From Historian to Intelligence Platform: Evolving PI System with Asset Framework

For many manufacturers, the historian began as a place to store time-series data. Process values, alarms, events and operational signals were captured to provide a record of what happened and when. That remains important. However, the organisations creating the most value from their industrial data today are moving beyond storage alone.

They are transforming the historian into an intelligence platform.

At the centre of that evolution is Asset Framework (AF). When implemented properly, AF changes a PI System from a repository of tags into a contextualised, scalable data environment that supports analytics, decision-making, AI initiatives and digital twin strategies.

For life sciences, pharmaceutical and manufacturing organisations, this shift can be the difference between having data available and having data that is truly usable.

The Traditional Role of a Historian

Industrial historians such as AVEVA PI have long played a critical role in operations. They collect and store high-frequency time-series data from PLCs, SCADA systems, DCS platforms and other sources across the plant.

This provides significant value in areas such as:

• Process trending
• Root cause investigations
• Compliance and traceability
• Performance monitoring
• Historical reporting

However, many legacy historian environments were built around tags rather than business context. While the data exists, users often need deep system knowledge to understand what tags relate to which asset, process or production line.

That is where the next stage of maturity begins.

What is Asset Framework?

Asset Framework is the contextual layer within the PI System that organises raw data into meaningful models aligned with real-world operations.

Rather than asking users to search through thousands of tags, AF structures information around assets such as:

• Production lines
• Reactors
• Filling machines
• Utilities systems
• Cleanrooms
• Pumps, motors and compressors

It can also model processes, sites, batches and hierarchies across the wider business.

This means users interact with data through equipment and process context rather than tag names.

That shift is transformational.

Moving Beyond Time-Series Storage

Time-series data on its own answers the question: what happened?

Contextualised data helps answer:

• Why did it happen?
• Where did it happen?
• Which asset was affected?
• How does this compare across lines or sites?
• What should happen next?

With Asset Framework, the PI System becomes more than a historian. It becomes a connected intelligence platform where data is organised, reusable and easier to analyse at scale.

This enables engineers, operations teams and leadership teams to move faster and make better decisions using trusted information.

How AF Enables Contextual Intelligence

The real strength of Asset Framework lies in standardisation and reusability.

Templates can be created for common asset types such as pumps, skids, packaging lines or utilities equipment. Once defined, those templates can be applied consistently across multiple assets and sites.

This creates several advantages:

Faster Deployment

New equipment can be onboarded quickly using existing templates.

Standard KPIs

Metrics such as OEE, uptime, energy use or cycle time can be applied consistently across operations.

Easier Comparison

Performance can be benchmarked across lines, plants or regions.

Better Visualisation

Dashboards and analytics tools can consume structured asset data rather than raw tags.

Stronger Governance

Naming conventions, calculations and metadata are controlled centrally.

This is what turns operational data into contextual intelligence.

Real-World Example: From Spreadsheet Reporting to Live Intelligence

Many facilities still rely on Excel-based reporting built from manually retrieved historian data. While workable in the early stages, this often becomes slow, resource-heavy and difficult to scale.

We regularly help clients evolve from this model by implementing Asset Framework structures and connecting them to modern reporting platforms.

For example, instead of manually compiling weekly reports from hundreds of tags, a production manager can access a live dashboard showing:

• OEE by line
• Downtime by cause
• Batch performance trends
• Utility consumption by area
• Alarm frequency by asset

The result is less time gathering data and more time improving performance.

The Foundation for AI

Artificial Intelligence is only as strong as the data environment beneath it.

AI models perform best when data is:

• Structured
• Consistent
• Contextualised
• Trusted
• Scalable

Asset Framework helps deliver exactly that.

Rather than feeding models disconnected tags and inconsistent naming conventions, AF provides a clean operational model linked to assets, processes and relationships. This improves model accuracy, speeds up deployment and makes insights easier to interpret.

For organisations exploring predictive maintenance, anomaly detection, process optimisation or generative AI, AF is often one of the most valuable existing assets they already own.

Enabling Digital Twins

Digital twins require a digital representation of physical assets, enriched with live and historical data.

Asset Framework provides the ideal foundation for this by modelling real-world equipment and connecting it to operational data streams.

This allows organisations to build digital twins that can:

• Monitor asset health
• Simulate scenarios
• Compare expected vs actual performance
• Support maintenance planning
• Improve operational decision-making

Without contextual models, digital twin projects often become overly complex. With AF, much of the required structure is already in place.

Why This Matters for Life Sciences

In regulated industries such as pharmaceuticals and life sciences, the value of contextualised data is even greater.

Teams need trusted information for:

• Batch investigations
• Continuous improvement
• Process monitoring
• Energy optimisation
• Cross-site standardisation
• Audit readiness

Asset Framework supports these goals while maintaining a scalable architecture that can grow with the business.

Common Signs It Is Time to Modernise Your PI System

Many organisations already have the foundations in place but are not using them fully. Common indicators include:

• Heavy reliance on Excel reporting
• Difficulty finding the right tags
• Inconsistent site structures
• Limited self-service analytics
• Slow reporting cycles
• Separate systems for similar KPIs
• AI ambitions without a clear data model

If any of these sound familiar, it may be time to evolve your PI System.

How Réalta Technologies Can Help

Réalta Technologies helps organisations move from basic historian environments to scalable intelligence platforms.

Our team supports clients with:

• PI System architecture reviews
• Asset Framework design and rollout
• Historian upgrades and migrations
• KPI and reporting layers
• AI readiness assessments
• Digital twin data foundations
• Global standardisation programmes

We combine deep technical expertise with practical experience in life sciences and manufacturing environments.

If you want to unlock more value from your PI System and build a stronger foundation for analytics, AI and digital transformation, speak with Réalta Technologies today.

📧 [email protected]

💻 https://realtatechnologies.com

📞 IRL: +353 21 243 9113 | US: +1 302 509 4401