Gigaton offers a self‑learning control system for heavy‑industry plants such as cement, steel, glass, and mining operations.
Funding
$35M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
CECGPASNUTFounders
Product
Problem
Heavy‑industry plants such as cement, steel, glass and mining operations rely on legacy control systems that are static, require extensive manual tuning, and often degrade in performance as process conditions change. This leads to higher fuel consumption, increased carbon emissions, and elevated operating costs, while the industries face pressure to decarbonise and improve resilience.
Solution
Gigaton provides a self‑learning control system that continuously retrains AI models and control policies using real‑time plant data. The platform predicts key process variables, visualises the rationale behind each control action, and integrates directly with existing DCS environments, enabling autonomous optimization of temperature, fuel use, and gas composition. Operators can adjust strategic priorities—such as cost versus production—with a single click, and the system adapts without drift. A digital twin of the plant allows safe simulation of controller changes before deployment, accelerating rollout and reducing risk. By combining expert systems with cutting‑edge machine learning, Gigaton reduces fuel consumption, stabilises process variability, and cuts carbon emissions at scale.
Target Audience
Primary customers are operators and engineering teams of energy‑intensive heavy‑industry plants—particularly cement, steel, glass and mining facilities—seeking to lower fuel costs, improve process stability, and meet decarbonisation targets.
Features
- Continuous model retraining and policy updates to maintain performance as plant conditions evolve
- Explainable AI visualisations that show why each control decision is made, building operator trust
- Predictive forecasting of temperature, gas composition and other process variables to act before disturbances occur
- Integrated digital twin for offline testing of control strategies and rapid, safe deployment
- Flexible priority setting that lets plant managers switch focus between cost, production, or emissions with a single configuration change
- Direct connection to existing Distributed Control Systems (DCS) for seamless integration without hardware replacement