, allowing for transfer learning. The results of the project are expected to produce new knowledge on how to optimally leverage AI algorithms for energy conversion systems.

Funding source

Academy of Finland

Contact person

Tatiana Minav
Assistant Professor (tenure track)
tatiana.minav@tuni.fi
+358 50 5940 496

Hydraulic hydrid working machines

The project studies energy efficiency of different hydraulic hybrid solutions. The objective is significant reduction in fuel consumption and emissions. The project is one of the Challenge Finland projects funded by Business Finland.

Impact

The results of the project show that the fuel consumption of working machines can be reduced up to 30 percent by  a simple and low-cost hydraulic hybrid solution. In practice, this means up to 10 000 litres savings per year in the medium sized working machine.

Funding source

Business Finland

Contact person

Matti Linjama
Principal investigator
matti.linjama@tuni.fi
+358 40 8490 525

Edge Analytics for Smart Diagnostics in Digital Machinery Concept (EDGE)

The overall objective of this research is to develop technical solutions to provide edge analytics for providing autonomous devices and components with high reliability and availability. The technical methods consist of algorithms for processing raw data, requirements for edge processing elements and support by cloud and operator infrastructure. The edge analytics provides predictability, and hence possibilities for operational optimization, diagnostics and predictive maintenance.

Research consortium: Tampere University (TAU), Åbo Akademi University (ÅAU), University of Vaasa (UVA)

Planned duration of project: 9/2018 –10/2020

Impact

We have set high expectations for the outcome of this project while discussions with industry partners we are convinced how important research area we are dealing with. We see that same issues raise in different applications in the industry due to rapid digitalisation effect. Therefore, our aim is that the results of this research will be generic as possible so that those can applied to a wide range of machine systems and within other fields. We have defined the following vision of the impacts:

  • Machinery compatible with autonomous systems → increased safety (10x), i.e. 40 M€ less cost of accidents in Finland
  • Emission reductions through optimized operating points → up to 30% increased engine efficiency, i.e. -30% CO2 emissions
  • Optimised maintenance, on-ship/on-site automation
  • Reduced data transfer requirements
  • Reduced downtime
  • Reduction of total costs up to -50% (e.g. safety, zero downtime, data transfer, optimized maintenance)
  • Technological readiness to create new data based services
  • New SMEs in data analytics (+100…300 persons)
  • Increased competitive edge for organizations
  • State-of-the-art research information about methods for edge analytics

Funding source

Business Finland and companies

Contact person

Kalevi Huhtala
kalevi.huhtala@tuni.fi
+358 40 849 0512

 

Novel Predictive Analytics Technologies for Future Maintenance Business (OPENS)

The main objective of this research is to study and develop methods for predictive analytics using massive data stores (Big Data) of sensor, usage and also maintenance data of machine systems. Our aim is to integrate, analyse and enrich this data to get access to information which can be utilised in predictive decision making. Doing this way, we can access to the future health status of the analysed equipment and we can move from the health estimation to the predictive health estimation. The developed methods will then provide information and input for the processes of the organizations.

Research consortium: Tampere University of Technology (TUT), Åbo Akademi (ÅA).

Duration of project: 1.9.2016 – 31.12.2019

Impact

Significant impacts are expected when the future behaviour of systems are estimated beforehand. This research project will create added value from Big Data and develop new intelligent and efficient analysis methods to enable new digital business solutions and services. It is also our aim that the results of this research will be generic as possible so that those can applied to a wide range of machine systems and also within other fields. The following impacts are expected from this research project:

  • State-of-the-art research information about methods for predictive analytics, and usage of various data sources in predictive analytics
  • State-of-the art methods and insights in automated maintenance feature extraction from data sources
  • New business possibilities
  • Technological readiness to create new data based services
  • Optimization of service actions, early warnings
  • Avoid unnecessary technician callouts, remote monitoring
  • Increased competitive edge for organizations
  • Proactive planning of processes of organizations
  • Improved reliability and availability of machine systems
  • Lengthened life cycle of machine systems

Funding source

Business Finland and companies

Contact person

Kalevi Huhtala
kalevi.huhtala@tuni.fi
+358 40 849 0512