Process Optimization ( 2024 - 2026 ) - Baker Hughes

Project Brief

Baker Hughes is a leading global energy company that provides equipment, services, and digital solutions — Cordant™ to the industrial sectors. Process Optimization is a product within the Cordant Suite.

I led the design of Process Optimization, a million-level product line for Baker Hughes. I was collaborating with the PM, TPM, SME, Researcher, and Engineers to ship a B2B SaaS product from scratch.

Client pain

Qatar Fertilizer Company (QAFCO) first came to us as they were facing several operational challenges that limited their Ammonia production.

Solution

An AI-enabled web software that provides real-time setpoints and visualized production metrics, enabling users to capture dynamic changes of an asset to achieve target production and maximize its potential.

Outcomes & Impacts

1-2% Increase

in production

5% -10% Reduce

in specific energy consumption

Business Challenge to Solve In The Early Stage — Scale Insights Across Product Ecosystem.

⚡️ Clients needs and Business goals: QAFCO needed highly customized workflows with their own unique performance metrics. But Process Optimization is part of Cordant™ Suite. Our business targets to build a broader, integrated, and modular universal solution for all industrial sectors.

The Architectural Pivot: The Micro-App Strategy

I took a step back and analyzed the underlying of their request. Worked with product and engineering to design a modular framework, separated out the specific metrics into a micro-app, and turned it into configurable widgets without affecting the core workflows.

Outcome

QAFCO got exactly what they wanted: a highly tailored experience. But more importantly for our business, we didn't build a dead-end feature. We expanded the core library of the Cordant Suite.

The Business Impact & ROI

In 2025, a major LNG company adopted the product. Because the core system remained clean, they integrated their data directly into the backend without requiring any design changes or breaking any workflows. Saved the business significant efforts while maintaining a highly manageable, scalable product ecosystem.

An Integrated Real-Time Dashboard with Visual Alerts

Operators' responsibility is to increase production as much as possible. Insights from user testing revealed that while they struggled to manage different sensors for each asset due to data fragmentation, they also frequently failed to adjust optimal parameters due to data latency.

To help panel operators monitor production status and respond immediately. I designed a recommendation dashboard where data is integrated, and sensors needing immediate attention will be colored (orange) in real-time for alert. it empowers operators to monitor status seamlessly and act instantly.

Multiple Actions By One-Click

There is a scenario, when the production meets the target, to keep maximizing the production capacity, the panel operator will reset the optimal range. The Inline table editing allows them to tackle multiple tasks simultaneously and spend less time on each small task.

Visualize Dense Data into Actionable Insights

If the operator's responsibility is to meet the production target, then the unit supervisor is the one who sets the target.

“My biggest pain point is tracking when and why we're missing optimization potential. My job isn't to look at a single valve, but to ensure the entire plan is actually implemented."

— Omar, Unit Supervisor

“My biggest pain point is tracking when and why we're missing optimization potential. My job isn't to look at a single valve, but to ensure the entire plan is actually implemented."

— Omar, Unit Supervisor

To help the unit supervisor track the production gap and identify potential opportunities more efficiently from the density data, I visualized KPIs in charts for quick comprehension of trends to set the next target.

User Starting Point A

Predictability And Visibility: Modal Deployment

Process Optimization is a product that combines deep domain expertise with AI/ML-driven insights from the engineers. The deployed models in the backend are the key to optimizing production. Although engineers can run the simulation on other systems before deployment, they still feel frustrated by unpredictable model performance.

If I can build a model list with real-time performance trends to address unpredictable issues, what else can I do to support engineers to react faster?

After the product launched, at first, they can quickly checking or comparing through the list. But later I observed that the number of tags (models) was increasing over time.

If I can build a model list with real-time performance trends to address unpredictable issues, what else can I do to support engineers to react faster?

After the product launched, at first, they can quickly checking or comparing through the list. But later I observed that the number of tags (models) was increasing over time.

User Starting Point B

From Cognitive Overload to Saved Patterns

At the time, I was also working on building a pattern library for internal designers. I brought the workflows over there to shape the engineer's journey.

I added another starting point B, where engineers can save 20% time by choosing saved modal patterns in advance, which allows them to focus entirely on the critical model analysis task, instead of putting much effort into digging tags from the list that was generated 6 months ago.

At the time, I was also working on building a pattern library for internal designers. I brought the workflows over there to shape the engineer's journey.

Product Values

Over the past year, our team successfully deployed the Cordant™ Process Optimization solution across multiple core business lines, including ammonia production, gas processing, LNG, and offshore FPSO operations, serving several key account (KA) clients. We achieved beyond-expectation results in AI-driven advanced process modeling and real-time optimization. Not only did we deliver a 1-2% overall improvement in production and energy reduction, but we also drove significant commercial value in projects — such as boosting LNG production by up to 1.5% and helping a gas processing plant realize an estimated $10 million annual margin increase, fully empowering our clients to achieve their core goals of reducing costs and maximizing profitability.

💬 Quotes From Client

"This initiative has fundamentally changed how we operate. The First principles and AI-based platforms have empowered our teams to make faster, smarter decisions, and the results speak for themselves. Through QAFCO’s Operational Excellence Program and our collaboration with Baker Hughes, we have elevated reliability across our assets. We’re building a culture of continuous improvement and innovation.”

— Abdulla Al Naemi, Head of Reliability Engineering, Qatar Fertilizer Company (QAFCO)

"QAFCO has achieved a +0.8% daily production uplift and saved over 500 hours of production downtime since November 2023. Leveraging Physics-based AI technologies and engineering domain expertise from Baker Hughes have set a new benchmark in process optimization and reliability. Our teams are fully engaged in this transformation to realize sustainable value at scale. This success is not just technological; it is the result of a robust change management approach that engaged leadership and empowered our teams at every level. Our partnership with Baker Hughes and our commitment to digital transformation enabled operational excellence has positioned QAFCO as a global leader in fertilizer production, delivering measurable and sustainable value for our stakeholders and the industry."

— Giuseppe Franceschini, Chief Technology Officer, Qatar Fertilizer Company (QAFCO)

Other Resources

More details about the product on the official website

[ Next Project : Asset Strategy Management ]

[ Back on top ]

Let's chat.

Feel free to reach out for collaborations or just a friendly

Let's chat.

Feel free to reach out for collaborations

or just a friendly

Let's chat.

Feel free to reach out for collaborations or just a friendly