Achieve Better Operational Storytelling with a Connected Factory 

By connecting IT and OT systems, manufacturers put time-series data into context. 

Extracting insights from time-series data has been the foundation of advanced industrial analytics, but it only tells part of the story. To understand production performance within its operational context, time-series data must be viewed along with data from other business applications. 

Data from various business applications helps explain events that occur during the manufacturing process. It also provides better awareness of the manufacturing environment. However, data from business applications has been historically stored and managed separately. While Operational Technology (OT) teams have overseen the systems that produce time-series data, the Information Technology (IT) teams have controlled the applications that produce contextual data. 

This has created an IT/OT Gap in the manufacturing industry, which also has led to an IT/OT Convergence. In more recent business models, all of the datasets are managed by a unified team. Closing the IT/OT Gap breaks down data silos and democratizes data for further analysis. It also is an important step in a company’s Digitalization Journey. But closing this gap does not connect the systems. 

During the Connected Factory phase, companies integrate time-series and contextual data sources so that they can be viewed as a unified dataset. Unlocking these data silos provides a more holistic view of operational performance and it helps engineers make better decisions. 

Contextual Data Events 

Events in operations have a specific start and end date and time. With the help of an advanced industrial analytics platform such as TrendMiner, these timestamped events can be viewed by themselves to create situational awareness of what is happening on the factory floor. They also can be used to provide additional details to time-series data and provide a full overview of production. 

As raw materials are transformed into finished products, each piece of contextual data represents a factor that could affect product quality. Performance of manufacturing processes and their corresponding assets directly affect product quality, and each of these performance behaviors can be affected by additional factors both inside and outside the plant. These include: 

  • A request for an additional run, 
  • Sudden changes in temperature, 
  • Performance at another site, 
  • The grade of a vendor’s materials, 
  • The design and configuration of the process, 
  • An unexpected shutdown, 
  • A planned shutdown, and 
  • Maintenance events.  

Contextual Data in Use 

The insights found in contextual data help engineers perform a cleaner analysis, but they can also be used to better understand operations. For example, in a Connected Factory, engineers can find out how often events occurred and how long they lasted. They can search through them for similarities, or to find a specific event parameter. Engineers also can use contextual data to quantify the outcome of an event, such as how much energy or time was lost as a result of it. 

As companies grow in analytics maturity, they also want to address more advanced use cases. These complex use cases could include energy management, Overall Equipment Efficiency (OEE), shift-based reporting, and non-linear soft sensors, among many others. 

By applying contextual data to analysis, engineers also gain more control over their production environment. They can use the information to: 

  • Set a predictive maintenance schedule,  
  • Determine an ideal batch profile, 
  • Identify relationships between variables, and 
  • Provide training data for a machine learning exercise. 

Connecting Across Global Sites 

Most manufacturers still store sensor-generated data in an on-premises historian. However, many have also turned to the industrial cloud to store data from business applications. The industrial cloud allows manufacturers to scale complementary solutions—such as TrendMiner—to a global, remote workforce. 

In fact, Gartner predicts that more than 50% of manufacturers will use industrial cloud platforms to accelerate their business initiatives by 2027. The industrial cloud includes both data lakes for contextual data and modern historians. The shift from on-premises to cloud-based storage is also indicative of an increasing reliance on technology to make data more accessible. 

Bridging the Organziational Gap 

When companies begin connecting systems, they are not necessarily integrating apples with apples. There are few technical similarities between Information Technology and Operational Technolgoy systems. Connecting them can be more cumbersome than it first appears. As a result, manfuacturers that have connected their systems soon find themselves at the Organizational Gap. 

In the next phase of the journey, manufacturers will find ways to overcome these organizational challenges as they bridge another gap in pursuit of a fully Augmented Factory. 

From our Blog

The Organizational Gap

Bridging the Organizational Gap in Pursuit of an Augmented Factory

By closing the Organizational Gap, manufacturers can do more to improve operations with machine learning models and AI-powered systems.

Achieve Better Operational Storytelling with a Connected Factory

A Connected Factory unlocks data silos and provides a more holistic view of operations to help engineers make better decisions.
The smart factory with the help of IT OT Convergence

Navigating the IT/OT Convergence in Pursuit of a Smart Factory

The IT/OT convergence facilitates a more innovative, efficient, and adaptable manufacturing environment in a digital transformation.