BENEFITS OF ARTIFICAL INTELLIGENCE WORLD PULP&PAPER 98 to provide a comprehensive digital service for the mill of the future. It incorporates Solenis’ customer- and quality-first philosophy, which means it can accommodate every mill’s unique processes. Using process data, physical paper measurements of the critical quality parameters and papermaking process knowledge, Solenis applies robust data science techniques to turn complex, multidimensional relationships into an accurate, real-time, adaptive “soft sensor.” Unlike other data analytic tools, OPTIX does not require data interpretation and simply provides an actionable solution. The resulting real-time predictive and prescriptive analytics enable a step change improvement in mill optimisation not previously feasible. HOW OPTIX WORKS Solenis carefully evaluates mill process data using sophisticated data collection, cleaning and mining techniques. Advanced data mining practices, such as multiple regression and causal networks, reveal multidimensional relationships between the response and predictors that are not easily identified any other way. Figure 2 illustrates the relationships comprehensible by the human mind compared to the complex relationships that actually exist and can be identified using OPTIX. Solenis employs a proprietary screening methodology that allows OPTIX to focus on the most important tags needed to drive the machine-learning, predictive platform. The predictive model provides a real-time, mathematically driven measurement for paper quality metrics that cannot be delivered using any other method. The traditional method of laboratory testing key quality parameters only provides a quality measurement every reel turn-up or less frequently. As Figure 3 shows, real-time predictions from OPTIX provide high-frequency data every 15 to 30 seconds. For the first time, papermakers can have a real-time, machine-direction quality profile for the entire length of the reel. Because of the ever-changing environment of the papermaking process, it is crucial to continually update predictive analytics platforms. Predictive models incorporating machine learning adapt to changes in the process by learning from observations and interactions. This information drives shifts in the predictive model aimed at maintaining prediction accuracy. This level of machine learning is built into the platform, which is why OPTIX measurements remain robust and accurate in the face of changing machine conditions. Figure 4 shows how a static predictive model For the first time, papermakers can have a real-time, machine- direction quality profile for the entire length of the reel. Figure 3. Prediction trend: Green points indicate predictions, the grey band defines the prediction confidence interval, and black points indicate actual lab values.