0% found this document useful (0 votes)
43 views22 pages

Lecture 1

This document provides an introduction to machine learning for chemical engineers. It defines machine learning as using past experience to improve decision making by discovering patterns in large amounts of data. The document outlines various machine learning algorithms like supervised, unsupervised, and reinforced learning. It discusses applications of machine learning in areas like process monitoring, soft sensing, and parameter optimization. Finally, it provides examples of machine learning applications in oil refineries and process monitoring.

Uploaded by

sdsdsd
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
43 views22 pages

Lecture 1

This document provides an introduction to machine learning for chemical engineers. It defines machine learning as using past experience to improve decision making by discovering patterns in large amounts of data. The document outlines various machine learning algorithms like supervised, unsupervised, and reinforced learning. It discusses applications of machine learning in areas like process monitoring, soft sensing, and parameter optimization. Finally, it provides examples of machine learning applications in oil refineries and process monitoring.

Uploaded by

sdsdsd
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 22

Machine Learning for Chemical Engineers

CHE F315

Ajaya Kumar Pani


BITS Pilani Department of Chemical Engineering
B.I.T.S-Pilani, Pilani Campus
Pilani Campus
Lecture-1
10-01-2024
BITS Pilani
Pilani Campus
Introduction
BITS Pilani
Pilani Campus
CHE F315 Machine Learning for Chemical Engineers

Outline

What is Machine Learning


Applications
Why in Chemical Engineering
Hand-out

16 January 2024 4
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers

What is Machine Learning


Certain tasks are difficult to program by hand
How are you?

All learning problems can be formulated as mappings (complex)


between inputs and outputs
Mathematically, we search for a good function F: I → O
This function can be derived from available data
Data
Both I and O
Only I
No O but we can get measure of O quality produced by model

16 January 2024 5
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers

What is Machine Learning

Use of past experience in decision making


Use of historical data to discover patterns and improve
decision making
When there is excess data, learning must be automatic
ML technology  automatic learning from voluminous data

Output Prediction
Classification
Data ML Algorithm Pattern recognition
--
--

16 January 2024 6
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers

What is Machine Learning

Data
In the form of table (matrix)
Rows –
instances/samples/measurements/observations/records/
patterns/objects/events
Columns –
attributes/variables/features

16 January 2024 7
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers

16 January 2024 8
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers

Types of Machine Learning


Algorithms
Machine
learning
algorithms

Supervised Unsupervised Semisupervised Reinforced

Feature
Classification
extraction

Regression Clustering

16 January 2024 9
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers

AI Vs ML

Machine learning is a subset of the broader category of AI


AI refers to the general ability of computers to emulate
human thought and intelligence
ML refers to the technologies and algorithms that enable
systems to identify patterns and make decisions by
learning from data

16 January 2024 10
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers

16 January 2024 11
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers

Applications
Spam filter
Biometric/Handwriting/Speech/Text recognition
Image processing
Stock market forecasting/demand forecasting
Medical diagnostics
Drug discovery and optimization
Bioinformatics
Robotics and automation
--
--

16 January 2024 12
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers

Why in Chemical Engineering

• Chemical engineering is usually a data-rich field that


offers opportunities to exploit data science and machine
learning techniques for improved automation,
profitability, product quality maintenance, reduced
emissions and downtimes for several industrial
processes.
• There is a need to evaluate the potential of this new
wave of machine learning to influence the process
systems field
• Fourth industrial revolution call for a combination of
expertise in chemical engineering and information
technology(AI/ML/Data science)

16 January 2024 13
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers

Why in Chemical Engineering

• Third industrial revolution (analog  digital)


• Advanced instrumentation, data storage
• No utilization of available huge process data except some routine technical
checking
• Modern process industries are data rich and information poor

• Fourth industrial revolution (Industry 4.0)


Stringent emission norms, minimum tolerance on product quality, advanced process
control
• Intelligent manufacturing
• Cyber physical system
• Internet of things
• Smart factories

16 January 2024 14
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers

Why in Chemical Engineering

• Modern processes are quite complex (difficult to develop


first principle models)
• Solution??  why not utilize the huge amount of data
available in the historical database
• Data mining and analytics is a tool for transformation
from machine automation  information automation
• Analyze patterns of process data and relationships
among variables to extract useful information  develop
models from data [Statistical/AI (soft computing)]

16 January 2024 15
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers

Why in Chemical Engineering

Data driven
process
modeling

Process
Soft sensing of Parameter
monitoring/fault
key variables optimization
detection

16 January 2024 16
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers

Applications

Prediction of molecular properties from structures


Prediction and optimization of reaction outcome and
reactor performance based on the reaction conditions
(e.g., reagents, catalysts, solvents, reactants,
products,flow rate, temperature, and pressure)
Understanding flow patterns
Understanding catalytic mechanisms
Prediction of process response to control actions

16 January 2024 17
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers

Example

Ferreira, J., Pedemonte, M., & Torres, A. I. (2022). Development of a machine learning-
based soft sensor for an oil refinery’s distillation column. Computers & Chemical
Engineering, 161, 107756.
16 January 2024 18
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers

Example

Zhu, Q. X., Wang, X. W., Li, K., Xu, Y., & He, Y. L. (2022). Enhanced multicorrelation block
process monitoring and abnormity root cause analysis for distributed industrial process:
A visual data-driven approach. Journal of Process Control, 118, 1-15.

16 January 2024 19
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers

Popular journals in this field


IEEE Transactions on industrial informatics
IEEE Transactions on Industry Applications
IEEE Transactions on Automation Science and Engineering
Applied Soft Computing
ISA Transactions
Computers and Industrial Engineering
Computers in Industry
Computers & Chemical Engineering
Engineering Applications of Artificial Intelligence
Journal of Industrial Information Integration
Digital Chemical Engineering
Journal of Advanced Manufacturing and Processing

16 January 2024 20
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers

Handout

16 January 2024 21
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers

16 January 2024
22 BITS Pilani, Pilani Campus

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy