MSc Advanced Chemical Engineering / Course details

With the rapid development of Industry 4.0 technologies including Internet of Things (IoT), cloud computing and analytics, and AI and machine learning, chemical manufacturers are integrating these digital technologies into their production facilities and throughout their operations, moving chemical industries towards smart manufacturing to better manage productivity, energy efficiency and safety in production. As modern chemical plants are now highly automated, inter-connected and extensively equipped with sensors, a huge amount of production data is generated and needs to be exploited. Statistical and data-driven modelling methods or so-called machine learning is an important technological tool for effectively exploiting this huge amount of data.

This unit will mainly focus on applications of machine learning in chemical engineering. It will briefly explain the role of machine learning in chemical engineering. It will introduce various machine learning algorithms and delineate their fundamentals with multiple examples within the chemical engineering discipline. It will also demonstrate how to use these machine learning algorithms to develop machine learning models for different chemical engineering applications via Python programming language. The following topics will be covered in this course.

The unit aims to:

• Develop students’ understanding of fundamentals of different machine learning algorithms and appreciation of these algorithms.
• Help students develop different machine learning models relevant to chemical engineering applications such as chemical process design, process operations and control.
• Develop students’ skills in mathematical modelling and Python codes for generation of the different machine learning models.
   

Students will be able to:

Contents

Chapter 1: Introduction
1.1 What is AI & Machine Learning
1.2 The role of AI & Machine Learning in Chemical Engineering
1.3 Types of Machine Learning
1.4 Machine learning algorithms

Chapter 2: Regression
2.1 Examples (e.g., PM2.5, CO2 emission prediction)
2.2 Model training and validation
2.3 Error analysis

Chapter 3: Classification
3.1 Key concepts in classification
3.2 Probabilistic generative model
3.3 Logistic regression
3.4 Support vector machine
3.5 Examples

Chapter 4: Deep Learning
4.1 Why deep learning?
4.2 Neuron networks
4.3 Examples 

Chapter 5 Gaussian processes and Bayesian Optimization
5.1 Why Gaussian processes
5.2 Principles of Gaussian processes
5.3 Bayesian optimisation
5.4 Examples 

Chapter 6: Unsupervised learning
6.1 Linear dimension reduction (Principal Component Analysis)
6.2 Clustering
6.3 Examples

Chapter 7: Transfer learning
7.1 Why transfer learning
7.2 Principles of transfer learning
7.3 Examples

Chapter 8: Reinforcement Learning
8.1 Why reinforcement learning
8.2 Principles of reinforcement learning
8.3 Examples

Note that all examples for machine learning algorithms will be linked to sustainability goals like energy efficiency or waste reduction.

Fundamental aspects supporting the critical learning of the module will be delivered as pre-recorded asynchronous short videos via our virtual learning environment. These will be supported by synchronous sessions with master lecture content, Q&A, and problem-solving sessions where you can apply the new concepts.

Surgery hours are also available for drop-in and feedback support.

Feedback on problems and examples, feedback on coursework and exams, and support will also be provided through the virtual learning environment. Discussion boards provide an opportunity to discuss topics related to the material presented in the module.

Students are expected to expand the concepts presented in the session and online by additional reading (suggested in the Online Reading List) in order to consolidate their learning process and further stimulate their interest to the module.

Students will be provided technical support with detailed instructions for setting up Python programming environments (e.g., Notebooks, relevant libraries).

Students will also be provided specific chemical engineering datasets for practice (e.g., Aspen simulation outputs, process operation data).

Reading lists are accessible through the Canvas system linked to the library catalogue.

1. Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer: New York, USA. 2006.
2. Francisco Javier Lopez-Flores, Rogelio Ochoa-Barragan, Alma Yunuen Raya-Tapla, Cesar Ramirez-Marquez, Jose Maria Ponce-Ortega, Machine Learning Tools for Chemical Engineering: Methodologies and Applications, Elsevier Science, 1st edition, 2025. ISBN-10: 044329058X. ISBN-13: 978-0443290589.