Crimson Publishers Mini Review

Wings to the Research

Application of Machine Learning to

Frontiers in Mechanical Engineering
Mahesh S1, Anil Chandra AR1, Ravikumar L1 and Srivatsan TS2*
1
Department of Mechanical Engineering, BMS College of Engineering, Bangalore, India
2
Department of Mechanical Engineering, The University of Akron, USA
ISSN: 2640-9690
Abstract
Mechanical engineering has over the years evolved from mere “chassis-on-wheels” to “luxury-on-move”
with the introduction of advanced design and manufacturing sectors, such as additive manufacturing,
Computer-Numerically Controlled (CNC), mechatronics, robotics and more recently the Internet-of-
Things (IoT). However, challenges in terms of optimizing the process parameters, selection of materials,
standardization of the processes used and quality control, have gained increased importance and
attention. Hence, a multi-disciplinary approach involving both data science and data analytics have helped
in synergizing the application of Machine Learning (ML) techniques to address the aforementioned
challenges. In recent years, several technical publications have surfaced in this direction and show much
promise and excitement towards a future which will essentially be “intelligence-on-the-move”. In this
technical paper, an attempt is made to look at the current scenario in terms of application of machine
learning to the various sectors in the field of mechanical engineering.
Keywords: Additive manufacturing; Machine learning; Data mining; Quality control

*Corresponding author: Srivatsan TS,

Department of Mechanical Engineering, Introduction
The University of Akron, USA
The origin of human use of fire is unknown but evidence specific to the use of fire dates
Submission: April 13, 2024 back to at least over a million years. Initially what began as a source of protection did eventually
Published: May 20, 2024
lead to both fueling the economy and concurrently revolutionizing the landscape of every
Volume 5 - Issue 3 aspect on this planet up until the current day. It is certain that initially there was little scientific
knowledge and the numerous intricacies specific to heat transfer and thermodynamics.
How to cite this article: Mahesh S, However, there definitely did exist some logical understanding of an object being either hot
Anil Chandra AR, Ravikumar L and
Srivatsan TS*. Application of Machine or cold. These observations in synergism with a series of experiments eventually motivated
Learning to Frontiers in Mechanical the people involved to take advantage of these processes over time for the primary purpose
Engineering. Evolutions Mech Eng. 5(3). of increasing human comfort. Similarly, is the case with the other elements of nature resulting
EME.000613. 2024.
in the emergence and growth of concepts, such as (i) hydraulics and pneumatics, (ii) fluid
DOI: 10.31031/EME.2024.05.000613
mechanics, and (iii) fluid dynamics, to name just a few. Throughout this course of evolution,
Copyright@ Srivatsan TS, This article is man has seen various stages of development. Methods similar to subtractive manufacturing
distributed under the terms of the Creative were developed and used to shape stones as tools in the era of the stone age. With better
Commons Attribution 4.0 International
License, which permits unrestricted use understanding coupled with an application of improved processing techniques specific
and redistribution provided that the to metals did result in a spectrum of advanced machining operations that are in use today.
original author and source are credited. More observations and better understanding of the material along with material behavior
did eventually result in alloying, casting, forging and other aspects of materials science and
metallurgy. Invention of the wheel, lever mechanism, concepts of pulleys, screw, and the gear
mechanism did result in the design of complex drive-trains and the emergence and acceptance
of concepts specific to both kinematics and dynamics.

A continuous sharing of knowledge gained over the centuries did result in integrated
research along with massive scale of development culminating in establishing both a better
design and manufacturing. It is obvious that the core knowledge specific to science and
mathematics has significantly elevated each of these fields of study to levels never imagined
before. The invention of an analytical engine did transform the eco-system of science and
engineering by speeding up the progress. A machine that used to perform simple calculations

Evolutions in Mechanical Engineering 1

 EME.000613. 5(3).2024 2

has transformed both itself and the world to a stage where being continuously developed for the purpose of practical use to
arguments of it being sentient is not applicable. This transformation achieve useful methods of learning. Data mining engineers have
did fuel and carry every other field of science and technology, used Machine Learning (ML) algorithms to find and extract useful
which in turn has led to its development and exciting emergence. data from large commercial databases that contain the following: (i)
An increased power of computation did introduce new avenues of process information, (ii) equipment and maintenance information,
science and engineering that enabled critical evaluation and newer (iii) medical records, (iv) financial records, and few others [1]. The
ways of thought process coupled with an approach to various current or ongoing research being actively pursued in the domain
problems. Techniques, such as finite element methods and fracture specific to mechanical engineering can be broadly grouped under
mechanics, were integrated into engineering design. Concepts these categories:
specific to (i) automation, (ii) inspection, (iii) quality control, and
Additive manufacturing
(iv) design of experiments, did bring about noticeable changes in
the manufacturing sector. Additive Manufacturing (AM), or 3-D printing, has enabled
a revolution in engineering due to its unique “user friendly
Today, both Artificial Intelligence [AI] and Machine Learning [ML]
approach”. Production of customized products on-demand is a
are gradually taking over the world. Machine learning can be safely
noteworthy advantage of the Additive Manufacturing process over
categorized to be an inter-disciplinary field of statistics, computer
the conventional subtractive manufacturing process. It allows
science and mathematics that is both concerned and involved in
for the physical components to be made from virtual Three-
building algorithms from the data fed to the machine(computer).
Dimensional (3D) computer models by successfully building the
The machine aids in identifying the dependencies of the various
component layer-by-layer until the part is complete [2-5]. The
parameters of any random process, with the patterns identified
American Society for Testing and Materials (ASTM) F42 has broadly
in the data. Similar to various other inventions the inspiration for
listed the following under the category of AM processes: (i) VAT
Machine Learning (ML) was taken from nature coupled with the
photopolymerization, (ii) material jetting, (iii) binder jetting, (iv)
cognition capability of animal brain, which continuously learns
powder bed fusion, (v) material extrusion, (vi) sheet lamination,
and improves its decision-making ability based on experience.
(vii) direct energy deposition. and (viii) robotics, can result in
The ability of Machine Learning (ML) to automate a task and make
realizing the industry 5.0. However, a number of challenges arise
surprisingly accurate predictions did result in the following:
not only from the complexity specific to manufacturing systems
A. Predictive analytics but the concurrent demand for increasing complexity and high-
quality products, in terms of the following: (i) design principles,
B. Recommendation systems
(ii) standardization and (iii) quality control. Integrating additive
C. Image recognition and computer vision manufacturing (AM) with artificial intelligence (AI) / machine
learning (ML) does certainly seem to be the future for the purpose
D. Natural language processing
of addressing these challenges and well-reviewed in the published
E. Anomaly detection and fraud prevention literature [6-9].
F. Drug discovery and medical diagnosis Robotics and automation
G. Personalized learning and education Integrating digital technology to manufacturing and
industrial processes is the current trend. This is made possible
H. Financial forecasting and trading
by implementing Artificial Intelligence (AI) powered robots for
I. Scientific discovery and research in the field of robotics a spectrum of processing-related tasks. Automation of various
repetitive tasks coupled with tasks that could prove to be dangerous
J. Other automation
for humans by the introduction of robots could contribute to
K. Various creative and artistic tasks increasing the productivity while concurrently ensuring a safe
This review paper does provide a clean, clear and cohesively working environment. Applications of Machine Learning (ML) in
complete overview of the various possible applications of Machine advanced robotics has made possible the following: (i) autonomous
Learning (ML) in mechanical engineering. navigation, (ii) object recognition and manipulation, (iii) natural
language processing, (iv) predictive maintenance, (v) optimizing
Current Research in Mechanical Engineering robotic manufacturing, (vi) military robotics, (vii) service robots,
From the previous discussion it is clear that mechanical and (viii) robotic surgery possible [10]. A visual of AI powered
engineering is an ever-evolving and constantly adapting field that robots in the industry is as shown in Figure 1. An Internet-of-Things
attempts to embrace new challenges and opportunities. Artificial [IoT]-based implementation monitoring energy consumption
Intelligence [AI] can cater to all of the problems currently prevailing in machines and appliances coupled with prediction of future
and even more. All the data that has been collected over the years anomalous behavior using decision tree algorithm providing 78%
can be valuable in classifying, clustering, predicting and automating efficiency in the prediction was reported by Sujatha and co-workers
the numerous processes in various sectors. Many algorithms are [11,12].

Evolutions Mech Eng Copyright © Srivatsan TS

 EME.000613. 5(3).2024 3

Figure 1: Applications of Artificial Intelligence (AI) powered robots [11].

Unmanned vehicles: Aerospace industry is always at the short distance commuting. A drone delivery system in action is
fore-front of all technologies and innovation. The current research shown in Figure 2. This eases both the effort and requirement for
focuses on building technologies for faster and safer travel across man-power that could be put to effective use elsewhere. Sensing
the globe and beyond. The recent endeavor specific to space travel technologies, such as (i) image sensing, (ii) acoustic sensing, (iii)
did introduce new avenues to reduce the cost while concurrently radar, and (iv) lidar, are being increasingly used with an integration
increasing safety of the passengers. Use of sustainable energy, of the machine learning (ML) algorithms, such as (i) CNN, (ii) auto-
sustainable materials and implementing innovative methods of encoders, (iii) DBN, and (iv) reinforcement learning, to achieve
damage tolerance design and structural health monitoring is of the following: (i) Navigation. (ii) Object recognition, (iii) Scene
prime focus. Driverless cars and robotic delivery systems are also classification, (iv) Path planning, and (v) Feature extraction [13,14].
being introduced in certain parts of the world for the purpose of

Figure 2: Artificial Intelligence-based robotic delivery system in action [14].

Evolutions Mech Eng Copyright © Srivatsan TS

 EME.000613. 5(3).2024 4

Sustainable energy: Depleting fossil fuels in synergism with a) Based on type of prediction the algorithm is supposedly
increasing pollution and global warming have provided the much- going to make, and
needed incentive while concurrently demanding newer, renewable
b) Based on the type of data fed to the algorithm for training.
and sustainable energy sources. Solar, wind, tidal energy has
always been abundantly available but harnessing it for everyday Both these classifications are shown in Figure 3. In the first type
use often gets increasingly expensive and complicated. Therefore, of classification, the ML algorithms are used for either classification
the hunt for newer and novel technologies to both harness and or regression tasks. When the algorithm predicts the outcome as
extract power are the vital current generation problems specific to one of the predetermined classes based on the patterns identified
research. Search for alternate ways to power automobiles is also in the data then it is referred to as classification algorithm. In the
another thriving area of research currently centered around the use case of regression algorithms, the patterns identified are used to
of hydrogen power. Therefore, search for cleaner and eco-friendly predict a continuous value. Similarly, the other classification for
technologies did capture the focus of scientists and researchers Machine Learning (ML) algorithms are the supervised learning
towards sustainable materials. Ahmad and co-workers have algorithms and unsupervised learning algorithms. The supervised
proposed the use of smart power grids developed using Machine learning algorithms are fed with training data wherein both
Learning (ML) techniques in synergism with smart meters and the input and the output are available. However, for the case of
sensors providing real-time energy consumption. Further, the unsupervised learning, the input data fed to the algorithm for the
smart grid mitigates issues specific to failure of the grid, thereby purpose of training are only the input parameters. In this case,
enabling users to avoid service interruptions. Also, energy forecast clusters are formed based on the identified patterns in the data
made using neural network-based models can be used to conserve to make further prediction. Each of the algorithms in Machine
both energy and resources in the event or need for renewable Learning [ML] identify and form a unique representation from the
energy generation [15]. patterns identified in the data. These representations are adopted
from the various concepts of mathematics and statistics, such as
Structural health monitoring
(i) linear algebra, (ii) probability and information theory, and (iii)
Structural Health Monitoring (SHM) is a process of extensively other basic numerical computations. The algorithms based on (i)
and continuously assessing the health and integrity of structural Bayesian learning, (ii) Decision trees, (iii) Instance-based learning,
components. The sole purpose of Structural Health Monitoring (iv) Genetic algorithms, (v) Reinforcement learning, and (vi) Deep
(SHM) is to detect and diagnose any damage, or deterioration, in learning (DL) are often used. Various restrictions and drawbacks of
the structure before it reaches a critical stage that often culminates regular machine learning algorithms are overcome by using deep
in failure. Major focus of structural health monitoring (SHM) learning (DL) algorithms. Artificial neural networks (ANN) are
includes the following: (i) aero-space, (ii) naval, (iii) nuclear, and the core of Deep Learning. Neural networks, such as (i) the back
(iv) predictive maintenance. Adopting SHM techniques has proven propagation neural networks, (ii) radial basis function network, (iii)
to be beneficial as it led to the following: (i) optimized design, (ii) extreme learning machine, and (iv) convolutional neural networks
reduced maintenance cost, (iii) extended service life, and even (iv) are currently being chosen for use in various applications in the
improved safety. Machine Learning (ML) integrated inspection for domain of the field of mechanical engineering. Combinations of
the purpose of SHM in pipelines does have the capability to pin- multiple algorithms are being used for research to achieve certain
point the location of defect, while earlier an inspection gauge had representations that would be difficult for any of the standard
to be manually moved through the entire length of the pipeline algorithms to achieve [2-5].
to identify and/or locate a defect [16]. Machine Learning (ML)
algorithms are being used at every stage of Structural Health
Monitoring (SHM), i.e., damage detection, damage assessment and
damage prediction [16-19]. The Machine Learning (ML) models are
being increasingly used for the purpose of predictive maintenance
in the manufacturing industry by monitoring the vibration in
machine drives and shafts. Figure 3: Categories specific to classification of
Popular algorithms machine learning.

Machine learning is rapidly transforming the field of Conclusion

mechanical engineering, providing powerful tools for design, A. This technical manuscript provides a cohesively complete
analysis, and optimization across a wide range of applications. summary of Machine Learning (ML) technologies that are
Its ability to analyze large datasets, identify patterns, and make currently on demand and their integration with various core
useful predictions is proving to be invaluable for the following: problems in the field of ever-evolving mechanical engineering.
(i) optimizing processes, (ii) enhancing product performance and
B. The discussions provided also highlight the capability and
(iii) solving complex engineering problems. Machine Learning
potential of Machine Learning (ML) in solving these problems.
(ML) algorithms in general can be categorized into two separate
classifications: C. It is certain that an implementation of Machine Learning

Evolutions Mech Eng Copyright © Srivatsan TS

 EME.000613. 5(3).2024 5

(ML) can improve the current technologies by several order 8. Carrio Adrian, Carlos Sampedro, Alejandro Rodriguez R, Pascual
while concurrently reducing the risk and burden of several Campoy (2017) A review of deep learning methods and applications for
unmanned aerial vehicles. Journal of Sensors 2017: 13.
professions, and thereby creating a safe working environment.
9. Kocić Jelena, Nenad Jovicic, Vujo Drndarević (2019) An end-to-end
D. The techniques of Machine Learning (ML) also ensure an deep neural network for autonomous driving designed for embedded
efficient use of energy, resources and available capital thereby automotive platforms. Sensors 19(9): 2064.
improving the stability of both the process and the organization. 10. Ahmad Tanveer, Rafael Madonski, Dingdong Zhang, Chao Huang, Asad
Mujeeb (2022) Data-driven probabilistic machine learning in sustainable
E. Overall, it is evident that the ongoing era of Machine smart energy/smart energy systems: Key developments, challenges and
Learning (ML) integrated technologies in emerging frontiers of future research opportunities in the context of smart grid paradigm.
Renewable and Sustainable Energy Reviews 160: 112128.
mechanical engineering is promising a simpler, easier, efficient
and well-connected “intelligence-on-move” environment for 11. Saurabh Z, Tushar J, Bishakh B (2019) Application of wavelet analysis
and machine learning on vibration data from gas pipelines for structural
humanity.
health monitoring. Procedia Structural Integrity 14: 712-719.
References 12. Bao Tuan Pham, Vein Le Ngoc, Luan Vuong C, Nhi Ngo K (2023) Damage
1. Mitchell TM (2019) Machine learning. (1st edn), McGraw Hill Education, assessment in beam-like structures by correlation of spectrum using
USA, p. 432. machine learning. Fracture and Structural Integrity 17(65): 300-319.

2. Jian Qin, Fu Hu, Ying Liu, Paul Witherell, Charlie CL, et al. (2022) Research 13. Renuka VP, Sornalatha S, Roopsta DM, Ashokan R (2022) Prediction of
and application of machine learning for additive manufacturing. Additive fatigue crack growth of aluminum alloy 7075t6 using machine learning
Manufacturing 52: 102691. techniques 14(1): 99-104.

3. Wang C, Tan XP, Tor SB, Lim CS (2020) Machine learning in 14. Zhang L, Wang Z, Wang L, Zhang Z, Chen X, et al. (2021) Machine
additive manufacturing: State-of-the-art and perspectives. Additive learning-based real-time visible fatigue crack growth detection. Digital
Manufacturing 36: 101538. Communications and Networks 7(4): 551-558.

4. Sachin Kumar, Gopi T, Hari Keerthana N, Munish Kumar G, Vidit Gaur, 15. Liu, Jiantao, Xiaoxiang Yang (2018) Learning to see the vibration: A
et al. (2023) Machine learning techniques in additive manufacturing: neural network for vibration frequency prediction. Sensors 18(8): 2530.
A state of the art review on design, processes and production control.
16. Espinoza Sepúlveda, Natalia F, Jyoti K Sinha (2021) Blind application
Journal of Intelligent Manufacturing 34: 21-55.
of developed Smart Vibration-Based Machine Learning (SVML) model
5. Grierson D, Rennie AEW, Quayle SD (2021) Machine learning for additive for machine faults diagnosis to different machine conditions. Journal of
manufacturing. Encyclopedia 1: 576-588. Vibration Engineering & Technologies 9: 587-596.

6. Soori Mohsen, Behrouz Arezzo, Rosa Dastres (2023) Artificial 17. Umbrajkaar AM, Krishnamoorthy A, Dhumale RB (2020) Vibration
intelligence, machine learning and deep learning in advanced robotics: analysis of shaft misalignment using machine learning approach under
A review. Cognitive Robotics 3: 54-70. variable load conditions. Shock and Vibration 2020: 1-12.

7. Sujatha M, Priya N, Beno A, Blesslin Sheeba T, Manikandan M, et al. 18. Josh Patterson AG (2017) Deep learning: A practitioner’s approach. (1st
(2022) IoT and machine learning-based smart automation system for edn), Shroff/O’Reilly, India, p. 532.
industry 4.0 using robotics and sensors. Journal of Nanomaterials 2022:
19. Ian G, Yoshua B, Aaron C (2018) Deep learning.
6.

Evolutions Mech Eng Copyright © Srivatsan TS