ScienceDirect

Available online at www.sciencedirect.com

Available online atScience
Procedia Computer www.sciencedirect.com
00 (2022) 000–000
www.elsevier.com/locate/procedia
ScienceDirect
AvailableScienceDirect
online at www.sciencedirect.com
Procedia Computer Science 00 (2022) 000–000
Procedia Computer Science 00 (2022) 000–000
ScienceDirect www.elsevier.com/locate/procedia
www.elsevier.com/locate/procedia

4th International Conference

Procedia on 217
Computer Science Industry 4.0 and Smart Manufacturing
(2023) 395–402

Manufacturing Reliability and Cost Improvements through Data

4th
4th International Conference
Analytics:
International Conference Anon Industry
Industry 4.0
onIndustry Case
4.0 and Smart
Smart Manufacturing
and Study Manufacturing

Manufacturing
Manufacturing Reliability
Reliability
a
Rob Geary,and
and bCost
Cost Improvements
Improvements through
John Cosgrove* through Data
Data
Analytics:
Zimmer OrthopedicsAn
Analytics: An a Industry
Industry
Manufacturing Case
Case
Ltd, Shannon, Study
Study
Co Clare, Ireland.
b
Technological University Shannon, Limerick, Ireland.

aRob
Rob Geary,
Geary, bJohn
John Cosgrove*
a b
Cosgrove*
Abstract Zimmer Orthopedics Manufacturing Ltd, Shannon, Co Clare, Ireland.
a
Zimmerb Orthopedics Manufacturing Ltd, Shannon, Co Clare, Ireland.
a

bTechnological University Shannon, Limerick, Ireland.

Technological
Industry has entered a new age of industrial change which University Shannon, how
is revolutionising Limerick, Ireland.
products are manufactured. Driving this industry change
are newly developing digital technologies such as robotics, artificial intelligence, advanced analytics and the industrial internet. This
convergence of technology and manufacturing is driving the digital transformation of every industrial segment from operations to logistics,
Abstract
Abstract
and from aeronautics to retail product manufacture. The technology advances evident from Industry 4.0 will result in industry disruption and
build competitive
Industry has entered advantages
a new age foroftheindustrial
organisations
change who can master
which the technologies
is revolutionising in their manufacturing
how products processes.
are manufactured. Driving However, organisations
this industry change
Industry has entered a new age of industrial change which is revolutionising how products are manufactured. Driving this industry change
are struggling to developdigital
newly developing a tactical methodology
technologies to as
such introduce these
robotics, technologies
artificial while simultaneously
intelligence, transforming
advanced analytics and thetheir organisation
industrial cultures
internet. This
are newly developing digital technologies such as robotics, artificial intelligence, advanced analytics and the industrial internet. This
and organisations
convergence and maximising
of technology the benefits. is
and manufacturing One of thethe
driving keydigital
reasons for the FourthofIndustrial
transformation Revolution
every industrial called
segment Industry
from 4.0 isto
operations thelogistics,
need to
convergence of technology and manufacturing is driving the digital transformation of every industrial segment from operations to logistics,
strengthen
and the competitiveness
from aeronautics of Western
to retail product EuropeanThe
manufacture. economies,
technology which as a result
advances evident of from
the progressing
Industry 4.0globalization
will result inprocess
industryand rising labor
disruption and
and from aeronautics to retail product manufacture. The technology advances evident from Industry 4.0 will result in industry disruption and
and business
build costsadvantages
competitive [1]. A keyfor benefit of the introduction
the organisations who can of Industry
master 4.0 initiatives
the technologies in a manufacturing processes.
in their plant is to However,
help overcome current
organisations
build competitive advantages for the organisations who can master the technologies in their manufacturing processes. However, organisations
operations management
are struggling to developlimitations, such as, thetolack
a tactical methodology of knowledge
introduce on how thewhile
these technologies process is performingtransforming
simultaneously at a specifictheir
pointorganisation
in time. This paper
cultures
are struggling to develop a tactical methodology to introduce these technologies while simultaneously transforming their organisation cultures
will investigate theand
and organisations impact of deploying
maximising a range One
the benefits. of Industry 4.0 reasons
of the key technologies
for thetoFourth
accessIndustrial
machine and operations
Revolution performance
called Industry 4.0 data, to improve
is the need to
and organisations and maximising the benefits. One of the key reasons for the Fourth Industrial Revolution called Industry 4.0 is the need to
equipment
strengthen thereliability and to reduce
competitiveness the costs
of Western associated
European with the which
economies, maintenance
as a resultof equipment. With theglobalization
of the progressing introductionprocess
of the operational
and rising labordata
strengthen the competitiveness of Western European economies, which as a result of the progressing globalization process and rising labor
analytics
and businessas a costs
result[1].
of data
A keyextraction
benefit of fromthemanufacturing
introduction ofequipment,
Industry 4.0 along with integrating
initiatives other data plant
in a manufacturing sources,
is tothehelp
business
overcomehas realised
current
and business costs [1]. A key benefit of the introduction of Industry 4.0 initiatives in a manufacturing plant is to help overcome current
improvements
operations in key metrics
management like OTIF
limitations, such(Onas, Time
the lackin Full), OEE (Overall
of knowledge on how Equipment
the process Effectiveness),
is performingMTBF (Meanpoint
at a specific TimeinBetween
time. This Failure),
paper
operations management limitations, such as, the lack of knowledge on how the process is performing at a specific point in time. This paper
MTTR (Mean Time
will investigate to Return),
the impact CuC (Consumable
of deploying Unit Cost),
a range of Industry and Lead Time.
4.0 technologies This paper
to access discusses
machine this project
and operations and the results
performance data, obtained
to improve at
will investigate the impact of deploying a range of Industry 4.0 technologies to access machine and operations performance data, to improve
Zimmer
equipment Biomet whileand
reliability alsotodiscussing
reduce thethecostsresearch carriedwith
associated out for
the ZOML to begin
maintenance of its journey on
equipment. manufacturing
With digitalisation.
the introduction of the operational data
equipment reliability and to reduce the costs associated with the maintenance of equipment. With the introduction of the operational data
analytics
The paperasstarts
a result
withofa data extraction
background from manufacturing
in Industry 4.0. The next equipment, along with
section provides integratingonother
a background data sources,
the company where thethe
business
problem hasstatement
realised
analytics as a result of data extraction from manufacturing equipment, along with integrating other data sources, the business has realised
improvements
and project have in come
key metrics like some
from with OTIF (On Time in Full), OEE (Overall Equipment Effectiveness), MTBFthe (Mean Timeand Between Failure),
improvements in key metrics like OTIF detail
(On Timeon their digitalisation
in Full), OEE (Overall journey. The following
Equipment section details
Effectiveness), MTBF (Mean problem the project
Time Between that
Failure),
MTTR
the (Mean
research is Time to from
derived Return),
and CuC
the (Consumable
final section is Unit
in Cost),toand
relation the Lead
resultsTime.
of This
the paperand
research discusses
the this project and the results obtained at
project.
MTTR (Mean Time to Return), CuC (Consumable Unit Cost), and Lead Time. This paper discusses this project and the results obtained at
Zimmer Biomet while also discussing the research carried out for ZOML to begin its journey on manufacturing digitalisation.
Zimmer Biomet while also discussing the research carried out for ZOML to begin its journey on manufacturing digitalisation.
The2022
© paper starts with a background in ELSEVIER
Industry 4.0. TheThis
next section provides
accessaa article
backgroundunderon theCCcompany wherelicense
the problem statement
The paperThe Authors.
starts Published by
with a background in Industry 4.0. B.V.
The nextissection
an open provides background onthe BY-NC-ND
the company where the problem statement
and project have come from with some detail on their digitalisation journey. The following section details the problem and the project that
(https://creativecommons.org/licenses/by-nc-nd/4.0)
and project have come from with some detail on their digitalisation journey. The following section details the problem and the project that
Peer-review
the research isunder responsibility
derived from and the of the scientific
final section iscommittee
in relationoftothethe4th International
results Conference
of the research on project.
and the Industry 4.0 and Smart Manufacturing
the research
Keywords: is derived from
Manufacturing; and the final
Digitalisation; section
Smart is in relation
Maintenance; to the results of the research and the project.
Data Analytics;
©
©2022
2022The TheAuthors.
Authors.Published
Publishedby Elsevier B.V.
by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license
© 2022
This is an The
openAuthors. Published
access article under the byCCELSEVIER
BY-NC-ND B.V.license
This is an open access article under the CC BY-NC-ND license
(https://creativecommons.org/licenses/by-nc-nd/4.0)
(https://creativecommons.org/licenses/by-nc-nd/4.0)
(https://creativecommons.org/licenses/by-nc-nd/4.0)
Peer-review
Peer-review under responsibility of
under responsibility of the
the scientific
scientific committee
committee of of the
the4th4thInternational
InternationalConference
Conferenceon onIndustry
Industry4.04.0and
andSmart
SmartManufacturing
Manufacturing
Peer-review under responsibility of the scientific committee of the 4th International Conference on Industry 4.0 and Smart Manufacturing
Keywords: Manufacturing; Digitalisation; Smart Maintenance; Data Analytics;
Keywords: Manufacturing; Digitalisation; Smart Maintenance; Data Analytics;

* Corresponding author.
E-mail address: john.cosgrove@tus.ie

1877-0509 © 2022 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license
(https://creativecommons.org/licenses/by-nc-nd/4.0)
* Corresponding author.
* Corresponding
Peer-review author.
under responsibility of the scientific committee of the 4th International Conference on Industry 4.0 and Smart Manufacturing
E-mail address: john.cosgrove@tus.ie
1877-0509 © 2022john.cosgrove@tus.ie
E-mail address: The Authors. Published by Elsevier B.V.
This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0)
1877-0509 © 2022 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license
Peer-review
1877-0509 © 2022under
Theresponsibility
Authors. Published of the scientificB.V.
by ELSEVIER
(https://creativecommons.org/licenses/by-nc-nd/4.0)
committee
This is an of theaccess
open 4th International Conference
article under the CC BY-NC-ND onlicense
Industry 4.0 and Smart
Manufacturing
(https://creativecommons.org/licenses/by-nc-nd/4.0)
Peer-review under responsibility of the scientific committee of the 4th International Conference on Industry 4.0 and Smart Manufacturing
Peer-review under responsibility of the scientific committee of the 4th International Conference on Industry 4.0 and Smart Manufacturing
10.1016/j.procs.2022.12.235
2 Rob Geary/
Rob Procedia
Geary etComputer Science
al. / Procedia 00 (2022)Science
Computer 000–000
396
2 Rob Geary/ Procedia Computer Science 00 (2022) 000–000217 (2023) 395–402
2 Rob Geary/ Procedia Computer Science 00 (2022) 000–000
1.
1. Research
Research Context Context
1. Research Context
1.1.
1.1. Case
Case Description
Description
1.1. Case Description
Zimmer
Zimmer Orthopedics
Orthopedics ManufacturingManufacturing Ltd. Ltd. (Zimmer
(Zimmer Ireland Ireland -- ZOML) ZOML) was was set set upup in in 2008
2008 in in Shannon,
Shannon, Ireland, Ireland, and and
Zimmer Orthopedics
manufactures femorals for Manufacturing
the global market.Ltd. At (Zimmer
the time, Ireland
ZOML - consisted
ZOML) of wasjustsetone upsite in in2008 in Shannon,
Shannon. The Ireland,
original startandup
manufactures femorals for the global market. At the time, ZOML consisted of just one site in Shannon. The original start up
manufactures
strategy for the femorals
Shannon for
sitethewasglobal
to market.
transfer the Atexisting
the time, ZOML
process as consisted
it was from ofthejustheadquarters
one site in Shannon.site in The original
Warsaw, Indiana start
and up
to
strategy for the Shannon site was to transfer the existing process as it was from the headquarters site in Warsaw, Indiana and to
strategy
optimisefor thethe Shannon
process later.siteThewasas-transferred
to transfer theprocess existingreliedprocess as it was
heavily from the headquarters
on paper-based
paper-based records and andsite in Warsaw,
manual controls. IndianaAs the andsite
the to
optimise the process later. The as-transferred process relied heavily on records manual controls. As site
optimise
scaled in the process
capacity andlater. The as-transferred
complexity, becameprocess
this became relied heavily on paper-based records and manual controls. Aszero
the lost
site
scaled in capacity and complexity, this aa limiting
limiting factor
factor to achieving
to achieving the company
the company vision,
vision, which was
which was to have
to have zero lost
scaled
working in days
capacity due and
to complexity,
accidents, zero thisrecalls,
became onea limiting
day lead factor
time to
andachieving
build a the company
femoral product vision,
at a which
lower was
cost toinhave
line zero
with lost
the
working days due to accidents, zero recalls, one day lead time and build a femoral product at a lower cost in line with the
working
business’ days due to
strategy. The accidents,
Company zero
neededrecalls,
to one day lead
standardise its time and build
processes and a femoral
move from product
compliance at aby lower cost in line
verification at thewith
end the
of
business’ strategy. The Company needed to standardise its processes and move from compliance by verification at the end of
business’
the process
process strategy.
to complianceThe Company
compliance at source,needed
source, to standardise
in order
order to its processes and movecapacity from compliance by This
verification at the end of
the to at in to scale
scale up up to to full
full production
production capacity at at Shannon.
Shannon. This ledled to to the
the company
company
the processMES
deploying to compliance at transformational
source, in order project to scalethat up would
to full begin
production capacity at Shannon. This led Industry
to the company
deploying MES as as aa strategic
strategic transformational project that would begin the
the company’s
company’s journey journey in in relation
relation to to Industry 4.0 4.0 and
and
deploying
digitalisation. MESThe as aadvantages
strategic transformational
of MES that are project
widely that would begin
discussed are the company’s
increased journey improved
productivity, in relationproductto Industry quality4.0 and
digitalisation. The advantages of MES that are widely discussed are increased productivity, improved product quality and
digitalisation.
downtime reduction The advantages
reduction howeverofwhat
[2] however MES
what that are widely
is typically
typically not realised discussed
realised are increased
until post
post implementation productivity,
is the
the valueimproved
value in the product
the data
data that is quality
is generatedand
downtime [2] is not until implementation is in that generated
downtime
on the reduction
process. The [2] howeveradvances
technology what is typically
in Industry not4.0 realised
will until post
result in implementation
industry disruption isand
the value
build in the data that
competitive is generated
advantages for
on the process. The technology advances in Industry 4.0 will result in industry disruption and build competitive advantages for
on
thethe process. Thewho
organisations technology
can master advances
master in Industry 4.0
the technologies
technologies in will
theirresult in industry disruption
manufacturing processes. and Thisbuildrapidcompetitive
growth of ofadvantages
technologies for
the organisations who can the in their manufacturing processes. This rapid growth technologies
the organisations
interconnected withwho can master
electronics and the technologies
internet of things in their
things manufacturing
is enabling
enabling the development processes.
development of This rapid growth of has technologies
interconnected with electronics and the internet of is the of manufacturing
manufacturing which which has led to
led to the
the
interconnected
paradigm shift withhas
and electronics
become and the as
defined internet
the of things
fourth is enabling
industrial revolutionthe development
or Industry of [3].
4.0 manufacturing
Thus, the which
aim of has led to
Industry 4.0 the
is
paradigm shift and has become defined as the fourth industrial revolution or Industry 4.0 [3]. Thus, the aim of Industry 4.0 is
paradigm
to transform shift
the and has becomefactories
manufacturing defined as of the fourth
today using industrial
these revolution or
advancements in Industry
technology, 4.0 into
[3]. “smart”
Thus, the aim of using
factories Industry 4.0 is
solutions
to transform the manufacturing factories of today using these advancements in technology, into “smart” factories using solutions
to transform
like, the manufacturing
the Industrial
Industrial Internet of factoriesCyber
of Things,
Things, of today using these
Physical Systems, advancements
Machine Learningin technology,
Learning and Cloudinto “smart”
Cloud Computing, factories using solutions
to empower
empower these
like, the Internet Cyber Physical Systems, Machine and Computing, to these
like, the Industrial
manufacturing Internet
processes withof flexibility
Things, Cyber and Physical Systems,
adaptability. However, Machine
rather Learning
than and technology
specific Cloud Computing, solution, toitempower
is necessary theseto
manufacturing processes with flexibility and adaptability. However, rather than specific technology solution, it is necessary to
manufacturing
consider the processes
overall with flexibility
interaction of and adaptability.
implementing various However, rather
combinations of than specific
Industry 4.0 technology
enabling solution,which
technologies it is necessary
can deliverto
consider the overall interaction of implementing various combinations of Industry 4.0 enabling technologies which can deliver
consider
impact in inthe overall interaction
companies [4]. This
This visionof implementing
of Industry
Industry 4.0 various
4.0 aims combinations
incorporate of
to incorporate Industry
vertical and4.0 enablingintegrations
horizontal technologies of which corecan
all core deliver
functions,
impact companies [4]. vision of aims to vertical and horizontal integrations of all functions,
impact
from in companies [4].
manufacturing, This vision
procurement andof warehousing,
Industry 4.0 aims all to incorporate
the way to sales vertical
of the and horizontal
final product integrations
which leads to ofmore
all core rapid functions,
product
from manufacturing, procurement and warehousing, all the way to sales of the final product which leads to more rapid product
from manufacturing,
development, customised procurement
production, and improved
warehousing, all the way
management of to sales of the final
manufacturing product which
environments, faster leads to more
supply chains, rapid andproduct
so on.
on.
development, customised production, improved management of manufacturing environments, faster supply chains, and so
development,
This high level customised
of integration production,
allows improved management
transparency across businessof manufacturing
processes, environments,
which enables faster efficiency
greater supply chains, including and soclearon.
This high level of integration allows transparency across business processes, which enables greater efficiency including clear
This
decisionhighrecommendations
level of integration forallows
users [5].transparency across business processes, which enables greater efficiency including clear
[5].
decision recommendations for users
decision
As an recommendations
organisation the for users [5].
business needed aa scalablescalable and and sustainable
sustainable solution
solution for for anyany datadata integration
integration tool tool introduced,
introduced,
As an organisation the business needed
As an organisation
particularly for processes theinbusiness
the regulatedneeded a scalable
medical sector. andThe sustainable
Company solutionWonderware
selected for any dataasintegrationan appropriate tool platform
introduced, for
particularly for processes in the regulated medical sector. The Company selected Wonderware as an appropriate platform for
particularly
development, forasprocesses
their in theshowed
research regulated the medical
Wonderware sector.Platform
The Company selected other
outperformed Wonderware
similar as an appropriate
solutions in design platform
simplicity, for
development, as their research showed the Wonderware Platform outperformed other similar solutions in design simplicity,
development,
operational flexibility,as their research
flexibility, and informationshowed processing
information the Wonderware Platform
capabilities outperformed
[6]. Advanced
Advanced other similar
Analytics is the solutionsterm
the umbrella
umbrella in design
given to simplicity,
to the likes
likes
operational and processing capabilities [6]. Analytics is term given the
operational
of predictive flexibility,
analytics, and information
prescriptive processing
analytics, data capabilities
mining and [6]. Advanced
other analytics Analytics
that apply is the level
high umbrelladata term
science given to the likes
methods, such
of predictive analytics, prescriptive analytics, data mining and other analytics that apply high level data science methods, such
of predictive analytics, prescriptive analytics, data mining and other analytics that apply high level data science methods, such
as, Artificial Intelligence (AI), to cope with far more complex datasets and produce far deeper insights and predictions. The
as, Artificial Intelligence (AI), to cope with far more complex datasets and produce far deeper insights and predictions. The
as, Artificial
ultimate goal Intelligence
is to deploy (AI),
to deploy suitable to cope with far
predictive more complex
analytics datasetstools
and prescriptive
prescriptive and produce ensurefar
to ensure that deeper insights has
the company
company andthe predictions.
knowledge The
ultimate goal is suitable predictive analytics and tools to that the has the knowledge to to
ultimate
run the goal is to
business as deploy
efficiently suitable
as predictive
possible to analytics
provide the and prescriptive
customer with toolsthey
what to ensure
wanted, thatwhenthe they
company wanted hasit.the This knowledge
knowledge to
run the business as efficiently as possible to provide the customer with what they wanted, when they wanted it. This knowledge
run the business
is aa critical
critical asset as
asset for efficiently
for aa manufacturing as possible
manufacturing enterprise, to provide
enterprise, which the customer
which enables with
enables businesses what
businesses to they wanted,
to differentiate when
differentiate themselves they wanted
themselves from it. This knowledge
is from competitors
competitors and and
is a critical
compete asset forand
efficiently a manufacturing
effectively to enterprise,
to the
the best of whichabilities
of their
their enables[7]. businesses
Organisations to differentiate
that use themselves
use advanced
advanced from competitors
analytics can act act quicker and
quicker
compete efficiently and effectively best abilities [7]. Organisations that analytics can
compete
and with efficiently
a greater and effectively
degree of confidence to the bestfuture
about of their abilities It[7].
outcomes. Organisations
enables organizations that useto advanced
make analytics
data-driven can actand
decisions quicker
gain
and with a greater degree of confidence about future outcomes. It enables organizations to make data-driven decisions and gain
and
deeperwith a greater
insights on degree
market of confidence
trends, customer about future outcomes.
preferences, and keykeyItbusiness
enablesactivities
business organizations to make data-driven
by prompting
prompting potential outcomes decisions and than gain
deeper insights on market trends, customer preferences, and activities by potential outcomes rather rather than
deeper
relying insights
on end on market
users to trends,the
identify customer
trends preferences,
from and keyofbusiness
visualisation their dataactivities
sets. by prompting
However, potential
increasing outcomesof
applications rather than
machine
relying on end users to identify the trends from visualisation of their data sets. However, increasing applications of machine
relying
learningon and enddatausersscienceto identify the trends
techniques present from visualisation of their data including
sets. However, that increasing applications of machine
learning and data science techniques present aa range
range of procedural
of procedural issues issues including those those that involved
involved in in data,
data, assumptions,
assumptions,
learning
methodologies,and dataand science
applicabletechniques presentEach
conditions. a range of of procedural
these issues issues
may including
increase those thatforinvolved
difficulties in data, assumptions,
implementation in practice,
methodologies, and applicable conditions. Each of these issues may increase difficulties for implementation in practice,
methodologies,
especially associatedand applicable
with the conditions. Each
manufacturing of these and
characteristics issues may knowledge
domain increase difficulties
[8]. The for implementation
positive side of Industry in 4.0practice,
is the
the
especially associated with the manufacturing characteristics and domain knowledge [8]. The positive side of Industry 4.0 is
especially
creation of associated
value, whichwith include
the manufacturing
both an characteristics
increase in and domain
effectiveness and knowledge
the development[8]. Theofpositive side of Industry
contemporary business 4.0 is the
models.
creation of value, which include both an increase in effectiveness and the development of contemporary business models.
creation
Moreover, ofIndustry
value, which include both
4.0 introduces
introduces an increase in
new possibilities
possibilities thateffectiveness
will likely and the
likely disrupt
disrupt thedevelopment
traditional business of contemporary
business models. [9] [9]business models.
Moreover, Industry 4.0 new that will the traditional models.
Moreover,
While itIndustry
is positive 4.0 to introduces
have this new possibilities
data-driven that will the
knowledge, likely
risedisrupt
in the traditional
complexity brings business
with it amodels.
need [9]new skills in the
for
While it is positive to have this data-driven knowledge, the rise in complexity brings with it a need for new skills in the
While it business.
company’s is positiveAdapting to have to thisthese
data-driven skillknowledge,
new skill requirements theisrise in complexity the brings with it aindustry,
need forwhere new skills in the
company’s business. Adapting to these new requirements is aa challenge
challenge in the
in manufacturing
manufacturing industry, where it is
it is rare
rare to
to
company’s
find the business.
personnel with Adapting
advanced todata
theseanalytics
new skill requirements
skills and it is is a challenge
common for in the manufacturing
businesses to have problems industry,
finding where
qualified it is people
rare to
find the personnel with advanced data analytics skills and it is common for businesses to have problems finding qualified people
find the personnel
to organise,
organise, manage, withand advanced
analysedata big analytics
data. TheTheskills and it isand
technology commontools foraroundbusinesses
big data
datato have problems rapidly,
are advancing
advancing finding qualified therepeople
but there aren't
to manage, and analyse big data. technology and tools around big are rapidly, but aren't
to organise,enough
necessarily manage,skilled and analyse
people big data.
who can The technology
operate this and tools
technology at around
an expert big dataIt's
level. aremuchadvancing
harder rapidly,
to collect, butmanage,
there aren'tand
necessarily enough skilled people who can operate this technology at an expert level. It's much harder to collect, manage, and
necessarily
build actionableenough skilled
reports from people
big whoifcan
data your operate
team this technology
simply doesn't at anthe
have expert
know-how level. It's
[10]. much harder to collect, manage, and
build actionable reports from big data if your team simply doesn't have the know-how [10].
build actionable reports from big data if your team simply doesn't have the know-how [10].
1.2. Methodology
1.2. Methodology
1.2. Methodology
The research
The research project,
project, developed
developed in in conjunction
conjunction with with thethe IDEAM
IDEAM ResearchResearch Institute
Institute at at Technological
Technological UniversityUniversity Shannon Shannon
The research
(TUS), set out toproject,
investigate developed
the in conjunction
impact of developing with reliability
the IDEAM dataResearch
analytics Institute
on the at Technological
potential for a University
reduction in Shannon
the costs
(TUS), set out to investigate the impact of developing reliability data analytics on the potential for a reduction in the costs
(TUS),
associated set with
out to theinvestigate
maintenance theofimpact
equipment.of developing
The research
research reliability
work aimed data analytics
aimed developonaa solution
to develop the potential
solution for datafor extraction
data a reduction and incollection
the costs
associated with the maintenance of equipment. The work to for extraction and collection
associated
from the with the maintenance
the company’s
company’s equipment of andequipment.
processes The researchsubject
to provide
provide work aimedmattertoexperts
developwith
experts a solution for datadata
the relevant
relevant extraction
that cancanand collection
improve the
from equipment and processes to subject matter with the data that improve the
from the company’s equipment and processes to provide subject matter experts with the relevant data that can improve the
 Author name / Procedia Computer Science 00 (2022) 000–000 3
Author name
Rob Geary et al. // Procedia
ProcediaComputer
ComputerScience 00 217
Science (2022) 000–000
(2023) 395–402 3
397
Author name / Procedia Computer Science 00 (2022) 000–000 3
reliability of the equipment, in turn improving the OEE metric and providing the business unit with more stability and
reliability
confidenceof in the equipment,
the capacity planinwhile
turn also
improving
reducingthe theOEE metric and
maintenance providing the business unit with more stability and
costs.
reliability
confidence of
in the equipment,
the capacity planinwhile
turn also
improving the theOEE metric and providing the business unit with more stability and
A participatory action research approachreducing
was taken maintenance
for the project.costs.
By using this approach, the people most impacted by the
confidence in the capacity
A participatory actionupon plan while
research also reducing thefor
maintenance costs.
problem could be relied to be approach
motivatedwas taken
to work the project.
and help in solvingBythis
using this approach,
problem. the people
Using frequent andmost
clear impacted
communicationby the
A
problem participatory
could be action
relied research
upon to be approach
motivated was
to taken
work for
and the
help project.
in Bythis
solving using this approach,
problem. Using the people
frequent and most
clear impacted
communicationby the
to the stakeholders was key to keeping engagement high and ensuring the users were contributing to finding an effective
problem
to could
the stakeholders be relied upon to be motivated to work and help in solving this problem. Using frequent and clear communication
solution. Throughoutwas the key to keeping
project engagement
requirements high and
for upskilling ensuring the
of individuals users
and weretocontributing
changes to finding
their daily work an effective
schedules become
to the stakeholders was
solution. the key to keeping engagement high and individuals
ensuring the users weretocontributing to finding an effective
apparent, Throughout
as the solution project
developed requirements
to remove for the upskilling
non-valueof add activity from and changes
the end users their
anddaily work
to provide schedules
insight into become
their
solution. Throughout the developed
project requirements for upskilling of individuals and changes to their daily work schedules become
daily responsibilities they have not had before. Benchmark visits were carried out across a number of businesses withintheir
apparent, as the solution to remove the non-value add activity from the end users and to provide insight into the
apparent,
daily as the solution
responsibilities they developed
have not to remove
had before. the non-valuevisitsadd activity from theout end users and to provide insightwithin
into their
manufacturing industry to better understand whatBenchmark
has been carried out were
on carried
this subject across a number
elsewhere, as wellofasbusinesses
learning from the
others
daily responsibilities
manufacturing industry they have not
to better had before.
understand what Benchmark visitsout
has been carried were
on carried out across
this subject a number
elsewhere, as wellofasbusinesses within
learning from the
others
the positives and negatives regarding solution deployments .
manufacturing
the positives and industry
negativesto better understand
regarding solutionwhat has been carried
deployments . out on this subject elsewhere, as well as learning from others
the positives and negatives regarding solution deployments.
1.3. Digitalisation Strategy
1.3. Digitalisation Strategy
1.3. Digitalisation Strategy
It is the Company’s strategic view that Manufacturing plants more than ever need to integrate their decision making based
on Itfacts
is the
andCompany’s
a completestrategic
data set.view that Manufacturing
Traditionally businessesplants more thanthemselves
differentiated ever need through
to integrate their decision
achieving makingreliable
high quality, based
on Itfacts
is the
andCompany’s
a complete strategicset.view
data These that Manufacturing plants
Traditionally more thanthemselves
ever need through
to integrate their decision makingreliable
based
service and improved agility. elements arebusinesses
now simply differentiated
a qualifier to do business. Building achieving highthread"
a "digital quality, from raw
on factsand
service andimproved
a complete data These
agility. set. Traditionally
elements arebusinesses
now simplydifferentiated
a qualifier themselves
to do through
business. achieving
Building a highthread"
"digital quality,fromreliable
rawa
material to finished product and from supplier to customer is a key enabler to maintain the qualifiers but also to drive
service and
material improvedproduct
agility. and
These elements aretonow simply isa qualifier to do business. Building a "digital thread" from raw
competitive advantage in the area of collecting real-time manufacturing data, marrying the design process with manufacturing,a
to finished from supplier customer a key enabler to maintain the qualifiers but also to drive
material
competitive to finished
advantage product and
in the area from supplier
offeeding
collecting to customer
real-time is a key enabler to maintain the qualifiers but also to drive a
acquiring customer information and it back to the manufacturing
manufacturing data, marrying
site. This themanufacturing
enables design processtowith meetmanufacturing,
the true needs
competitive
acquiring advantage
customer in the area
information and offeeding
collecting
it real-time
back to the manufacturing
manufacturing data,
site. marrying
This themanufacturing
enables design processtowith meetmanufacturing,
the true needs
of our customers in a competitive way [11]. The Company places a clear focus on data being key to delivering this strategy,
acquiring
of our customer ininformation andwayfeeding itThe
backCompany
to the manufacturing site. Thison enables manufacturing to meet thethistrue needs
and thatcustomers
the tools and a systems
competitivethat have [11].
become available under places a clear
Industry 4.0 focus data being
enable improvements keyintothe
delivering
company’s strategy,
reliability
of our
and that customers
the tools in a competitive
and systemsrisk thatin way
have [11]. The Company places a clear focus on data being key to delivering this strategy,
and reduce the compliance thebecome
company’s available under Industry
processes. The data4.0 enable improvements
philosophy is based onina the company’s
hierarchy reliability
of Machines,
and that
and the tools
reduce the and systemsrisk
compliance that havethebecome available under Industry 4.0 enable improvements in the company’s reliability
Connectivity, Data and People, as in shown company’s
in Fig.1. processes. The data philosophy is based on a hierarchy of Machines,
and reduce the
Connectivity, compliance
Data and People, riskas in the company’s
shown in Fig.1. processes. The data philosophy is based on a hierarchy of Machines,
Connectivity, Data and People, as shown in Fig.1.

Fig. 1. Zimmer Biomet Digitalisation Strategy.

Fig. 1. Zimmer Biomet Digitalisation Strategy.
Fig. 1. Zimmer Biomet Digitalisation Strategy.
When building a strategic roadmap regarding data, it was decided to use a philosophy of starting with being reliable, then
When building
becoming agile anda with
strategic roadmap
a view regarding
to becoming data, it was
predictable. decidedfrom
In addition, to use a philosophy
a quality of starting
assurance withfor
perspective being reliable,
a medical then
device
When building
becoming agile anda with
strategic
a roadmap
view to regarding
becoming data, it was
predictable. In decidedfrom
addition, to usea a philosophy
quality of starting
assurance withfor
perspective being
a reliable,
medical then
device
company it is also crucial for the company’s validated equipment to run exactly within the validated specifications approved.
becoming
company agile and with
it is also crucial a view to becoming
for the company’s predictable. In addition, from a quality assurance perspective for a medical device
Thus, a standardized data extraction solution validated
needed toequipment to run
be developed thatexactly within
could be the validated
deployed specifications
on the process approved.
equipment (CNC
company
Thus, it is also crucial
a standardized data for the company’s
extraction validated
needed toequipment to run
thatexactly within the validated specifications approved.
Machines / Cleanlines) to extract the solution
critical parameters be
anddeveloped
alarms from could
the PLCbeindeployed on the process
order to monitor equipment
the operations. (CNC
Thus, a standardized
Machines / Cleanlines)data extraction
to extract the solution needed to be
critical parameters anddeveloped thatthe
alarms from could
PLCbeindeployed on the process
order to monitor equipment (CNC
the operations.
Machines / Cleanlines) to extract the critical parameters and alarms from the PLC in order to monitor the operations.
2. Industry Case Study
2. Industry Case Study
2. Industry Case Study
2.1. Problem Definition
2.1. Problem Definition
2.1. Problem Definition
A problem-solving session (2018) with the Business Unit where a CNC machine had required a spindle change-out within
fourA months
problem-solving
of a newsession
spindle(2018)
being with the Business
installed was carriedUnitout.
where a CNC machine
A spindle hadisrequired
change-out a spindle
costly for change-out
the company’s within
business
fourA months
problem-solving
of a new session
spindle (2018)
being with the Business
installed was Unitout.
carried where
A a CNC machine
spindle hadisrequired
change-out costly a spindle
for the change-out
company’s within
business
exceeding €60,000 once the labour, tools, spares and external vendor costs are factored in. This cost mentioned above, does not
four months
exceeding of a new spindle being installed was carried out. A spindle change-out is costly for the company’s business
include the€60,000
cost of once the labour,
disrupting tools, spares
the company’s and external schedule.
manufacturing vendor costsTheare factoredsolving
problem in. Thiswas
costthorough
mentioned andabove, doesthat
identified not
exceeding
include the€60,000
cost of once the labour,
disrupting the tools, spares
company’s and external schedule.
manufacturing vendor costsTheare factoredsolving
problem in. Thiswas
costthorough
mentioned andabove, doesthat
identified not
four bolts fastening the spindle has not been tight enough on original spindle change out. This was identified as the root cause
include
four the cost
bolts fasteningof disrupting
thespindle the
spindlewithincompany’s
has notfour manufacturing
beenmonths
tight enough schedule.
on original The
spindleproblem solving
change out. was thorough and identified that
for failure of the new of installation. It was commented thatThis waswas
“there identified
no wayaswe thecould
root cause
have
four
for bolts fastening
failure of the newthespindle
spindlewithin
has notfour
beenmonths
tight enough on original
of installation. spindle
It was change out.
commented thatThis waswas
“there identified
no way as thecould
root cause
known”. This prompted an investigation into whether there were any leading indicators that the machine was weapproachinghavea
for failureThis
known”. of the new spindle
prompted an within fourinto
investigation months of installation.
whether there were It was
any commented
leading thatthat
indicators “there
the was no way
machine was we could havea
approaching
catastrophic failure and could the maintenance and operations teams have limited the damage or eliminated the risk of failure.
known”. Thisfailure
catastrophic prompted an investigation
andincould the up into whether
maintenance andthe there were anyhave
operations leading indicators that the machine was approaching a
It was discovered that the lead to this event, business teams limited
had in fact used up the damage
to four timesorthe
eliminated
budgetedthe risk of failure.
(expected usage)
catastrophic failure
It was discovered and could
that ininthe the maintenance and operations teams have limited the damage or eliminated the risk of failure.
number of cutters(tool) thelead
threeupweeks
to thisleading
event, the business
up to hadHad
the event. in fact
thisused
beenup to four times
reviewed the budgeted
or highlighted to the(expected usage)
relevant people
It was discovered
number that ininthe
of cutters(tool) thelead
threeupweeks
to thisleading
event, the business
up to hadHad
the event. in fact
thisused
beenup to four times
reviewed the budgeted
or highlighted to the(expected usage)
relevant people
number of cutters(tool) in the three weeks leading up to the event. Had this been reviewed or highlighted to the relevant people
398 Rob Geary et al. / Procedia Computer Science 217 (2023) 395–402
4 Rob Geary/ Procedia Computer Science 00 (2022) 000–000

the business could have indeed avoided the failure of a four-month-old spindle and corrected the issue. It led to questions on
what other indicators would have been available that could have removed the risk to downtime and availability of the machine.
Based on feedback taken from benchmark visits at other companies, the researcher began to look for solutions regarding data
availability and accessibility. Identifying there is a difference between operational business intelligence and analytical business
intelligence allowed the team to begin deploying the solution for accessing data and to deliver a visualisation to the end user to
provide insights and drive action. The maintenance function became the focus of the project as there were obvious cost saving
potential through reduced downtime, reduced consumables and optimized maintenance operations.

2.2. Solution

A solution was developed to enable the end user to view their data and better equip themselves to make business decisions
with more confidence. The solution consisted initially of connecting a machine (Haas Grinder) to a Wonderware tool for data
extraction and then transferring this data into Qlikview to build visuals for the end user. During the execution of this project the
scope was widened to include extracting the process parameters from cleanline equipment and critical alarms and triggering a
“hold” functionality in MES as a result. The scope also grew to include other data sources that provided additional processing
data and tool/consumable usage that would provide more valuable information for end users regarding delivery and cost of
production. Figure 2 shows the control and data acquisition architecture for the project.

Fig. 2. Control and Data Acquisition Architecture.

In addition to the deployment of operational business intelligence, it was decided to investigate the use of a predictive model
to determine the “time to next alarm” using alerts, motor speed, motor current and motor temperature extracted from the
equipment. It was clear that further work is needed to define the key inputs of alerts leading to mechanical faults in order to
apply predictive analysis.

3. Results

With the introduction of operational data analytics as a result of data extraction from manufacturing equipment along with
processing data sources the business has realised improvements in key metrics like OTIF (On Time in Full), OEE (Overall
Equipment Effectiveness), MTBF (Mean Time Between Failure), MTTR (Mean Time to Return), CuC (Consumable Unit Cost),
and Lead Time. It was concluded that the introduction of data analytics has reduced the costs of the maintenance function and
the costs of consumables usage across the business unit included in the proof of concept. In addition, the Data Analytics has
improved the reliability of the equipment and reduced the costs of consumables in the process. The fact the business is now
using these tools is proof of the value that they are bringing to the business. An example of the Maintenance function dashboard
is shown below in Fig.3.
 Author name / Procedia Computer Science 00 (2022) 000–000 5
Rob Geary et al. // Procedia
Author name ProcediaComputer
ComputerScience
Science
00 217 (2023)
(2022) 395–402
000–000 399
5
Author name / Procedia Computer Science 00 (2022) 000–000 5

Fig. 3. Data-driven Maintenance Dashboard.

Fig. 3. Data-driven Maintenance Dashboard.
With the introduction of the Maintenance function dashboard
Fig. 3. Data-driven the accountability
Maintenance Dashboard. is in place and the ownership is now in the
With
hands ofthe
theintroduction
maintenanceoftechnicians
the Maintenance
to ensure function
that alldashboard the accountability
activities due are closed out is onintime
placeand andthethe ownershipisisnow
recognition nowalsoin the
an
With
hands
incentiveoftheto introduction
the maintenance
do so. Benefits oftechnicians
thethe
to Maintenance
to ensure
business function
have that dashboard
beenallseen
activities the accountability
due
in a number areofclosed
areas,out is
onintime
including; placeand andthethe ownershipisisnow
recognition nowalsoin the
an
hands
incentiveof the
to domaintenance
so. Benefitstechnicians to ensure
to the business havethat
beenallseen
activities due areofclosed
in a number areas,out on time and the recognition is now also an
including;
incentive to do so. Benefits to the business have been seen in a number of areas, including;
3.1 Mean Time To Repair
3.1 Mean Time To Repair
3.1This
Meanis Time To Repairmetric to understand how the maintenance team are tracking the return of equipment fit for use to
an important
This is anIt important
Operations. metric to the
is also important understand
leader ofhow the maintenance
the maintenance teamtoare
function tracking
measure how thethereturn
team of equipment fit
is performing for use to
in relation
This
Operations.
time is an
taken important
toIt repair metric to
is alsoequipment.
important to understand
the
Over leader
the ofhow the maintenance
the maintenance
fifteen-month teammonthly
function
pilot period, the toare tracking
measure how
average thethereturn
time team of equipment
is performing
to repair fit forbyuse
in relation
time reduced 40%to
to
Operations.
time taken
from toIt repair
1.89 hours is to
also important
equipment.
1.14 hours. This to the
Over leader
the
also of theformaintenance
fifteen-month
accounts function
pilotreduction
a 40% period, the to measure
monthly
on the how
actualaverage
time the
timeteam
recorded tofor ismaintenance
performing
repair in
time reducedworkrelation
by 40%to
orders,
time taken
from 1.89 to repair
hours to
955 hours equipment.
to 575
1.14hours. Over the fifteen-month pilot period, the monthly average time to
hours. This also accounts for a 40% reduction on the actual time recorded for maintenance work orders, repair time reduced by 40%
from 1.89
from hours to
955 hours to 575
1.14hours.
hours. This also accounts for a 40% reduction on the actual time recorded for maintenance work orders,
from 955 hours to 575 hours.
3.2 Unplanned Maintenance Occurrence
3.2 Unplanned Maintenance Occurrence
3.2Over
Unplanned
the pilot Maintenance
period of 15 Occurrence
months, the average occurrence of an unplanned maintenance related event has reduced from
Over
every the pilot
twelve daysperiod of 15 months,
to currently the average days.
being twenty-seven occurrence of an unplanned
This improvement can maintenance
be attributed related
to a couple eventofhas reduced
factors. Thefrom
fact
thatOver
every the pilot
thetwelve
data isdays period
called outof
to currently 15 months,
earlier being
is now the averagethe
twenty-seven
providing occurrence
days. of an unplanned
This improvement
Maintenance team withcan maintenance
be attributed
more visibility of related
to their
a coupleeventofhas reduced
factors.
performance Thefrom
along fact
with
every
that twelve
detailthe
of data isdays
the equipment to currently
called out
hasearlier being
enabled thetwenty-seven
is now providing
team to focus days.
the This
Maintenance
on the improvement
correct team with
issues andcan be attributed
more visibility
increase to their
of
the average a couple of factors.
performance
time between Thewith
along
failures. fact
that the data is called out earlier is now providing the Maintenance team with more visibility
detail of the equipment has enabled the team to focus on the correct issues and increase the average time between failures. of their performance along with
detail of the equipment has enabled the team to focus on the correct issues and increase the average time between failures.
3.3 Better Diagnostic Data
3.3 Better Diagnostic Data
3.3Providing
Better Diagnostic
variable Data
data from the Haas grinding machine enables better trouble shooting for the maintenance team. The
Providing
correlation of variable
historicaldata
datafromsets the
has Haas
showngrinding machine enables
that an unplanned better work
maintenance trouble shooting
order was raisedfor the formaintenance
this machineteam. The
just after
Providing
correlation
erratic of variable
behaviour historicaldata
was seen dataonfrom
sets the
has Haas
the spindleshown grinding machine
that an unplanned
temperature, which couldenables
havebetter
maintenance trouble
work
been flagged shooting
order foralso
wasItraised
earlier. is the formaintenance
this machine
apparent that theteam.
just The
after
duration
correlation
erratic
of the alarm ofprovides
behaviour historical a data
was seen on sets
greater has shown
theindication
spindle ofthat
the an
temperature, unplanned
impactwhich the maintenance
of could haveon
alarm been work
theflagged order
machine inwas
earlier. Itraised
is also
relation tofor this machine
apparent
downtime. thatFor just after
theexample,
duration
erratic
of
during behaviour
the alarm
the pilot was
provides seen
period,afor on
greater the spindle
indication
the Haas temperature,
Grinder, of the
the third
impactwhich could
of thealarm
highest have
alarmandbeen
onthe flagged
thelongest
machine earlier. It
in relation
duration is also
alarmtowas apparent
downtime. that the duration
Fortoexample,
in relation coolant.
of the same
during
In the alarm
the pilotprovides
period,
period, afor
while greater indication
the Haas
reviewing Grinder, of the
the reasons thefor
impact
third of thealarm
highest
unplanned alarmand
onthe
maintenance thework
machine
longest inonrelation
duration
orders the alarm
sametowas
downtime. Fortoexample,
in relation
machine, “Coolant”coolant.
was
during
called the as
In the same
out pilot
theperiod,
period, while
highest for the Haas
reviewing
reason Grinder,
the reasons
for maintenance thetothird
for highest
on thealarm
unplanned
work and the work
maintenance
machine. longest duration
orders on the alarm
samewas in relation
machine, to coolant.
“Coolant” was
In the same
called out asperiod, whilereason
the highest reviewing the reasons to
for maintenance forwork
unplanned
on the maintenance
machine. work orders on the same machine, “Coolant” was
called out as the highest reason for maintenance to work on the machine.
3.4 Consumable Usage
3.4 Consumable Usage
3.4ItConsumable
was identified Usageby the business that there was a lack of knowledge regarding the usage of consumable tools in the
It was identified
manufacturing by the
process. Throughbusinessthe that there was
application of aa spares
lack ofvending
knowledge regarding
system, linked thewithusage of consumable
the maintenance tools in the
dashboard,
It wasnow
manufacturing
business identified
has by reflection
process.
a true the
Throughbusiness that
theusage
of there
for thewas
application of aatime.
first lack This
spares ofvending
knowledge regarding
system,
has also enabled linked the
withusage oftoconsumable
the maintenance
the visualization tools
show thedashboard,
trend of in the
the
usage
manufacturing
business now has process. Through of
a true reflection theusage
application of a time.
for the first sparesThisvending system,
has also enabled linked with the maintenance
the visualization to show thedashboard,
trend of usage the
business now has a true reflection of usage for the first time. This has also enabled the visualization to show the trend of usage
6 Rob Geary/ Procedia Computer Science 00 (2022) 000–000
400
6 Rob Procedia
Rob Geary/ Geary etComputer
al. / Procedia Computer
Science 00 (2022)Science
000–000217 (2023) 395–402
6acrosseach machine for all tools. Over the pilot
Rob Geary/ period,
Procedia the Consumable
Computer Unit
Science 00 (2022) Cost (CuC) has reduced by 10% from the value
000–000
in the first quarter of 2021. This was successful by highlighting by tool
across each machine for all tools. Over the pilot period, the Consumable Unit Cost how the (CuC)
business
hasunit was performing
reduced by 10% fromagainst the
the value
across each
budgeted machine
usage and for all
enable a tools. Over
“finger on the
the pilot
pulse” period,
type the Consumable
dashboard using theUnit
data Cost (CuC)
extracted has
from reduced
the by 10%
electronic
in the first quarter of 2021. This was successful by highlighting by tool how the business unit was performing against the from the value
kanban(dispenser)
in
so the
thatfirst
budgeted quarter
usage and of
Engineering 2021.
and
enable This was
Operations
a “finger on successful
teams
the by highlighting
were type
pulse” able by tool
to identifyusing
dashboard issues how
theand
data the business
resolve thatfrom
extracted unit
at the was of
thetime performing againstthan
the
thekanban(dispenser)
electronic issue rather
budgeted
reviewing
so usage andon
the data
that Engineering enable
paper
and a at
“finger
Operations on
the end thethe
of
teams pulse”
month
were type
able dashboard
when using
the event
to identify could
issues theand
data
be extracted
aresolve
number offrom
that weeksthein
at the electronic
the of
time thekanban(dispenser)
past. issue rather than
so that Engineering
reviewing the data onand Operations
paper at the endteams
of thewere
monthable to identify
when the eventissues
couldand be aresolve
numberthat at the in
of weeks time
the of the issue rather than
past.
reviewing the data on paper at the end of the month when the event could be a number of weeks in the past.
3.5 OEE
3.5 OEE
3.5 In
OEErelation to OEE, the availability of the equipment is key to the calculation. The business measures the availability of the
equipment from
In relation to the amount
OEE, of time that
the availability ofthe
theequipment
equipmentisisinkey a “Productive” state as
to the calculation. Thedefined
businesspermeasures
MES (thethe equipment is placed
availability of the
in In
an relation to
“unproductive”OEE, the
state availability
by of
maintenance the equipment
technician is key
when to the
they calculation.
are working The
on business
the measures
machine)
equipment from the amount of time that the equipment is in a “Productive” state as defined per MES (the equipment is placed and the
use availability
this in the ofOEE
the
equipment
calculation. from
in an “unproductive”the amount
As can seen of
bestate intime
by that the equipment
the appendix,
maintenance iswhen
from January
technician in a2020
“Productive”
theya are
positive state
working asondefined
trend can per
seenMES
thebemachine) in the(thenumber
and equipment
use is placed
thisofinhours
the that
OEE
in an “unproductive”
equipment
calculation. inAs
being bestate
can set in
seenanbyin maintenance
unproductive
the appendix, technician
state. Reviewing
from when
January the they
2020 are
dataa for working
the
positive trendoncan
previous thebemachine)
year 2021,
seen its andbe
in can
the use thisofinhours
identified
number the OEE
that May
that
calculation.
and
equipment inAs
July were can set
being be in
seen
particularly in the
anpoor appendix,
months
unproductive for from January
availability
state. Reviewing of the2020
the a for
Haas
data positive
fleet. trend can
Across
the previous yearbe2021,
2021 seen
the in can
average
its theresult
number
be of hours
across
identified that
the Haas
that May
equipment
machines
and July werein being
was 95.37%,set in
particularly anpoor
while unproductive
2022 to datefor
months state. Reviewing
is recording the
the data
anofaverage
availability forfleet.
the previous
availability
Haas of 95.49%.
Across year 2021,
2021 its can4.result
See average
the Figure beAtidentified
glance that
a across May
this Haas
the does
and
not July were
necessarily particularly
show a poor
significant months
increase for
in availability
availability of
but the
over Haas
just fleet.
one weekAcross
this is2021 the
twenty-six
machines was 95.37%, while 2022 to date is recording an average availability of 95.49%. See Figure 4. At a glance this doesaverage
hours result
of across
machine the
time Haas
across
machines
eighteen
not was 95.37%,
machines
necessarily show that while
is now2022
a significant to date
available
increase is
toin recording that
Operations
availabilityanbut
average
they
overdid availability
justnot
onehave
week of
across95.49%.
this is2021. See
ThisFigure
twenty-six just 4.
ishours ofAt
looking a glance
machine at the this
time does
eighteen
across
not
Haasnecessarily
grinding
eighteen machinesshow
machinesa significant
that isinnow increase
one business
available toinOperations
unit. availability
This butthey
is scalable
that overdid
across just one
allnot week
equipment
have this is2021.
in the
across twenty-six
This ishours
manufacturing of machine
justplants
looking without time
at the across
a eighteen
massive
eighteen
amount ofmachines
effort
Haas grinding as that
machines isinnow available
the functionality is out
one business toofOperations
unit. the box
This thatthe
from
is scalable they didallTaking
MES.
across not havethis
equipment across
into
in the2021.
account This is just
within
manufacturing looking
theplants
Ireland at thea eighteen
plants
without we have
massive
Haas
amountgrinding
approximately machines
of effortten
asother in one business
types of CNC
the functionality unit.
is out of This
machines is
onscalable
the box across
MES.allTaking
the production
from the equipment
floor with in the
thisover
into one manufacturing
hundred
account within theplants
machines without
in
Ireland all a we
massive
groups.
plants The
have
amount
company of effort
has the as the functionality
potential to retrieveis out of
significantthe box from
capacity the
in MES.
additional Taking
machine this into
hours. account
See within
Haas
approximately ten other types of CNC machines on the production floor with over one hundred machines in all groups. The fleet the
OEEIreland
in plants
Figure 4.we have
approximately
company has the tenpotential
other types of CNC
to retrieve machinescapacity
significant on the production
in additional floor with over
machine hours. one hundred
See Haas fleetmachines
OEE ininFigure
all groups.
4. The
company has the potential to retrieve significant capacity in additional machine hours. See Haas fleet OEE in Figure 4.

Fig. 4. OEE
Fig. 4. OEE
Fig. 4. OEE

3.6 Other Benefits

3.6 Other Benefits
Other Benefits
3.6Connecting the Maintenance function dashboard to the MES data has also enabled other initiatives which are showing
benefits for the the
Connecting business. This includes
Maintenance functionthedashboard
opportunity to for
the‘campaign
MES databuilding’
has also of sequencing
enabled other SKUs to reduce
initiatives whichthearenumber
showingof
Connecting
change-overs
benefits for the the
and Maintenance
decrease
business. set-up
This function
times.the
includes dashboard
For example,toinfor
opportunity the
2021MES data
there
‘campaign werehaseighteen
also of
building’ enabled other
different
sequencingSKUsinitiatives
SKUs built onwhich
the the
to reduce arenumber
Haas showing
Grinder,
of
benefits
while in for
April
change-overs the
andbusiness.
2022 there This
decrease were includes
only
set-up fivethe
times. opportunity
different
For SKUs
example, infor ‘campaign
manufactured.
2021 building’
there were This of sequencing
allows
eighteen the machine
different SKUs
SKUs tooptimally
to built
run reduce
on the the
Haas number
and of
reduces
Grinder,
change-overs
the inspections and decrease
required on set-up
product. times. For
Additional, example,
adding in
a 2021 there
requirement were
in MES eighteen
for the different
operator SKUs
to
while in April 2022 there were only five different SKUs manufactured. This allows the machine to run optimally and reduces built
record theon the
data Haas
of the Grinder,
grinding
while
wheel
the in April 2022
balancing
inspections thereon
process
required were
has onlyAdditional,
provided
product. five
thedifferent
MaintenanceSKUsateam
adding manufactured. This
visibilityinonMES
requirement allows
for the the
a significant machine
source
operator of to runthe
unplanned
to record optimally
downtime,
data andgrinding
of the reduces
and has
the inspections
shown
wheel a reduction
balancing required on
hasproduct.
in spindle
process relatedAdditional,
provided issues sinceadding ateam
requirement
its introduction.
the Maintenance visibilityinonMES for the operator
a significant to record
source of unplanned the data of the grinding
downtime, and has
wheel
shownbalancing
a reduction process has provided
in spindle the Maintenance
related issues team visibility on a significant source of unplanned downtime, and has
since its introduction.
shown
The ateam
reduction
agreed in spindle
to buildrelated issues
a visual in since
the QV its introduction.
application to trend alarms. It was agreed that this would be a useful
representation of the data to enable end users
The team agreed to build a visual in the QV application to track particulartoalarms
trend ofalarms.
interestIt and
wasprovide
agreed an indicator
that on if be
this would a particular
a useful
Thepattern
alarm team agreed
representation to build
isofreducing
the data after aaction
to enablevisual
endhasin the toQV
been
users application
executed
track toalarms
to resolve
particular trend ofalarms.
interestItissue.
that particular wasprovide
and agreed
As shownanthatin this would
Fig.4.,
indicator be a useful
theifoverview
on of
a particular
representation
alarmspattern
alarm generated of the data
on the Haas
is reducing to enable
afterGrinderend
action over users to track
the study
has been particular
period
executed to are alarms
shown,
resolve of
thatwith interest and
a significant
particular provide
issue. decline
As shown an indicator
in occurrence. on
in Fig.4., the if
The a particular
alarms are
overview of
alarm
alerts pattern
alarmsof is reducing
all levels
generated that
on thethe after action over
machine.
Haas Grinder has been executed
the study period to are
resolve
shown,thatwith
particular issue. decline
a significant As shown in Fig.4., the
in occurrence. The overview of
alarms are
alarms generated on the Haas
alerts of all levels that the machine. Grinder over the study period are shown, with a significant decline in occurrence. The alarms are
alerts of all levels that the machine.
 Author name / Procedia Computer Science 00 (2022) 000–000 7
Rob Geary et al. / Procedia Computer Science 217 (2023) 395–402 401

Fig. 5. Data-driven Maintenance Dashboard.

Based on all of the above detail, it was concluded that the introduction of data analytics has reduced the costs of the
maintenance function and the costs of consumables usage across the business unit included in the proof of concept as can be
seen on the business’ key performance indicators.

4. Conclusions

Should the company continue in the plan and roadmap proposed through this project and continue to roll-out the data analysis
to the fleet (>20) of Haas Grinders and to other production machines (>100), they can expect to see a significant reduction in
over usage of tooling and consumable materials and increased production capacity available to the business. This will continue
to reduce the costs for the business and improve the reliability of the equipment as unplanned events would become rarer and
eventually eliminated through a predictive model. The pilot study has demonstrated that data analysis has improved the
reliability of the equipment and reduced the costs of consumables, with the improvement in reliability providing more capacity
for the company to grow their business. It could be argued to make an improvement you must first measure what you are
improving and while this is true in this scenario using data analytics has improved the business across multiple metrics and also
reduced the transactional waste that employees were carrying out in the daily duties. Removing this waste and providing clean
data allows for a paradigm shift from independent automated and human activities towards a human-automation symbiosis (or
‘human cyber-physical systems’) characterised by the cooperation of machines with humans in work systems and designed not
to replace the skills and abilities of humans, but rather to co-exist with and assist humans in being more efficient and effective.
[12]

References

[1] Grabowska, Sandra. (2020) Smart Factories in the age of Industry 4.0 pp. 90-96. doi: 10.2478/mspe-2020-0014.
[2] Balashov, Victor M. et al. (2018) Improvement of operational management of innovative production processes based on the implementation of MES. doi:
10.21511/ppm.16(4).2018.01
[3] Qin, J., Liu, Y. and Grosvenor, R. (2016) ‘A Categorical Framework of Manufacturing for Industry 4.0 and beyond’, in Procedia CIRP. doi:
10.1016/j.procir.2016.08.005.
[4] Büchi, G., Cugno, M. and Castagnoli, R. (2020) ‘Smart factory performance and Industry 4.0’, Technological Forecasting and Social Change, 150. doi:
10.1016/j.techfore.2019.119790.
[5] Nikolic, B. et al. (2017) ‘Predictive manufacturing systems in industry 4.0: Trends, benefits and challenges’, in Annals of DAAAM and Proceedings of the
International DAAAM Symposium. doi: 10.2507/28th.daaam.proceedings.112.
[6] Grachev, V. V. et al. (2021) ‘Development of a control system for the technological complex of “mine No. 12” processing plant based on the Wonderware
System Platform 2017’, in IOP Conference Series: Earth and Environmental Science. doi: 10.1088/1755-1315/823/1/012053.
[7] Kenett, R. S., Yahav, I. and Zonnenshain, A. (2020) ‘Analytics as an enabler of advanced manufacturing’, in Systems Engineering in the Fourth Industrial
Revolution: Big Data, Novel Technologies, and Modern Systems Engineering. wiley, pp. 321–343. doi: 10.1002/9781119513957.ch13.
[8] Lee, C. Y. and Chien, C. F. (2020) ‘Pitfalls and protocols of data science in manufacturing practice’, Journal of Intelligent Manufacturing. doi:
10.1007/s10845-020-01711-w.
[9] Jerman, Andrej. et al. (2019) The Influence of Critical Factors on Business Model at a Smart Factory: A Case Study. doi: 10.
2478/brsj-2019-0004
402 Rob Geary et al. / Procedia Computer Science 217 (2023) 395–402
8 Rob Geary/ Procedia Computer Science 00 (2022) 000–000

[10] Campos, L. (2022) 5 Challenges Associated with Big Data and How to Solve Them, Hubspot. Available at: https://blog.hubspot.com/website/big-data-
challenges
[11] Brian Dilleen, 2022 – Internal presentation by the Global Supply Chain Director, Zimmer Biomet.
[12] Romero D, et al. (2016) The operator 4.0: Human cyber-physical systems & adaptive automation towards human-automation symbiosis work system. doi:
10.1007/978-3-319-51133-7_80