Introduction
At Bravura AI, we recently encountered a fascinating challenge that required a blend of cutting-edge technologies and creative problem-solving. Our client faced a critical situation: they needed to report annual gas consumption, but due to a migration project they had lost some crucial data. With time ticking away, we embarked on a mission to estimate gas usage by leveraging the remaining information available to our team. We’ll dive into this success story and explore how we eventually cracked the code.
The Scenario
Our journey begins with a seemingly straightforward migration project. A boiler house was transitioning to DeltaV version 14 with DeltaV Live. It was both unexpected and unfortunate that, during this process, module tag renaming led to the loss of data. In fact, this minor migration hiccup cost the client approximately six weeks of vital data that proved impossible to recover. As the reporting period drew near, the pressure mounted — the client had to report gas consumption figures to state regulatory authorities.
The Data Dilemma
Despite consulting every expert in our network, including Emerson Corporate HQ and the local Impact Partner’s senior engineering staff, there was no direct way to retrieve the missing data. Time was of the essence, and we needed a solution. Here’s the challenge we faced:
Data Set Overview: Our dataset included various time-series data points — gas flow, air flow, exhaust flows, temperatures, pressures, and valve/damper positions.
Critical Gaps: The missing data fell into specific time windows:
- January to October — The boiler house was inactive during these months, rendering the data irrelevant for our estimation.
- November 1 to December 15 — Gas-flow data was lost during this period, when there were boiler start-up activities.
- December 15 to March 1 — We possessed a complete dataset for this period.
The Solution: Chemical Engineering Meets Artificial Intelligence
Our challenge resembled an undergraduate senior thesis problem. Given a complex dataset loaded with physical and chemistry relationships, we needed to develop a model and then make predictions based on that model. Unlike the typical thesis problem, though, we weren’t confined to classical process modeling techniques — the days of resolving eigenvalues and linear systems by hand were too far in the past for efficient recall.
In practice, here’s how we tackled it:
- Data Aggregation — We used Bravura AI proprietary scripts to extract the data needed for loading into the Microsoft Azure Machine Learning engine.
- Machine Learning — Using the complete dataset available from December 15 to March 1, we trained the model to predict gas flow. We then tested the model on independent data and proved it was over 95% accurate.
- Data Imputation — We leveraged the model we had built to estimate missing gas-flow values during the critical weeks. By analyzing the available data, we filled in the gaps intelligently.
Bravura’s Novel Innovation
This project showcases two relatively novel innovations employed by Bravura:
- Repurposing DeltaV’s data infrastructure. DeltaV’s Continuous Process Historian and the DeltaV Excel Add-in and VBA Object Library can be used for much more than surface-level visualization. Interaction with underlying databases and data services is exposed for developers’ use in the Development Environment. Bravura leveraged the object library in this project and others, turning the DeltaV Continuous Historian into a data source for broader process analytics.
- Pairing historian data with cloud ML tools. By accessing the databases through the VBA Object Library, the data was made available for analysis in Microsoft Azure’s Machine Learning Studio. This toolset accomplished in about two days what would otherwise have taken at least a dedicated week of modeling and analysis.
Results and Impact
What was striking was the ease with which we were able to develop the model on the Azure Machine Learning platform from the DeltaV history.
Within a week, we delivered an accurate estimate of the annual gas consumption. Our client met regulatory requirements, and the success story spread across the industry. By combining existing tools in novel ways, we transformed a tough task into a triumph.
Technical Roadmap Implications
The chemical processing industry will capture the value of multimodal AI, as the potential is far too great to ignore. It has been 25 years since data networking and integration innovations offered a comparable level of efficiency gain. The use case described here is a discrete, batch-process example of what’s expected to evolve into continuous monitoring. Agentic AI will essentially be an agglomeration of tools, including the machine learning techniques used in this case.
Importance of Microsoft Solutions
Our team relies heavily on Microsoft solutions for internal collaboration, ensuring seamless remote work despite being spread across vastly different time zones. This setup minimizes the impact of working independently and maintains high productivity levels. Microsoft Teams supports virtual meetings, file sharing, and real-time communication, fostering a collaborative environment even when team members are miles apart. SharePoint serves as our central repository for documents, making it easy to manage and access information securely. Together, these tools keep everyone aligned, reducing the risk of miscommunication and enhancing overall efficiency.
Our Azure and SQL-based cloud environment is the backbone of our operations, offering scalable and secure solutions for data storage and processing. This setup allows us to handle large volumes of data with ease, perform complex queries, and generate insights that drive our decision-making. The cloud infrastructure also provides the flexibility to scale resources up or down based on our needs, ensuring cost-effectiveness and optimal performance.
In summary, the combination of Microsoft Teams, SharePoint, Azure, and SQL — along with an extensive list of other Microsoft tools we deploy as needed — has been instrumental in enabling our team to work effectively and efficiently regardless of geographical barriers. This integrated approach not only supports our current operations but also positions us well for future growth and innovation.
Conclusion
At Bravura AI, we thrive on challenges like this one. Our ability to blend technology, expertise, and creativity allowed us to crack the gas consumption mystery. As we continue to push boundaries, we’re reminded that innovation knows no bounds — whether in a boiler house or an R&D laboratory, we’re always drawing on our collective experience to deliver success.
To explore how we can leverage our skills and tools for your business needs, contact Bravura AI today. You can also visit bravura-ai.com to learn more about our integrations and how they can benefit your operations.