In Germany, the chemical industry is one of the leading energy consumers in the industrial sector while remaining a vital pillar of the national economy and global export market. Enhancing energy efficiency in this sector is therefore the primary lever for reducing industrial CO2 emissions and safeguarding global competitiveness. Downstream solid-processing operations such as drying, fluidization, agglomeration, granulation, and comminution are inherently energy intensive. Coupled with essential utility systems like compressed air generation, refrigeration, steam generation, and industrial heating and cooling, these processes hold substantial, yet underutilized, potential for waste heat recovery, heat integration, and cross process optimization.

The project establishes a two-tiered optimization framework for energy-efficient plant operations. The global optimization level focuses on the integrated site scale to achieve optimal distribution, utilization, regeneration, and cross-process reuse of material and energy flows, while the local optimization level focuses on individual process units to optimize performance through dynamic control of process parameters using advanced machine learning techniques. Together, this dual-level approach targets up to a 10% improvement in overall energy efficiency at the integrated site.

The methodology combines advanced flowsheet simulation, industrial validation, and machine learning to build a robust computational foundation:

• Dyssol Modeling & Validation: Developing physically consistent models for energy intensive solid processes focusing on fluidized bed spray granulation and heat recovery from air compressors and process flue gas. Models are validated against industrial data from Pergande GmbH.
• Integrated Flowsheet: Combining individual units into a dynamic, site-wide simulation that forms the computational foundation for the TwinLink digital twin.
• Data Provision for Machine Learning: Generating high-fidelity simulation and thermodynamic data to feed machine learning modules and advanced control strategies developed by the project counterpart.
• Efficiency Analysis & System Integration: Quantification of energy, material, fuel consumption through systematic scenario analysis, alongside the provision of standardized data formats and interfaces for seamless integration into the final digital twin architecture.