Examples of customer references
Simulation model estimates the added value of services
Customer: Metso Automation
Challenge: Understanding and communicating the value of provided maintenance services to the client.
Solution: System dynamic model for estimating the added value of maintenance services, and acting as a communication tool between Metso and its customers.
understanding of customer’s business and added value of services.
of different kind of industrial services and their added value.
of robust policies by locating critical areas of service systems.
pricing and value propositions.
LEO: Lifecycle Efficiency Online
Challenge: Working machines containing hydraulic components operate at various environmental conditions from light to heavy use, which makes it difficult to predict the lifetime of these components. A reliable method is needed to monitor the condition of these components in order to better estimate the need for maintenance and the time to failure.
VTT developed an IoT and data analytics system for hydraulic component condition based maintenance (CBM).
Pulp and paper
Process operation improvement
Customer: Metsä Fibre
Challenge:40% increase in cooking kappa
number variation, extra cost in bleaching and
increased production losses
Solution: Applying data analysis, defective
equipment were found
Customer testimony: "Even without including wood raw material, decrease in production loss or increase in energy savings, the payback period of the problem solving project may only be a matter of days."
Pulp quality and tracking
Customer: Metsä Fibre
Challenge: Quality information from pulp is based on few samples and results are available after several days from sampling.
Solution: Development of real-time pulp quality control method. The core computational model was developed by VTT combining the theoretical domain knowledge, customer feedback and data mining.
Analytics in Steel Industry
Customer: SSAB, Outokumpu
Challenge: Discovery of product quality deviations early enough in strip hot rolling. Number or process variables difficult to monitor in real-time and lack of performance figures.
Customised model based online quality monitoring system that provides detailed product quality information in real-time. Tool utilises mathematical models predicting the upcoming quality and finding the root-cause for lower product quality. Tool visualises hundreds of process inputs into descriptive interactive user interface.
Arctic Thruster Ecosystem (ArTEco)
Partners: Wärtsilä, ATA Gears, Klingelnberg Group, SKF, Katsa, Technische Universitat Dresden, Luleå University of Technology, Tampere University of technology, Finnish Transport Safety Agency (Trafi)
Understanding of the thrusters operating in ice and the phenomena causing ice loads. Understanding how the loads are transferred to critical components like gears and bearings
1. Software tool to predict ice loads on thrusters and propellers.
2 Concept creation and validation for reduced loads.
3. Simulations of various thruster installations & loads.
4. New sensing, data transmission options for smart gear concept