MAC AIChE Workshop
Participants of the Minority Affairs Committee (MAC) Workshop – 27 August 2026 can now access and download all training materials directly from the Training Menu on the AKC Technology website. These resources include the full slide deck, case studies, glossaries, quizzes, and Python programs demonstrated during the workshop.

Downloadable Items

  • Workshop PowerPoint Slides — Complete slide deck used during the live session.
  • Examples and Case Studies (PDF) — Consolidated examples and case studies presented during the workshop.
  • A–G Glossary and Human Cognition — Key terms, cognitive principles, and foundational concepts.
  • MAC Assessment Quiz — Self assessment quiz for participants to evaluate understanding.
  • Example 1: First Order Isothermal CSTR + ANN Surrogate Digital Twin (Python) — Python script demonstrating hybrid modelling.
  • Example 2: distillation_tray_efficiency_ann_complete.py — ANN based tray efficiency prediction model.
  • Case Study 1: Jacketed CSTR with First Order Kinetics (Python) — Full dynamic modelling case study.
  • Case Study 2: Prediction of Distillation Overhead Purity Using Machine Learning (Python) — ML based purity prediction script.
Click here to download the files now.

Python Program Download and Run Guide

Download the zip file and extract the files to a folder on your local machine. You will find the python files in the folder with their following purpose:
  • Case Study 1. JACKETED CSTR WITH FIRST-ORDER KINETICS-akc1.py - Jacketed CSTR simulation with first-order kinetics, Arrhenius temperature effect and cooling failure analysis
  • First-order isothermal CSTR plus an ANN surrogate digital twin.py - First-order isothermal CSTR model with an artificial neural network surrogate digital twin
  • Case Study 2. Predicting Distillation Overhead Purity Using Machine Learning.py - Distillation overhead purity prediction using machine learning
  • distillation_tray_efficiency_ann_complete.py - Complete ANN workflow for predicting distillation tray efficiency from operating and design variables
Step 1: Install Python Check and confirm if python is installed on your system. Open your terminal / command prompt and type:
python --version

If you are using windows and you probably installed python with python launcher, you can also try:
py --version

If you see a version number, python is installed. If not, you can download and install python from https://www.python.org/downloads/. Make sure to check the option to add python to your system PATH during installation. After installation, you can verify the installation by running the version command again.
Step 2: Create Your Project Folder Create a folder on your computer, e.g.: C:\Users\YourName\Documents\akc_python_engineering_programs, then copy the extracted files to that location such that it contains the python files listed above.

For example, after extracting the downloaded zip file, your folder should contain:
  • Case Study 1. JACKETED CSTR WITH FIRST-ORDER KINETICS-akc1.py
  • First-order isothermal CSTR plus an ANN surrogate digital twin.py
  • Case Study 2. Predicting Distillation Overhead Purity Using Machine Learning.py
  • distillation_tray_efficiency_ann_complete.py

Step 3: Install Required Libraries (IMPORTANT) The programs use python libraries such as numpy, matplotlib, pandas, scipy, scikit-learn and joblib. Open your command prompt or terminal and run:
pip install numpy matplotlib pandas scipy scikit-learn joblib

If you are using windows with python launcher, you can also run:
py -m pip install numpy matplotlib pandas scipy scikit-learn joblib

These libraries are required for numerical calculations, data handling, plotting graphs, solving engineering equations and training the artificial neural network models.
Step 4: Run the Programs You can run the programs by first ensuring you navigate to the project folder and then execute the following commands in your terminal or command prompt:
cd C:\Users\YourName\Documents\akc_python_engineering_programs

Then run the first program:
python "Case Study 1. JACKETED CSTR WITH FIRST-ORDER KINETICS-akc1.py" or py "Case Study 1. JACKETED CSTR WITH FIRST-ORDER KINETICS-akc1.py" (use py if you installed on windows using python launcher)
This will bring the following:
  • Input data for the jacketed CSTR reactor
  • Normal cooling and cooling failure simulation results
  • Step-by-step concentration and temperature values
  • Graphs showing concentration and temperature profiles

Run the second program (CSTR digital twin and ANN model):
python "First-order isothermal CSTR plus an ANN surrogate digital twin.py" or py "First-order isothermal CSTR plus an ANN surrogate digital twin.py" (use py if you installed on windows using python launcher)
This will bring the following:
  • Synthetic CSTR operating dataset
  • ANN model training result
  • Comparison between first-principles result and ANN prediction
  • Saved results and plots inside the cstr_results folder

Run the third program (Distillation overhead purity prediction):
python "Case Study 2. Predicting Distillation Overhead Purity Using Machine Learning.py" or py "Case Study 2. Predicting Distillation Overhead Purity Using Machine Learning.py" (use py if you installed on windows using python launcher)
This will bring the following:
  • Generated distillation operating data
  • Training and test data split
  • ANN prediction of overhead purity
  • Model performance results such as MAE, RMSE and R-squared
  • Predicted-versus-actual purity plot

And then the fourth program (Complete tray efficiency ANN workflow):
python "distillation_tray_efficiency_ann_complete.py" or py "distillation_tray_efficiency_ann_complete.py" (use py if you installed on windows using python launcher)
This will bring the following:
  • Tray efficiency input and output variable description
  • Generated or imported tray efficiency dataset
  • Artificial neural network training and testing results
  • Prediction for a new operating condition
  • Saved CSV files, model files and plots inside the tray_efficiency_results folder
These programs are useful for Chemical Engineering, Petroleum Engineering, Process Engineering, Energy Systems, Artificial Intelligence, Machine Learning and Digital Twin learning applications.