Artificial Intelligence in Chemical Engineering

Syllabus

1. Fundamentals of AI and Applications (2 hours)
   1. Definition, historical overview, applications
   2. AI, ML, deep learning: Differences and overlap
   3. Ethical considerations (Bias, transparency, interpretability)
   4. Applications in chemical engineering
2. Python Basics and Data Handling (6 hours)
   1. Intro to python and Jupyter notebooks
   2. Data handling with python: Data manipulation with pandas
   3. Python for basic statistics
3. Data Visualization and Scientific Computing (8 hours)
   1. Basic libraries: Numpy, Scipy, Matplotlib, Seaborn
   2. Solving linear, nonlinear, interpolation, curve-fitting and ordinary differential equation problems
   3. Data visualization with Matplotlib
   4. Solving chemical engineering problems
4. Data Engineering (9 hours)
   1. Data gathering, types of data, data quality
   2. Data cleaning, handling missing values, outlier detection
   3. Feature engineering (Selecting and transforming features)
   4. Data scaling and normalization, dealing with imbalanced data
5. Introduction to Machine Learning (10 hours)
   1. Overview of supervised learning and applications
   2. Regression models: Linear regression, K-nearest neighbors (KNN), simple neural network regressor
   3. Classification Models: Decision trees, random forests, KNN classifier
   4. Evaluation metrics for regression and classification (MAE, MSE, accuracy, confusion matrix)
6. Introduction to Neural Networks (10 hours)
   1. Neurons, layers activation functions
   2. Neural network architectures
   3. Simple neural network example using Keras
   4. Applications in chemical engineering: Process optimization, predictive maintenance (Time-series data)
   5. Clustering techniques (K-means) for anomaly detection in chemical processes