Swedish forest industry cooperative Södra has signed a framework agreement with AI company Viking Analytics to deploy the MultiViz vibration analytics platform across its three pulp mills in Värö, Mörrum, and Mönsterås. The agreement covers 3,650 sensors in total.
The decision follows several years of use at Södra’s Värö mill, where the platform reduced weekly maintenance alarms from approximately 500 to 20. Södra reports that the deployment has also lowered spare parts costs and improved plant uptime, with total annual savings at the Värö site now exceeding several million Swedish kronor.
“Vibration data has been available at our facilities for many years, but we have lacked tools to handle the large volumes of data generated by modern monitoring systems. For us, the value is not only in detecting faults earlier; it is in creating impact across the entire organization — increased plant uptime, lower spare parts costs, and more efficient analysis and maintenance operations. We see Viking’s technology enabling exactly that, allowing us to work more proactively and achieve significant annual savings.”
Thomas Håkansson, Head of Technology, Södra Cell
What the technology does
Pulp mills operate large numbers of rotating machines, e.g. pumps, fans, conveyors, and similar equipment. These machines are fitted with vibration sensors that continuously generate data. Traditional monitoring systems trigger alerts when readings cross a fixed threshold, which can produce a high volume of false alarms when normal process conditions fluctuate.
MultiViz takes a different approach. The platform builds a model of how each machine typically behaves under different operating conditions. It then monitors for deviations from that established pattern, flagging potential faults before they develop into failures. Normal process variation is filtered out automatically, which reduces false positives and allows maintenance teams to focus on genuine issues.
“What makes Södra Värö particularly interesting is that these results come not from a pilot project or an isolated deployment, but from day-to-day operations in one of Sweden’s most advanced industrial facilities. By reducing weekly alarms from 500 to 20, data engineers and maintenance teams have been able to focus on the right problems instead of managing noise. The results clearly demonstrate that when behavior-based AI is used to prioritize the right actions, the impact can be measured in increased uptime, lower costs, and greater organizational efficiency. Södra’s decision to scale the solution across the entire group is a strong validation of the technology’s robustness, stability, and business value.”
Stefan Lagerkvist, COO and Co-Founder, Viking Analytics
Why it matters for sustainability
Södra processes wood from member-owned forests into pulp, timber, and biochemicals — materials positioned as renewable alternatives to fossil-based products. Continuous production uptime is central to the efficiency of that supply chain. Unplanned equipment failures result in production stops, wasted raw material, and higher energy consumption per unit of output. Earlier fault detection reduces the frequency and severity of such interruptions, supporting more efficient use of resources across the mills.
Södra is owned by more than 50,000 family forest owners and has stated commitments to sustainable forest management and low-carbon industrial operations. Under the framework agreement, Södra will progressively roll out MultiViz across all three mills.
Viking Analytics is a Swedish company whose platform is also used by ABB, Weir Mining, CEMEX, and Audi.
