Ai-based handling of gasification feedstocks
Data-driven models optimize waste stream selection and syngas production by correlating waste composition with target chemical products, improving efficiency and sustainability in converting waste into high-quality syngas for chemical synthesis.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- BASF SE
- Filing Date
- 2025-12-15
- Publication Date
- 2026-06-25
AI Technical Summary
The variability of waste composition complicates the production of synthesis gas, making it challenging to efficiently convert waste into valuable chemical products due to fluctuations in moisture content, calorific value, and chemical composition, which affects the quality and yield of syngas.
A method involving data-driven models to determine target feedstock composition data by correlating waste stream characteristics with desired synthesis gas composition, optimizing the selection and matching of waste streams to produce high-quality syngas tailored for specific chemical products, using neural networks and regression models to predict and adjust production based on availability and demand.
This approach enhances the efficiency and flexibility of syngas production, optimizing feedstock utilization, reducing reliance on fossil fuels, and achieving consistent syngas quality for downstream processes, thereby supporting sustainable and resilient chemical production.
Smart Images
Figure EP2025087032_25062026_PF_FP_ABST