The company prides itself on its large-scale, modern facilities that primarily produce softwood and hardwood pulp. In addition, they generate green energy based on biomass and operate one of the largest softwood lumber mills. 

Sustainability and self-sufficiency act as key driving factors for this organisation. Material production is carried through the generation of electrical and thermal energy from biomass by-products which are created from the in-house process of pulping and sawmilling, resulting in overall waste reduction and maximization of forest resources. 

In 2018, the product specialists were facing cultural and technical disruption when their automated machine health diagnostics provider discontinued their service and use of the system which lead them to begin their search for a new provider. 

When searching for a new platform, they were looking for a robust solution that could efficiently process and manage large volumes of data, enhance machine learning, forecast failures whilst automatically monitoring equipment performance.    

Traditionally, the pulp and paper market has been self-sufficient from the power produced with sold on the market. However, issues regarding machine health and unplanned downtime proved to be diffcult to prevent and predict despite maximum self-sufficiency.  

When searching for a new provider, first class Artificial Intelligence (AI), system integration and maximization of planned downtime were significant factors when choosing a new provider. They were looking for a system with the right cultural fit that also that aligned with their goals.

After considering various factors, such as market influences, in 2018, they partnered with Siemens to deploy Senseye Predictive Maintenance to seamlessly integrate the platform with their new CMS system and replace their previous automatic diagnostic software.

The partnership was a result of three pilot runs that were primarily based on a combination of structured and unstructured learnings. Senseye Predictive Maintenance allowed the client to monitor multiple sets of equipment and provide individual reporting across each machine, which meant performance could be tracked and compared along with predicting potential breakdown and failures.