Data management: the formula for pulp and paper analytics success

Process Optimization
Typography
  • Smaller Small Medium Big Bigger
  • Default Helvetica Segoe Georgia Times

Effective data management requires having a strategy and reliable methods to access, integrate, cleanse, govern, store and model - to prepare data for analytics so that it adds value.

The promises of the digitalization revolution are significant: as a 2019 McKinsey report estimates, digital technologies could offer pulp and paper producers a 15% reduction in total cost and provide a five percentage point improvement in overall equipment effectiveness.

While the industry is certainly embracing digitalization - particularly in terms of an enhanced ability to collect data - knowing how best to utilize it is key. Data management and data analytics cannot be designed and executed independently from each other. Pulp and paper manufacturers need to extend corporate data management and data governance from enterprise level systems through to manufacturing operations management and automation systems - as the foundation of their digital success.

Using data effectively

abb 10nov20 2Simply having data is not the same as understanding how to utilize it effectively.

While most mills use some sort of process data management system, simply having data is not the same as understanding how to utilize it effectively. IBM Research estimates that up to 88% of Industrial Internet of Things (IIoT) data goes unused; The Economist suggests that 99% of the value of manufacturing data is lost, with only 3% tagged and analyzed. Other pitfalls include legacy systems that are inaccessible or not digitalized; not labeling data logically across the enterprise; a lack of real-time data; and the failure to communicate data-derived conclusions effectively.

The first steps of any digitalization journey are therefore understanding the foundations of process data management and managing the collected data so that it adds value. The ultimate goal must be to create a fully integrated digital infrastructure that allows asset and operational data to be accessed, visualized and analyzed for improved performance.

Where to start?

abb 10nov20 3Bringing structure, standardization to data, which may have been collected (and unused) for decades, ensures the integrity and consistency of data models.

A good place to start is by ensuring that your data strategy is closely aligned to your business strategy. It is encouraging to see that our customers are increasingly recognizing the value of a holistic view of their data assets throughout the business, but this is by no means yet the industry norm.

Traditionally, process data has been stored as an extension to automation systems at a production line level. In many cases, there has also been no harmonization over production lines in technology and naming conventions. This has resulted in fragmented, unstructured data that makes it difficult to do anything on an application level or across multiple production lines. Meanwhile, the flat structures in many process information systems (PIMS) don’t make life any easier when integrating to site and enterprise level.

Bringing structure and standardization to data, which may have been collected (and unused) for decades, is a vital step in transforming data into something of significant business importance. One example could be ensuring data tags are tied to a specific production phase or piece of equipment in a standard way. These can then be grouped together into units that align with a particular strategic business or process function – e.g. all data that is needed to analyze the equipment health of electric drives.  We also spend a lot of time ensuring the integrity and consistency of our data models. This is vital work, as the models are then used throughout the customer organization to harmonize the data and interface, and as the basis for providing useable insights for smarter decision making.

The aim here is to extend corporate data management and data governance from ISA-95 level 4 enterprise level systems, right through to Level 3 manufacturing operations management and Level 2 automation systems.

The benefits of good data management

abb 10nov20 4Without a comprehensive and consistent approach to data management, there can be no comprehensive and consistent approach to data security, leaving valuable assets vulnerable to attack.

All good so far, but how does effective process data management contribute in practice to the improvement of a pulp and paper manufacturer’s operations? This is the key question and comes in three different areas:

  1. Improved productivity: Properly stored and labeled data allows mills to take advantage of advanced digitalization solutions, such as advanced process control (APC). Our ABB Ability™ APC applications, such as the recently launched Wet End Control, leverage data to build predictive models and implement control strategies that stabilize and improve process conditions in a cost-efficient way. The benefits include reduced energy consumption and optimized raw material use.
  2. Smarter decision making: Visualization of performance against KPIs at an equipment, site, and company-wide level ensures broad situational awareness that supports effective decision making throughout an organization. But visualization is only possible through the effective management of data from a range of different sources.
  3. Enhanced data security: Without a comprehensive and consistent approach to data management, there can be no comprehensive and consistent approach to data security, leaving valuable assets vulnerable to attack. Strong data management structures that work at all levels of the business are required as the basis for the advanced data governance and security that is required in today’s interconnected industrial environment.

Selecting an expert guide …

abb 10nov20 5 The lack of domain expertise leads to impractical solutions built on data that isn’t understood, managed or leveraged properly

The importance of process data management makes the choice not only of platform, but also of implementation partner vital, and businesses must be able to answer some key questions confidently.

First and foremost, does a potential partner have the right combination of domain-specific expertise and knowledge of both IT and OT infrastructure to ensure their solutions offer real value? A partner with deep industry experience, will - at a minimum - save you a lot of time (for example, by being able to adapt ‘off-the-shelf’ systems rather than custom build from scratch), and can quite easily be the difference between a solution that works and one that is unusable.

Another question to ask is whether a potential partner appreciates the challenges of collecting data in the real-world conditions of a mill. Do they recognize the need for robust and reliable sensors that can withstand the rough-and-tumble of the mill environment? Do they understand how to integrate the different legacy systems common in brownfield sites - often systems that were typically not designed to support modern, open, or standard connectivity protocols - with the process data management platform?

We’ve found decades of experience in the industry not only provides knowledge of a customers’ business and operations but when combined with vertical expertise - from sensors to automation to IT systems - it enables the collection, analysis, management and deployment of data-driven models and insights that create value specifically for pulp and paper. Otherwise, the lack of domain expertise leads to impractical solutions built on data that isn’t understood, managed or leveraged properly.

… and the right platform

abb 10nov20 6When the same data structure and data models are shared across data levels (control system, site and enterprise), transfer between levels is straightforward, secure and controllable to the finest degree.

Turning to the process data management platform itself, it is important that this should be secure, high-performance, scalable and able to integrate third-party applications that can bring additional functionality to your digital environment. With established players and start-ups all competing for a piece of the pie, it is important to avoid being locked into a limited digital ecosystem that will prevent you from leveraging the full range of solutions.

Ideally, it should be possible to set up your selected process data management platform hierarchically, i.e. at a control system, site and enterprise level. This means the same data structure and data models are shared across data levels, ensuring transfer between levels is straightforward, secure and controllable to the finest degree. This saves significantly on time and implementation costs as the platform expands: for example, if you have to move applications between levels, you don’t need to re-write the interface as it is already harmonized. The right platform should also support a range of open interfaces and application programming interfaces (APIs) for streaming and pulling data, including REST API, .Net SDK, ODATA, ODBC, OPC UA, OPC DA, making the data available to use as new use cases emerge on your digital journey.

Data streaming - both between levels, and to and from the Cloud - should be available in real time and in both directions in order to maximize the advantages of digitalization: if an application calculates the optimal set values for a process, it must be able to communicate those values to the process or there is no benefit! When using the Cloud, it is also important to consider the cost efficiency not only of the data storage but also the cost of data transfer, which can be expensive as data is constantly being transferred back and forth.

Of course, in any process data management platform, strong data modelling features should be present, allowing data to be used and harmonized throughout your organization. For example, an ABB customer wishing to transfer a sensor application between two mills found that they had measured values for the sensors they were following in one mill but lacked set values for the other mill, resulting in no targets for their process data algorithms to optimize. This is where robust data modelling comes in, enabling you to implement process data powered applications on multiple sites to maximize benefits.

Only by considering all the above can a business create a cost-efficient architecture upon which to build their digital future and applications.

Conclusion

How well a company manages its digitalization journey will determine its future. It is therefore vital to ensure that the fuel for that journey - the vast amounts of data that are now available through the IIoT - is as strategically managed as possible. A process data management system from a partner with deep sector knowledge, such as ABB, is key to this. This partner will help navigate the challenging digital road with the goal of interpreting the wealth of data with a pulp and paper leans to maximize the business value delivered, and providing the trust businesses need to act on the analysis and insights that is unlocks.


CASE STUDY

Process Data Management - first step to help cut costs for Kotkamills OY

abb 10nov20 7

When Kotkamills Oy wanted to implement ABB Ability™ Manufacturing Execution System to ensure a smooth order-production-delivery process, the first module they needed to implement was ABB’s Process Data Management. This was to help increase the integrability of the individual systems on site after Kotkamills was acquired by a private company. “System integration has not only brought us new technology but also enabled us to build a system that matches our needs perfectly,” said Petri Hirvonen, CFO of Kotkamills Oy. The single integrated system has produced savings in both the cost of managing the order-production-delivery process and the cost of maintaining the hardware and updates. “We have realized considerable savings in our system costs,” said Hirvonen.


Source: ABB