Skip to content

Transforming the pulp & paper industry through systematic data management

Papermaking gets smarter with applications like soft sensors that leverage robust data strategies and machine-based learning to reduce waste and improve operational effectiveness.

Today, Industry 4.0 technologies are transforming the pulp and paper industry, empowering manufacturers to achieve unprecedented levels of efficiency and output. In my three decades of working in the pulp and paper industry, I have seen an increasing number of firms that are dedicating a chunk of their revenue for developing smarter technologies to stay one step ahead of changing consumer behaviors through increased accuracy.

According to a recent McKinsey & Co study, digitalization, automation and AI have the potential to deliver additional global economic activity of around U$13 trillion by 2030. This change, I believe, will largely be fueled by data that forms the core of sustainable, robust results.

But, in my opinion, data is almost irrelevant unless it is collected and validated in a systematic manner. This makes data collection and conditioning often deemed as a time-consuming task, however vital for extracting valuable insights with minimal deviations. To make data indispensable we should take an approach towards data acquisition and cleansing that leverages industry expertise and ensures that our advanced data-driven applications are accurate and useful in optimizing the production process with a significant reduction in wastage and carbon emissions.

But how do we achieve this level of accuracy in collecting and cleansing data?

Driving smart papermaking

The success of smart papermaking depends on the implementation of a solid strategy. Our team of experts at ABB has come up with a multi-step approach, which systematically combines industry 4.0 technologies, data analysis and process expertise, to help our customers deploy reliable and sustainable tools that will mitigate the risk of performance degradation.

This also reduces production costs by lowering raw material usage while increasing throughputs by improving equipment reliability and improving quality by stabilizing processes and automation performance.


The following six steps are crucial in optimizing smart papermaking:
  1. Data acquisition and harmonization: Key considerations include identifying variables of interest across a wide variety of data sources, contextualizing in regards to functions in process and overall operation, time synchronization (at the system level if possible), ensuring data across sources is consistent and closet to its ‘raw’ form, and finding a balance between data frequency and storage limits.
  2. Data preparation and validation: It’s not unusual to get invalid data hence cleansing, filtering, sorting and validating becomes even more important and a crucial component for further modelling.
  3. Offline data utilization: Often the insights derived from the collected data are presented through the creation of models, such as soft sensors, that are based on machine learning and produce inferred calculations of physical measurements.
  4. Online implementation of data-driven solutions: Integrating the soft sensors with control systems is crucial for ensuring a seamless operation. The integration is usually done via application programming interfaces (APIs), which provide connectivity, for various data-driven solutions allowing data to flow seamlessly through control systems from the soft sensors.
  5. Operational integration and training: A people-focused and inclusive implementation approach is fundamental to ensure operational integration by taking inputs from all the stakelholders of the production process from opeartors, engineers to field officers.
  6. Collaborative monitoring and continuous enhancement: Finally, a digital strategy should look beyond the technicalities of the production process while enabling a scope for collaborative monitoring and continuous improvement that ensure its long-term use to its users.

The steps enumerated above together ensure the lifecycle of digitalization solutions while generating huge benefits for our pulp and paper customers who are looking to not only optimize smart papermaking but also improve their environmental footprint.

Implementing data strategy for online soft-sensor applications

To illustrate the idea of how the six-step approach can bring real value to mills, let’s delve deeper into the functionalities of soft sensors which primarily take offline data in the absence of a physical sensor to estimate a process variable or product quality measurement.

Building soft sensor models requires a significant investment in time and effort before they can be used online in the manufacturing process. Historical process and product quality data – the foundational inputs for soft sensor development – are usually stored in different databases. To create soft sensors, various exporting tools and techniques (examined in steps 1 and 2) are needed to extract and synchronize this data. Step 3 is the physical creation of the model using the insightful information extracted from the data. Step 4 helps make the most of these applications by establishing APIs that provide connectivity for integration and data handling, making the measurement output from the soft sensor available in the control system for monitoring.

All the above activities including data collection, validation, model building and soft sensor development becomes a futile exercise unless the gains obtained from it are sustained. Which is why our soft sensor applications also include engendering a people-focused and inclusive implementation approach. Operators, engineers and supervisors all have valuable insight into their process and therefore their inputs on the areas of improvement should be brought to the table. For example, insights from process operators have been used in our Virtual Measurement user interfaces and displays to ensure they are informative and intuitive.

Finally, continuous monitoring and enhancement ensures the viability and continued use of such applications by mill personnel, which is why we deliver ours as a connected service. I believe this approach to soft sensors can make a huge difference in delivering long-term value for mills and can be applied to anything from strength and weight to kappa and more.

Going forward

I believe for a better tomorrow, digitalization will be the force behind creating a sustainable, environmental-friendly world. Such an atmosphere will not only help us make smart business choices but also positively impact the lives of communities around the world.

John Schroeder
Global Product Manager