BANGALORE

BANGALORE INSTITUTE
INSTITUTEOF OF
TECHNOLOGY
TECHNOLOGY
Department of Mechanical
Department Engineering
of Mechanical Engineering

MACHINE LEARNING IN
MECHANICAL DESIGN
Internal Guide:
Dr. M.K PRASANNA KUMAR
Associate Professor
Department of Mechanical Engineering
Bangalore Institute of Technology, Bengaluru-04

NAME OF THE STUDENT

Vineet Prakash
1
USN 1BI18ME153
 BANGALORE
BANGALORE INSTITUTE
INSTITUTEOF OF
TECHNOLOGY
TECHNOLOGY
Department of Mechanical
Department Engineering
of Mechanical Engineering

Content

1. Introduction
2. Manufacture Industry
3. Mechanical design
4. Autonomous cars
5. Conclusion

NAME OF THE STUDENT

Vineet Prakash
2
USN 1BI18ME153
 BANGALORE
BANGALORE INSTITUTE
INSTITUTEOF OF
TECHNOLOGY
TECHNOLOGY
Department of Mechanical
Department Engineering
of Mechanical Engineering

INTRODUCTION
Artificial Intelligence especially machine learning and deep learning is
becoming an important tool in the fields of materials and mechanical
engineering, attributed to its power to predict materials properties,
design new materials and discover new mechanisms. As the structural
complexity soars, the material design problem to optimize mechanical
behaviors can involve massive design spaces. Addressing this challenge,
ML models trained from large material datasets have offered fast
exploration of the design spaces.

NAME OF THE STUDENT

Vineet Prakash
3
USN 1BI18ME153
 BANGALORE
BANGALORE INSTITUTE
INSTITUTEOF OF
TECHNOLOGY
TECHNOLOGY
Department of Mechanical
Department Engineering
of Mechanical Engineering

WHAT IS IT
ALL
ABOUT?

NAME OF THE STUDENT Vineet Prakash 4

USN 1BI18ME153
 BANGALORE
BANGALORE INSTITUTE
INSTITUTEOF OF
TECHNOLOGY
TECHNOLOGY
Department of Mechanical
Department Engineering
of Mechanical Engineering

HOW DO MACHINES LEARN?

Machine learning uses programmed
algorithms that receive and analyse
input data to predict output values
within an acceptable range. As new
data is fed to these algorithms,
they learn and optimise their
operations to improve performance,
developing ‘intelligence’ over time.

NAME OF THE STUDENT

Vineet Prakash
5
USN 1BI18ME153
 BANGALORE
BANGALORE INSTITUTE
INSTITUTEOF OF
TECHNOLOGY
TECHNOLOGY
Department of Mechanical
Department Engineering
of Mechanical Engineering

NAME OF THE STUDENT Vineet Prakash 6

USN 1BI18ME153
 BANGALORE
BANGALORE INSTITUTE
INSTITUTEOF OF
TECHNOLOGY
TECHNOLOGY
Department of Mechanical
Department Engineering
of Mechanical Engineering

DIFFERENT ML
ALGORITHMS

Vineet Prakash
NAME OF THE STUDENT 7
USN 1BI18ME153
 BANGALORE
BANGALORE INSTITUTE
INSTITUTEOF OF
TECHNOLOGY
TECHNOLOGY
Department of Mechanical
Department Engineering
of Mechanical Engineering

ML IN
MANUFACTURING
• Quality Checks
• Prediction of failure modes
• Predictive maintenance
• Generative Design
• Making use of data
• Price forecast

NAME OF THE STUDENT Vineet Prakash 8

USN 1BI18ME153
 BANGALORE
BANGALORE INSTITUTE
INSTITUTEOF OF
TECHNOLOGY
TECHNOLOGY
Department of Mechanical
Department Engineering
of Mechanical Engineering

ML IN DESIGN

• Prediction of mechanical behaviors

• Designing topological structures of multi-phase materials such as
composites or architected materials.
• Development of new computational methods

NAME OF THE STUDENT

Vineet Prakash 1BI18ME153
9
USN
 BANGALORE
BANGALORE INSTITUTE
INSTITUTEOF OF
TECHNOLOGY
TECHNOLOGY
Department of Mechanical
Department Engineering
of Mechanical Engineering

With material problem in mind

•Researchers encode their domain
knowledge into the pre-processing of the
data collected resulting in input data
•Data is collected from the literature,
existing databases, high-throughput
experiments and simulations
•ML model is prepared which is able to
predict mechanical behaviors and/or provide
novel designs of the mechanical materials
Schematic of a typical workflow for design of mechanical
materials using ML.

NAME OF THE STUDENT Vineet Prakash 10

USN 1BI18ME153
 BANGALORE
BANGALORE INSTITUTE
INSTITUTEOF OF
TECHNOLOGY
TECHNOLOGY
Department of Mechanical
Department Engineering
of Mechanical Engineering

Predicting dynamical fracture using a

deep learning approach, dependent
on microstructural details. (a)
Workflow of fracture patterns
prediction. (b) Comparison of crack
path, length and energy release
between molecular simulations and
the ML approach. (c) Prediction of
crack patterns in bicrystalline and
gradient materials 

NAME OF THE STUDENT Vineet Prakash 11

USN 1BI18ME153
 BANGALORE
BANGALORE INSTITUTE
INSTITUTEOF OF
TECHNOLOGY
TECHNOLOGY
Department of Mechanical
Department Engineering
of Mechanical Engineering

Data-driven design of super-

compressible and recoverable
metamaterials using Bayesian
machine learning

NAME OF THE STUDENT Vineet Prakash 12

USN 1BI18ME153
 BANGALORE
BANGALORE INSTITUTE
INSTITUTEOF OF
TECHNOLOGY
TECHNOLOGY
Department of Mechanical
Department Engineering
of Mechanical Engineering

ML IN SELF DRIVE
CARS
Driverless cars can identify
objects, interpret situations,
and make decisions based on
object detection and object
classification algorithms. ML
algorithms are trained to
make the right decisions
when navigating the roads.

NAME OF THE STUDENT Vineet Prakash 13

USN 1BI18ME153
 BANGALORE
BANGALORE INSTITUTE
INSTITUTEOF OF
TECHNOLOGY
TECHNOLOGY
Department of Mechanical
Department Engineering
of Mechanical Engineering

ML algorithms used by self-driving cars

• SIFT - Scale-invariant feature
transform algorithms detect objects
and interpret images

• AdaBoost – Data Classification

algorithm. It groups different low-
performing classifiers to get a
single high-performing classifier
for better decision-making.

NAME OF THE STUDENT Vineet Prakash 14

USN 1BI18ME153
 BANGALORE
BANGALORE INSTITUTE
INSTITUTEOF OF
TECHNOLOGY
TECHNOLOGY
Department of Mechanical
Department Engineering
of Mechanical Engineering

• TextonBoost for object recognition -

It receives data from shape, context,
and appearance to increase learning
with textons (micro-structures in
images). It aggregates visual data with
common features.

• Histogram of oriented gradients

(HOG) - HOG facilitates the analysis
of an object’s location, called a cell, to
find out how the object changes or
moves.

NAME OF THE STUDENT Vineet Prakash 15

USN 1BI18ME153
 BANGALORE
BANGALORE INSTITUTE
INSTITUTEOF OF
TECHNOLOGY
TECHNOLOGY
Department of Mechanical
Department Engineering
of Mechanical Engineering

• YOLO (You Only Look Once) -

Detects and groups objects like
humans, trees, and vehicles. It assigns
specific features to each class of object
that it groups to help easily identify
them.
• Wrap up - Allows a car to collect data
on its surroundings from cameras and
other sensors, interpret it, and decide
what actions to take. Helps to perform
these tasks as good as (or even better
than) humans.

NAME OF THE STUDENT Vineet Prakash 16

USN 1BI18ME153
 BANGALORE
BANGALORE INSTITUTE
INSTITUTEOF OF
TECHNOLOGY
TECHNOLOGY
Department of Mechanical
Department Engineering
of Mechanical Engineering

CONCLUSION
•The long term goal of machine learning systems is to override the processes that can
be assimilated into an algorithm.
•It will reduce the number of jobs and tasks for designers to do.
•Machine learning systems will remove repetitive or boring tasks from a designers
brief.
•It will allow them to focus on actual challenges, improving their designs and
techniques along the way.

NAME OF THE STUDENT Vineet Prakash 17

USN 1BI18ME153
 BANGALORE
BANGALORE INSTITUTE
INSTITUTEOF OF
TECHNOLOGY
TECHNOLOGY
Department of Mechanical
Department Engineering
of Mechanical Engineering

THANK YOU

NAME OF THE STUDENT

Vineet Prakash
18
USN 1BI18ME153