Machine Learning in Chemical Processes via Python: A distillation column case study
LEVEL: BEGINNER HRDF: CLAIMABLE
Ten (10) CPD Hours approved by MBOT
TRAINERS:
Associate Professor Dr Dr Haslinda Zabiri, MR. Amar Haiqal Che Hussin & ASSOCIATE PROFESSOR Ir Dr A Halim Shah Maulud
25 - 26 OCTOBER 2024
MS TEAMS
DAY 1:9.00AM - 1.00PM
DAY 2:9.00AM - 5.00PM
RM 830 FOR PROFESSIONALS
10% Discount for Early Bird (until 25 September 2024) / Group / Students
CONTENT SUMMARY
INTRODUCTION
This course is designed to provide an exclusive insight for beginners on how machine learning can be effectively applied for descriptive (fault detection), diagnostic (fault classification) and predictive (prediction) analytics in chemical process systems. The practicality of the course is emphasized through the use of a distillation column example, which is one of the most commonly found unit operations in industrial processing plants.
Machine Learning Overview (Module 1)
- Why ML?
- General Application
- ML vs classic code
- Model overview
- Steps in ML (Importing data to deploying model)
- How to evaluate ML Model (R2, MSE, RMSE, Confusion Matrix, Accuracy Paradox for CLASSIFICATION)
Machine Learning for Descriptive Analytics (Module 2)
- Principal Component Analysis
- Fault Detection and Identification
- Hands on exercise and problem-solving: Distillation Column Case Study
Machine Learning for Diagnostic and Predictive Analytics (Module 3)
- Python Basic Syntax and Modules ((NumPy, Pandas, Matplotlib, Scikit-Learn, XGBoost))
- Model development
- Training and Testing
- Feature Selection (if necessary)
- Hyperparameter Tuning
- Hands on exercise and problem-solving: Distillation Column Case Study
OBJECTIVES
Upon completion of this course, participants will be able to:
- To provide beginners an easy to follow guide on familiarizing themselves with machine learning tools.
- To apply Machine Learning tools in industrial chemical processes for descriptive (what happened), diagnostic (why it happened) and predictive (what will happen) analytics.
WHO SHOULD ATTEND?
- Undergraduate, Post-graduate students and researchers
- Plant Operation Engineers
- Process Engineer
OUR TRAINERS
1. Associate Professor Dr. Haslinda Zabiri (UTP)
Dr Haslinda Zabiri received her PhD degree in Process Systems Engineering from Universiti Teknologi PETRONAS specializing in advanced process control. Her current interests include modelling, control, monitoring and diagnostics of industrial process systems using machine learning based methods. She has developed fault detection and diagnosis techniques for monitoring industrial process control loops. She is currently an Associate Professor and the Program Manager for MSc in Process Integration (by Coursework) in Chemical Engineering Department at Universiti Teknologi PETRONAS.
2. Mr Amar Haiqal Che Hussin (UTP)
3. Associate Professor Ir Dr A Halim Shah Maulud (UTP)
Dr Abdul Halim Shah Maulud received his PhD degree in Process Systems Engineering from University of Sydney, Australia specializing in multivariate process monitoring. He has developed multi-scale fault detection and analysis techniques for industrial processes. He is currently an Associate Professor and the Chair of Chemical Engineering Department at Universiti Teknologi PETRONAS.
REGISTRATION FEES
PROFESSIONALS
MYR830*
*fee quoted does not include SST, GST, HRDF service fee / VAT or withholding tax (if applicable).
EARLY BIRD/ GROUP/ STUDENT
MYR747*
*fee quoted does not include SST, GST, HRDF service fee / VAT or withholding tax (if applicable).
OUR LOCATION
Centre for Advanced & Professional Education (CAPE)
Level 8, Permata Sapura, Kuala Lumpur City Centre, 50088 Kuala Lumpur​
CALL US
+605 - 368 7558 /
+605 - 368 8485
DROP US AN EMAIL
cape@utp.edu.my