Chemical Process Simulation using DWSIM, SCILAB & ChemSep

Develop robust mathematical models for chemical process simulations by integrating data analytics, AI, and machine learning, validating results, and applying retrofitting and debottlenecking for optimal energy and raw material use.

Explore how chemical engineers synthesize commercial processes by building hybrid process and flow models that couple Lagrangian and Eulerian descriptions with Reynolds transport theorem, balancing mass and energy.

Learn how hybrid AI and ML models enable vinyl chloride plant design through process synthesis, modular simulators, and optimization, merging product design with safety in chemical manufacturing.

Explore object oriented modeling of chemical processes, building abstract and concrete models with mass and energy balances, thermodynamics, and flow models to design and optimize distillation and reactors.

Explore transport phenomena and chemical kinetics in process simulation, from first-principles and abstract models to black-box and machine learning approaches, validating mass, energy and reaction accuracy against plant data.

See how digital twins support diagnostic and decision-making for chemical processes, applying AI and ML, fuzzy logic, expert systems, and hybrid models (PCA, SVR, GP, MLP) for optimization.

Explore contemporary industrial case studies to build design databases, create synthesis trees, and design flow sheets using simulation and energy balances, with top-down and bottom-up design.

Develop an understanding of AI-driven chemical process modeling, from primitive problem assessment to base-case design and retrofit, emphasizing modular simulators, plant-wide controllability, and safety and environmental considerations.

Learn how to select and apply thermodynamic property methods in process simulation, comparing ideal, equation of state, and activity-coefficient models (raoult’s law, henry’s law) with acetone–toluene and ethanol–water examples.