Visplore 2.1 brings a powerful set of new capabilities centered around three themes: seamless integration, smart standardized analysis, and deeper data access.
Here is a brief overview of these new capabilities:
Visplore 2.1 introduces the ability to load multiple independent time intervals from data sources such as PI, SQL, iba, and others, all in a single workflow. This means you can now pull high-resolution data for specific events scattered across months or years of history, without the prohibitive cost of loading an entire time range at full resolution.
This unlocks powerful new workflows for root cause analysis of recurring faults and for tracking drift across repeated operations or process cycles. The way intervals are defined is fully flexible:
Whether you’re investigating why a fault keeps recurring or comparing how a process behaves across dozens of production runs, Visplore 2.1 gives you the resolution you need, exactly where you need it.
Example: Use a coarse resolution to identify patterns for comparison, then refine the resolution only for them.
If your team already works in PI Vision, Visplore 2.1 meets you right there. The new PI Vision integration extension module embeds Visplore directly into your existing dashboards. The path from spotting a problem to understanding its root cause has never been shorter.
The integration covers two practical scenarios:
The result: your PI Vision dashboards become a natural launchpad for the kind of in-depth investigation that PI Vision alone wasn’t built for. Whether you’re chasing a recurring fault or trying to make sense of an unexpected KPI drop, Visplore is now just one click away from wherever your attention already is.
One click in PI Vision gets you to a standardized analysis in Visplore. Here: Comparison of the most recent start-up of an overheating asset.
Visplore is a powerful platform, and with that power comes a wealth of features and possibilities. The new AI Copilot in Visplore 2.1 makes sure that depth never feels overwhelming. Simply ask a question in natural language and get instant, relevant guidance on how to get the most out of Visplore.
What sets this assistant apart is its awareness of what you’re actually doing. It automatically takes the context of your current session into account such as the loaded cockpit, your active selection, and more. This way, answers are specific and actionable rather than generic. It’s like having an experienced Visplore user sitting next to you, who always knows what you’re looking at.
We know the privacy of your processes is important to your organisation. As such, your process data never leave your environment. The AI Copilot provides intelligent guidance without transmitting any customer data to the cloud, keeping all sensitive information strictly on-premise, as you’d expect.
Whether you’re a new user finding your footing or an experienced analyst exploring unfamiliar functionality, the AI Copilot helps you move faster and work more confidently without ever leaving your workflow.
Since version 2.0, Visplore has helped analysts cut through complexity by automatically ranking variables and their combinations by how strongly they differ across time periods, assets, or operating conditions. This way the most meaningful differences rise to the top immediately. Visplore 2.1 takes this capability significantly further in three ways:
Together, these enhancements make Visplore 2.1 a significantly more powerful tool for anyone who needs to understand why things differ, whether they’re investigating a batch quality issue, benchmarking assets against each other, or keeping a continuous eye on process health.
Example: Batches with high yield (orange) and little yield (blue) are compared regarding their process curves. Visplore automatically finds distinguishing variables and phases of the batch production.
Visplore 2.1 introduces powerful new trend capabilities that let you extrapolate both linear and non-linear trends into the future with a single click.
This goes well beyond drawing a line on a chart. Visplore calculates precisely how long it will take for a trend to breach any threshold you care about; turning a visual observation into an actionable, quantified prediction. These capabilities combine naturally with the rest of Visplore: For example, extract meaningful indicators from complex events, such as the startup duration of a machine, and immediately project how that metric is evolving over time.
You can even obtain automated predictive alerts: Set threshold-based alerts driven by trend extrapolations, not just current values. Instead of reacting when a limit is already exceeded, you get warned well in advance, for example, when asset behavior suggests that intervention will be needed within the next three weeks. This enables sophisticated monitoring workflows without any scripting or model building.
The result is a fundamentally more proactive approach to asset and process management — one where your data doesn’t just tell you what happened, but gives you the foresight to act before problems escalate.
Example: A KPI extracted from shutdowns of an asset, in this case the speed of the temperature drop, is trended over time, indicating a breach of a critical threshold in 3 weeks.
Visplore Stories have long been a favorite way to turn Visplore’s analytical power into polished, standardized PDF reports. Visplore 2.1 takes this further by making reports not just visually compelling, but truly dynamic and context-aware.
Two common real-world challenges are now solved elegantly:
All of this is achievable without writing a single line of code through Visplore’s familiar, intuitive interface. Reports can be generated on demand or scheduled as automated, recurring deliverables, giving teams a reliable and always-relevant information source that scales effortlessly across any number of assets or categories.
Every data landscape is different, and real-world data sometime does not arrive in exactly the shape you need it. Visplore 2.1 introduces an optional Python scripting node per data source, giving technically inclined users the full flexibility to transform imported data before it enters any analysis workflow.
This is more than just cleaning up outliers. The Python node enables both value-level and structural transformations, opening up use cases that were previously difficult or impossible to achieve without custom preprocessing pipelines outside of Visplore:
The result is a clean separation between raw data and analysis-ready data, managed entirely within Visplore. Teams with diverse or complex data sources gain a powerful new tool to standardize and prepare their data exactly the way they need. And end users just get exactly the analyses in Visplore they need, without needing to preprocess the data pipeline.
Visplore Stories are already a powerful way to define structured, repeatable analysis workflows. With an optional extension module, stories in Visplore 2.1 can now be organized into multiple distinct sections each with its own focus, data sources, and data pipeline.
This is purpose-built for scenarios where analysis naturally spans several stages or process steps. A systematic root cause investigation along a production chain is a prime example: each stage of the process may draw on different data sources, require different transformations, and demand its own analytical perspective while all sections belong to a single, coherent workflow.
Key capabilities of multi-section Stories include:
Combined with the Python transformation node, multi-interval loading, and the broader Visplore feature set, multi-section Stories make Visplore 2.1 a uniquely capable platform for tackling the kind of deep, structured analysis that complex industrial processes demand.
Visplore 2.1 delivers a range of additional enhancements that further streamline data access, analysis flexibility, and everyday usability:
