Applications of Machine Learning in Mechanical Engineering: September 2021

This document discusses applications of machine learning in mechanical engineering. It describes three common types of machine learning (supervised, unsupervised, reinforcement learning) and gives examples of each. The document also discusses challenges mechanical engineers face and how machine learning can help with predictive maintenance, generative design, and the Internet of Things in applications like smart factories. Machine learning is presented as a promising solution to many problems mechanical engineers encounter.

Uploaded by

asdf ghjkl

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)

100 views

Applications of Machine Learning in Mechanical Engineering: September 2021

Uploaded by

asdf ghjkl

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/ 4

See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/354653455

APPLICATIONS OF MACHINE LEARNING IN MECHANICAL ENGINEERING

Article · September 2021

CITATIONS READS

0 334

1 author:

Mohammed Wais
IU International University of Applied Sciences
4 PUBLICATIONS 0 CITATIONS

SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Change manangement View project

All content following this page was uploaded by Mohammed Wais on 17 September 2021.

The user has requested enhancement of the downloaded file.

APPLICATIONS OF MACHINE LEARNING IN MECHANICAL
ENGINEERING

Mohammed Wais

Abstract: Mechanical engineers are facing many challenges that come from
making decision about design, operations, and maintenance. Here is this article we
take a brief view of some cases that used machine learning.

Keywords: Machine learning, Mechanical Engineering, IoT , Smart Factory

What is Machine Learning?

Machine learning is a set of many algorithms and techniques that is utilized to

design system able to learn from data. Traditional programming inputs data and
program to get the output. In machine learning computers take data and output to
produce a program. Machine leaning is based on firm foundation of knowledge in
following disciplines (Lee, 2019):

 Scientific computing.
 Mathematics.
 Statistics.

There are three common types of machine learning (The types of machine learning,
n.d.):

• Supervised Learning: we train the model here by giving an input, e.g.

a photo of crack or damage and the goal is to predict the correct output
by confirming if it is true or false.
• Unsupervised Learning: here are no determined outputs to train the
model based on, rather than we are looking to discover the data
structure. e.g. warranty segments.
• Reinforcement Learning: this type is commonly used where it is
required to go along with feedback. Self-driving is good example
where we can find this type of machine learning.

Challenge in front of Mechanical Engineers

Covid-19 affects whole the world for two years (2020 and 2021), the pandemic
made it necessary to force mechanical engineers to find solution through rapid design
process of mechanical ventilator. The problem has facets; decrease the cost and
increase the efficiency. 3D printing has come as solution for this problem by
providing quickly and cheaply production. (Karthikeyan, Shashi, Raju, & Abhishek,
2021). In other hand, self-driving car is still a dilemma in automobile industry. A lot
Researches are still in process regarding to it.

Machine Learning: The turnkey solution

Predictive maintenance is technique to help to provide a feedback about the
condition of equipment that in service. This process is required to estimate when then
next maintenance is going to be. Machine learning is used to keep the work simple
by providing prediction approaches. (Susto, Schirru, Pampuri, McLoone, & Beghi,
2012).

Generative design is iterative process that is used to explore the options for
design, engineers input design goals along with parameters such performance, color,
material, weight, manufacturing methods, and cost constrains. Output is many
options those could be used. (Autodesk, 2012)

IoT or “Internet of Things” are very important features of Industry 4.0. It

visualize physical objects in digital domain. This is done though embedded sensors
and models which working together in collaborative manner to enhance the ability
of the system. Smart factory is good example for IoT (Gillis, n.d.).
Conclusion
Machine learning can be the turnkey solution for many challenges that faces
mechanical engineers. While there still many researches in this field, there are many
promising applications in predictive maintenance, generative design , and IoT.

References
Autodesk. (2012, September 17). GENERATIVE DESIGN. Retrieved from
https://www.autodesk.com/solutions/generative-design
Gillis, A. S. (n.d.). What is internet of things (IoT)? Retrieved September 17, 2021,
from https://internetofthingsagenda.techtarget.com/definition/Internet-of-
Things-IoT
Karthikeyan, I., Shashi, B., Raju, V., & Abhishek, V. (2021, September 17).
Challenges and solutions in meeting up the urgent requirement of ventilators
for COVID-19 patients. Retrieved from
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7198404/
Lee, W.-M. (2019). What is Machine Learning? In Python Machine LEarning.
Wiley.
Susto, G. A., Schirru, A., Pampuri, S., McLoone, S., & Beghi, A. (2012, September
17). Machine Learning for Predictive Maintenance: A Multiple Classifier
Approach. Retrieved from https://ieeexplore.ieee.org/document/6879441
The types of machine learning. (n.d.). Retrieved September 17, 2021, from
https://course.elementsofai.com/4/1