Reference

Valmet uses analytics and expands it service offering

Valmet Corporation serves the pulp, paper and energy industries and is known as the global leader in its field. It delivers technology, automation and services to manufacturing companies. Valmet is a frontrunner in big data, analytics and industrial internet investment. It wants to offer its customers increasingly extensive advisory services, to improve the servicing of paper machines and to understand which factors influence the life cycle of the most valuable machine parts. Together with Teradata and Houston Analytics, Valmet is now collecting data from sensors in its customer’s production paper machine. 

Its services are comprehensive, covering everything from maintenance outsourcing to mill and power plant upgrades and spares. Pulp mills, tissue, board and paper manufacturing lines and bioenergy power plants form the core of Valmet’s strong technology offering. In 2014, Valmet’s revenue was approximately 2.5 billion euros and it employed some 12,000 people globally. In accordance with its vision, the company’s goal is to be the best in the world in serving its customers.

”More and more of our customers want to buy demanding servicing and maintenance services from the original equipment manufacturer, which would be us. There is also growing demand for long-term contracts in paper machine wear and spare parts supply. Paper machines are very complicated and have a large number of very expensive parts that wear in production use. We wanted to develop a model that would allow us to identify the factors that influence their life cycles and the optimisation of production use,” says Pekka Linnonmaa, Director, Paper Technology, EMEA, at Valmet.

Valuable data from hundreds of sensors

In autumn 2014 Valmet acquired an industrial internet platform from Teradata, to which Houston Analytics integrated an IBM SPSS Modeler solution. Houston Analytics’ specialists took part in the Proof of Concept (PoC) project as experts in advanced analytics to analyse the customer’s needs, available data and desired outcome.

“We collected data from the most valuable wear parts of the paper machine so that we could understand what influences lifespans. The Proof of Concept was carried out in our customer’s production environment in 2014 and the first customer service report based on the data from the sensors was delivered at the beginning of April 2015. We needed analytics expertise and decided on Houston Analytics,” explains Linnonmaa. “The development team also needed the paper machine expertise of Valmet’s professionals. Houston offered us an agile service model and the project made rapid progress.”

Houston Analytics supplied Valmet with IBM SPSS Modeler Professional work station applications and the IBM SPSS Modeler Server and IBM SPSS Collaboration and Deployment Server software.

“We analysed the need, available data and desired outcome using our agile service model,” says Juha Raunama from Houston Analytics.“Our job was to help them to forecast paper machines’ servicing needs more efficiently and to help optimise production. In collaboration, we created an automated predictive analytics solution for business operations.”

Data was collected from 6,500 sensors on the Valmet customer’s paper machine.”We use reports based on advanced analytics to develop a life cycle model. With the data from the sensors we can reduce the risk of unscheduled shutdowns,” says Linnonmaa.

New development and business opportunities in 2016

Valmet has attained significant results in a very short time.

“Thanks to the headway we have made with the development of the lifecycle model of the roll covering, our customer has been able to extend the servicing interval from five to six weeks. This means substantial direct savings for each roll covering. A single paper machine has from two to ten roll coverings. Production reliability also improves. We can offer our customers more comprehensive advisory services,” says Linnonmaa.

“Our co-operation with Houston Analytics is based on an agile co-operation model under which they provide us with their advanced expertise in data. They have also provided us with significant added value in improving the efficiency of an industrial process machine though collaboration with our experts. The IBM SPSS Modeler solution generates new forecasts every day and the modelling is increasingly accurate. We have now modelled two thirds of the wear parts of the paper machine and will reach 100 per cent by the end of 2015,” Linnonmaa says.”We will continue the business-based integration of data sources in 2016 and launch Proof of Concepts that deal with predictive services business.”

Houston Analytics offers expertise and further analyses for a variety of needs and the maintenance of life cycle models and their further development. “We are at our customer’s disposal also with regard to enhancement of the production use of new paper machines with a different structure,” Raunama says.