ai in manufacturing b.techd dsadad da .ppt

ai in manufacturing

1. Artificial Intelligence in Manufacturing
Supervisor By

Dr. Arvind Jayant(Professor) Vivek Mishra
Mechanical Engineering Department PME/2105
SLIET, Longowal

2. CONTENT
1.Introduction
2.What is Artificial Intelligence
3.Research Steps
4.Scope of AI in Mechanical Engineering
5.Industry 4.0
6.Condition-Monitoring
7.Application
8.Research Gap
9.Problem Statement
10.Objective
11.Methodology
12.Literature Survey
13.Work Schedule
14.References

3. 1. INTRODUCTION

4. 1.0 What is Artificial Intelligence (AI)
The word "Artificial Intelligence" first adopted by American Computer scientist John
McCarthy at the Dartmouth Conference in 1956.
Artificial Intelligence (AI) is an umbrella term for
 technologies that enable machines to
mimic human intelligence.
Artificial intelligence plays a vital roll in mechanical engineering as it
 improves the
precision of mechanical manufacturing and automation and originates the concept of
Industry 4.

5. 2.0 Scope of Artificial Intelligence
Natural language processing(NLP)
Vision and speech processing
Robotics
Self driving cars
Theorem proving etc

6. 3.0 Research Steps
Define a
problem
literature
survey
Formulation
of
hypothesis
Prepare
research
design
Data
collection
Data
interpretation
Interpretation
& Report
writing

7. 4.0 Scope of AI in Mechanical
 INDUSTRY 4.0
CIRCULAR ECONOMY
THERMAL
FLUID MECHANICS etc.

8. 5.0 Industry 4.0
•It is a term first coined by the German engineer and economist Klaus Schwab in
2015.
•
=+
•SMART means Data Based Decision
New Innovative
technologies(Artificial
Intelligence, IOT, Cloud
Computing)
Older concepts to new standards
(SMART supply chain, SMART inspection,
SMART manufacturing, and SMART
production)
Industry
4.0

9. 5.0 Industry 4.0 contd.
•Smart Inspection: Visual inspection (Using AI Image Recognition)etc.
•Smart Manufacturing: Robotics process automation[1] etc.
•Smart Supply Chain: Routing product optically and dynamically.

10. 6.0 Condition-monitoring
•Condition-monitoring is an activity used to detect or anticipate the failure.
•Various techniques are implemented for condition monitoring to prevent breakdown of
component and assist in maintenance.
•Failure modes are detected in advance.
•It is feasible to take possible measures to arrest failure so that the consequences of the
failures can be avoided.
Thermal Monitoring
Vibration Monitoring
Acoustic Monitoring
Oil Monitoring

11. •With advancements in computational facilities, it is becoming easier to
acquire and process the data at higher processing rate.
•Most of the acquisition systems are capable of logging real time data
digitally.
•With advancements in technology, many new processing techniques
evolving day by day which help to extract features from the acquired data
to identify the default in the system
Condition monitoring through vibration signal
Signal Processing

12. 7.0 Applications
Fig. 1: Machining
Fig. 2: Gear Box
Fig. 3: Engine
Fig. 4: Pump

13. 8.0 Research Gaps
A limited work has been reported on condition monitoring of the tool using thermal and
vibration analysis.
There is a need to develop a robust Automatic defect identification system based on
artificial intelligence.

14. 9.0 Problem Statement
•It is proposed to develop a real time fault identification system for machining tool making use
of thermal, vibration signal and artificial intelligence. Effect of defects in chattering on thermal
and vibration signature shall be studied. A suitable signal processing algorithm shall be
investigated to extract weak fault features in the signal. It is expected that the system
developed shall be able to give information of defect type within the machine and its severity
as an output just by placing sensor on the structure.

15. 10.0 Objectives
1.Develop a signal processing algorithm to extract defect features in vibration signal of a
tool while machining.
2.Automatic defect diagnosis for machining tool making use of artificial intelligence with
special emphasis on drilling.
3.Develop vibration-based system through software and hardware for diagnosis of defect
in tool.

16. 11.0 Methodologies

17. 1.Vibration data acquisition for machining (healthy and seeded defect
conditions) in laboratory. It shall be done in LabVIEW environment.
2.Processing of vibration signal by appropriate algorithm to enhance machining
defect features. MATLAB and LabVIEW shall be used for the purpose.
3.Artificial intelligence shall be applied on collected data to identify the classified
faults.
4.Test run shall be performed on actual water turbine in field.

18. 12.0 Literature Review
S.
No
Title Author Year/Journal Conclusion
1.
Application of artificial
intelligence technology in the
manufacturing process and
purchasing and supply
management
Mito Kehayova, Lukas
Holdera, Volker Koch
(2022),Procedia
Computer Science
The manufacturing sector and purchasing and supply management
have the perfect fit for artificial intelligence implementation. While
the revolution of Industry 4.0 is still in its early stages, we are
already seeing major benefits from AI. This technology is intended to
transform forever the way in which we produce goods and manage
materials, from the design process and manufacturing shop floor,
through to the supply chain and administration. In this context it is
essential to state clearly that the broad topic of AI in manufacturing
and purchasing and supply management must be a core element in
the curriculum of higher education institutions for all technical fields
of study to be future-oriented.
2.
Robotic Process Automation
and Artificial Intelligence in
Industry 4.0 – A Literature
review
Jorge Ribeiro*, Rui Lima,
Tiago Eckhardt, Sara Paiva
(2021), Procedia
Computer Science
A set of proprietary tools (UiPath, Kofax, Automation Anywhere and
WinAutomation) and Opensource tools (AssistEdge and Automagica)
were identified, and for each of them a characterization of their RPA
features, their integration with ERPs and support for ERPs was
made. It has been concluded that most of the proprietary tools
implement algorithms associated with the objectives of AI, such as
recognition, optimization, classification and extraction of knowledge
from either RPA documents or processes. It also enhances their
optimization and exploration of the information by the users of
these applications. The AI techniques and algorithms that these
tools implement, focus on computer vision (image recognition using
for example Artificial Neural Networks), statistical methods, decision
trees, neural networks for classification and prediction, fuzzy logic
and implementation of techniques associated with text mining,
natural language processing and recommendation systems.

19. S.
No
Title Author Year/Journal Conclusion
3.
Industrial Artificial
Intelligence for
industry 4.0-based
manufacturing
Systems
Jay Lee, Hossein Davari,
Jaskaran Singh, Vibhor
Pandhare
2018, Society of
Manufacturing Engineers
There is an urgent need for systematic development and implementation
of AI to see its real impact in the next generation of industrial systems,
namely Industry 4.0. In addition, by providing an overview of the
Industrial AI eco-system in today’s manufacturing, this paper aims to
provide a guideline for strategizing the efforts toward realization of
Industrial AI systems.
4.A quantitative
framework for
Industry 4.0 enabled
Circular Economy
Marco Spaltinia,*, Andrea
Polettia, Federica Acerbia,
Marco Taischa
2017, Procedia CIRP The authors could highlight the potentiality of the integration between
the two concepts. It is showed that understanding CE and I4.0
potentialities stay at the basis for maximizing the sustainability value
obtainable from business, since environmental goals need powerful
instruments to manage their intrinsic high complexity. The authors
supported the general awareness about synergies between I4.0 and CE
detailing a concrete and quantitative BM.

20. S.
No
Title Author Year/Journal Conclusion
5
Technology mining:
Artificial intelligence
in manufacturing
Gordana Zeba, Marina
Dabic, Mirjana, Tugrul Daim,
Haydar Yalcin
Technological Forecasting
& Social Change
Research on the topic of AI in manufacturing has intensified since the
emergence of the term ‘Industry 4.0’, the most common areas of research
for both periods are engineering, computer science, and technical areas,
although there has been a growing interest in other areas of research in
recent years, the results indicate that, in the 1979-2010 period, the most
prominent country in terms of its publication of journal articles on AI in
manufacturing was the USA and, from 2011 to 2019, the most prolific
country was the People’s Republic of China and there has been a shift in
research topics in the last few years in the context of Industry 4.0. This
study of existing literature serves as a basis for determining the future
directions of research in the field of AI in manufacturing, especially in the
context of Industry 4.0.
6 Key resources for
industry 4.0
adoption and its
effect on sustainable
production and
circular economy: An
empirical study
Surajit Bag, Gunjan Yadav,
Pavitra Dhamija, Krishan
Kumar Kataria
2020, Journal of Cleaner
Production
The study aspired to develop a theoretical model linking key
resources for I4.0 adoption, sustainable production and circular
economy. The reviews of literature led to identification of thirtyfive
resources that are playing a critical role in adoption of I4.0 in
context to sustainable production environment. This work is an
excellent contribution to the existing body of knowledge as the
research team has extensively identified the resources for sustainable
manufacturing practices. Majority of the discussed factors
falls in line with the guidelines of sustainable developmental goals
suggested by United Nations Developmental program. Production
systems form the core of every manufacturing organization irrespective
of product being produced.

21. S.
No
Title Author Year/Journal Conclusion
7.
Introducing an
application of an
industry 4.0 solution
for circular
supply chain
management
Theofilos D. Mastos,
Alexandros Nizamis, Sofia
Terzi
2021, Journal of Cleaner
Production
The present work evaluated the industry 4.0 solution against the ReSOLVE
model for circular economy in a real-world supply chain. The developed
solution, gives answer to the first research question related to the
deployment of Industry 4.0 and ICT solutions as an enabler for a circular
economy scenario. The ReSOLVE model is used as a key starting point for
the discussion of the results but also as a guiding tool for evaluating the
specific waste-to-energy scenario and answers the second research
question. The results indicate that electricity can be produced by using
different types of wastes such as wood. This circular process that is
monitored in every step has the potential to reduce environmental
impacts caused by the extraction of raw materials and the disposal in
landfills, improving the circular economy.
8.Industry 4.0, cleaner
production and
circular economy: An
integrative
framework for
evaluating ethical
and sustainable
business
performance of
manufacturing
organizations
Himanshu Gupta , Ashwani
Kumar
2020, Journal of Cleaner
Production
manufacturing industry has emerged stronger
and is recognized as one of the top contributors to economic
growth of developing economies like India. In India, sustainable
and cleaner production, circular economy and Industry 4.0 practices
are gaining significant attention due to pressure from customers
and global markets. By adopting these practices,
manufacturing organizations in emerging economies can achieve
greater global competitive advantage. This study proposes an integrated
framework for designing and evaluating the ethical and
sustainable performance of manufacturing organizations in the
Indian context. To the best of our knowledge, this study is the first
attempt to explore the integration of Industry 4.0, sustainable and
cleaner production and circular economy practices, for gauzing
ethical and sustainable performance of manufacturing organizations

22. S.
No
Title Author Year/Journal Conclusion
9.Circular supply chain
management: A
state-of-art review
and future
opportunities
Swapnil Lahane , Ravi Kant2020, Journal of Cleaner
Production
This paper examine the CSCM research published in the last decade
(January 2010 till July 2019) using content analysis methodology. Based
on its content, the articles were categorized in predefined structural
dimensions and analytics. The implementation of the CSCM has several
noteworthy benefits such as improving resource efficiency, supply chain
efficiency, economic growth, value propositions, end of life strategy,
competitiveness, etc. that an organization may achieve. The research on
CSCM is in the initial phase and has numerous research opportunities in
quantitative modeling and its application in reallife problems.
Furthermore, research areas such as additive manufacturing, smart
manufacturing, industrial ecology, resource management etc. have a huge
potential to obtain the socioeconomic
growth in perspectives of sustainability.
10.Environmental
assets, industry 4.0
technologies and
firm performance
in Spain: A dynamic
capabilities path to
reward sustainability
Angel Díaz-Chao , Pilar
Ficapal-Cusí
2021, Journal of Cleaner
Production
Research results partially confirm individual and complementary
effects on the established firm results. The good news is linked
to obtaining positive individual and complementarity effects from
environmental assets, use of robots and flexible production technologies
on sales, exports and labour productivity. However, bad
news has also been obtained. Some technologies, such as
computer-aided design or manufacturing, do not have significant
effects. Similarly, firm profitability is not explained by any interaction
between I4.0 technologies and environmental assets. To
overcome this obstacle, this research designed and validated a
model that confirms significant and positive total effects of environmental
assets, I4.0 technologies, R&D spending, productive
flexibility and human capital management on the established firm
results, and especially on gross operating margins.

23. S.
No
Title Author Year/Journal Methodology Conclusion
12Application of wavelet
energy and Shannon
entropy for feature
extraction in gearbox
fault detection under
varying speed
conditions
Hojat Heidari Bafroui,
Abdolreza Ohadi
2014
Neurocomputing
Re- sample
technique,
Continuous wavelet,
Artificial neural
network
In this paper, author have combined two signal
processing technique viz, re sampling ad continuous
wavelet. Four different condition was analyzed by
these techniques, they are healthy condition,
chipped condition and two worn condition one with
5% and 10% worn respectively. The non-stationary
vibration signals of gear fault were converted into
stationary one using angle domain technique. Then
Morlet wavelet was used to define the statistical
features from the extracted signals. Energy and
Shannon entropy have been applied as the input of
ANN. The obtained results indicate the accuracy of
the classifier increased by 5% to 10% by applying
these two parameters. Results showed that the
performance of the three techniques described in
the research paper was very in the fault diagnosis.
13Planetary gearbox fault
diagnosis using an
adaptive stochastic
resonance method
Yaguo Lei, Dong Han, Jing
Lin, Zhengjia He
2013
Mechanical System
and Signal Processing
Adaptive stochastic
resonance,
Ant colony algorithm
In this paper Planetary gear box was selected as
rotating machine whose fault was diagnosed. Gear
with three different condition was diagnosed viz,
healthy, missing tooth and chipped tooth processed
by Adaptive stochastic method. Adaptive stochastic
method was upgraded method of Stochastic
Resonance combined by ant algorithm which
automatically search and optimize the SR
parameters. From the result, it was concluded that
the signal with low Signal to noise ratio easily
detected in comparison to other techniques. This
method was also compared with EMD and it was
found that ASR method provides advantages over
EMD method.

24. 13.0 Work Schedule

25. 14.0 References
[1] Ribeiro, J., Lima, R., Eckhardt, T. and Paiva, S., 2021. Robotic Process
Automation and Artificial Intelligence in Industry 4.0 – A Literature review. Procedia
Computer Science, 181, pp.51-58.
[2]Kehayov, M., Holder, L., & Koch, V. (2022). Application of artificial
intelligence technology in the manufacturing process and purchasing and Supply
Management. Procedia Computer Science, 200, 1209–1217.
NEED TO ADD SOME REFERENCE