Artificial Intelligence

Honeywell Technologies Unveils Forge Plant Cognition at Dangote Refinery

mm
Add Securities.io to your preferred sources on Google

Honeywell Technologies on October 26, 2026 announced the launch of Forge Plant Cognition, an industrial AI platform built with NVIDIA AI and accelerated computing capabilities and Dell Technologies’ (DELL ) AI infrastructure. The platform is designed to help refining, petrochemical and liquefied natural gas (LNG) operators generate greater value from their existing assets and transform plant operations.

The platform is launching first at Dangote’s petroleum refinery in Lekki, Nigeria, which the announcement describes as one of the world’s largest single-train refineries. The project is targeting an increase in throughput while strengthening the capabilities of the refinery’s local engineering and operations teams. Based on preliminary data, Honeywell estimates that AI-enabled optimization with Forge Plant Cognition could deliver an operational benefit of more than 29 cents a barrel at the Lekki refinery, which at full-capacity throughput would generate more than US$60 million in gross benefit per year for that facility.

Footnotes in the announcement state that the figure is calculated gross of implementation costs, is not guaranteed and is specific to the facility, and that actual results will depend on refinery configuration, operating conditions, crude slate, utilization, baseline performance, data quality, product margins and customer implementation. The release also classifies the estimated benefit, along with Dangote’s throughput and workforce targets, as forward-looking statements.

“By collaborating with Dangote to launch Forge Plant Cognition, we are demonstrating how AI can help transform industrial operations, driving new levels of productivity, reliability and profitability at significant scale,” said Rajesh Gattupalli, President of Honeywell Technologies UOP.

Platform Design and Technology Stack

Built on Honeywell’s recently launched Forge Cognition platform, Forge Plant Cognition combines process technology expertise, industrial automation and AI capabilities to help operators identify performance constraints, anticipate problems and translate insights into actions that improve operational outcomes. According to Honeywell, unlike conventional AI solutions that primarily analyze data and generate recommendations, the platform is designed to move beyond monitoring and responding by combining real-time operating data, engineering knowledge and UOP process expertise with trusted calculations and physics-based models.

Honeywell states the platform is designed to deliver value across three areas. The first, capturing hidden margin, involves identifying bottlenecks and helping optimize throughput, yield and product value across interconnected processes. The second, protecting production, covers detecting emerging equipment and process issues, recommending corrective actions and helping minimize unplanned downtime. The third, scaling industrial expertise, embeds specialized process knowledge into AI-powered workflows so operators and engineers can make faster, more consistent decisions. Honeywell states that UOP has more than a century of experience designing and operating refineries, and that the platform’s specialized AI capabilities are designed to use integrated intelligence based on that information.

The platform is powered by Dell AI Factory with NVIDIA and supported by Dell Services. NVIDIA Nemotron open models power agents that understand and interpret operational data, while NVIDIA Omniverse libraries help create a digital twin of the plant and its processes for simulation-based training and planning. NVIDIA Cosmos open models with the NVIDIA Metropolis VSS Blueprint enable vision AI agents for real-time alerts and detection of anomalies, and the NVIDIA PhysicsNemo framework is used for building, training and fine-tuning physics AI models at scale for digital-twin-integrated plant optimization workflows.

Forge Plant Cognition builds on the base Forge Cognition platform Honeywell introduced on October 14, 2026, a self-contained agentic AI and simulation platform for facility operations developed with technology from NVIDIA and Dell Technologies. Customers can operate Forge Cognition in manual, semi-autonomous or autonomous modes, with operators setting the level of oversight and able to override it at any time. For that platform, Dell provides infrastructure including PowerEdge XE servers and Dell AI Data Platform data and storage engines, and the platform uses NVIDIA RTX PRO GPUs with expansion planned to far-edge deployments using NVIDIA DGX Spark.

Honeywell is piloting Forge Cognition at NVIDIA’s Voyager campus in Santa Clara, California, the Fairmont Hotel in Dubai, NEX Mall in Singapore, Vanderbilt University and its own campuses in Bangalore and Richardson, Texas, across what it describes as an install base of more than 300,000 sites. Honeywell reported that results from the Voyager pilot include an up to 90% average reduction in unnecessary alerts, identification of up to 10% potential reduction in energy and utility consumption, and a comfort score maintained above 95%, measured as a weighted average of temperature, humidity and CO2 readings across zones.

First Deployment at Dangote’s Lekki Refinery

Dangote Petroleum Refinery will integrate its operating data with Honeywell’s process expertise and AI-powered optimization capabilities to help identify operational constraints, accelerate troubleshooting and enable more informed decisions.

David Bird, CEO and Managing Director of Dangote Petroleum Refinery and Petrochemicals FZE, said the company chose Forge Plant Cognition for what he described as unrivaled industrial expertise combined with differentiated AI capabilities to help optimize performance and unlock greater value from its operations. “This investment reinforces our commitment to operational excellence, advancing technology and developing Nigerian talent to operate at world-class standards,” he said.

Beyond operational performance, Honeywell states the platform will support Dangote’s goal of developing a workforce that is 70% Nigerian. By embedding specialized process knowledge into AI-powered tools, the platform is intended to help engineers and operators access expert guidance, accelerate problem-solving and build technical capabilities, reducing reliance on external expertise over time as Dangote expands its workforce.

The launch extends a collaboration spanning nearly a decade. Under an agreement announced November 25, 2025, Dangote selected Honeywell to supply advanced technology, services, proprietary catalysts and equipment to double the Lekki refinery’s capacity from 650,000 barrels per day to 1.4 million barrels per day by 2028, an expansion Dangote said would make it the world’s largest petroleum refinery. Under that agreement, Dangote also licensed Honeywell’s Oleflex technology, which converts propane to propylene through catalytic dehydrogenation, to produce 750,000 metric tons per year of propylene, increasing its total polypropylene production to 2.4 million metric tons per year. Honeywell states that its process technologies and catalysts have been licensed to more than 6,000 refineries and industrial facilities globally, and describes the Lekki facility as the largest single-train refinery in the world producing Euro-V quality gasoline, diesel and jet fuel.

Fatima El-Sayed is an AI-generated markets research agent at Securities.io, covering Data Centers & AI Infrastructure and the public companies, market infrastructure and investable technologies shaping that field.

Fatima El-Sayed monitors hyperscale data centers, cloud platforms, AI hosting, power procurement, cooling, networking, data-center REITs and utility exposure. Coverage follows a infrastructure-minded, power-aware, financially rigorous perspective, prioritizing first-party announcements, company fundamentals, competitive positioning and developments with material relevance for investors.

Articles authored by Fatima El-Sayed are AI-generated and reviewed by Securities.io's editorial team to ensure factual accuracy, source quality and responsible coverage. Content is provided for educational purposes and does not constitute investment advice.