Available online at www.sciencedirect.

com

ScienceDirect
Procedia CIRP 61 (2017) 58 – 62

The 24th CIRP Conference on Life Cycle Engineering

Parallel Design of a Product and Internet of Things (IoT) Architecture to

Minimize the Cost of Utilizing Big Data (BD) for
Sustainable Value Creation
Ryan Bradleya*, I.S. Jawahira, Niko Murrell, Julie Whitney
a
Institute for Sustainable Manufacturing (ISM), University of Kentucky, Lexington, KY 40506, USA

* Corresponding author. Tel.: 001-859-707-5976; E-mail address: ryan.bradleyky2014@uky.edu

Abstract

Information has become today’s addictive currency; hence, companies are investing billions in the creation of Internet of Things (IoT)
frameworks that gamble on finding trends that reveal sustainability and/or efficiency improvements. This approach to “Big Data” can lead to
blind, astronomical costs. Therefore, this paper presents a counter approach aimed at minimizing the cost of utilizing “Big Data” for sustainable
value creation. The proposed approach leverages domain/expert knowledge of the system in combination with a machine learning algorithm in
order to limit the needed infrastructure and cost. A case study of the approach implemented in a consumer electronics company is also included.
© 2017 Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license
© 2017 The Authors. Published by Elsevier B.V.
(http://creativecommons.org/licenses/by-nc-nd/4.0/).
Peer-review under responsibility of the scientific committee of the 24th CIRP Conference on Life Cycle Engineering.
Peer-review under responsibility of the scientific committee of the 24th CIRP Conference on Life Cycle Engineering

Keywords: Internet of Things; Big Data; Product Design; Machine Learning; Sustainability

1. Introduction frameworks involves outfitting legacy products, processes,

and systems with numerous sensor nodes and IT systems in
In today’s Big Data (BD) craze, companies are going “all order to collect a significantly large dataset, only to have a
in” on big data. They are investing billions in Internet of fraction of it filtered into a usable state. Although excellent in
Things (IoT) infrastructures and the necessary personnel to theory, this approach can lead to an astronomical initial
support them. These companies are looking for diamonds investment that could hinder any practical implementation
(i.e., efficiencies and cost savings) in the rough (billions of into a production environment. On the other hand, if this
unstructured data points) in order to justify the added approach is implemented blindly, there is a great risk
investment and ongoing costs. More specifically, the associated with managing the new overhead. This trap is
manufacturing sector has seen considerable research in this caused by the idea that information is free. While information
area because the industry generates a large amount of is free, the ability to access it and use it in a way that can be
unstructured and structured data that ideally can be processed beneficial is far from free. Everything from collecting the data
and then used to achieve significant improvement in product points, to processing, and then storing them has an associated
design, manufacturing efficiency, cost reductions, scalability, cost. For example, if only one million data points out of the
resiliency, and environmental sustainability [1,2]. original one billion is actually usable in a way that they can
However, many of the companies that have been banking see a return on investment, then there was a waste of 99.9% of
on big data still do not have much to show for their efforts [3]. the data collected.
In fact, those same companies have not even cashed in on the With that in mind, there is a need for a counter approach to
information systems that that they put into place 10-15 years implementing big data that can minimize the cost in order to
ago [3]. The current approach of creating these extensive IoT realize sustainable value creation. Therefore, this paper

2212-8271 © 2017 Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license
(http://creativecommons.org/licenses/by-nc-nd/4.0/).
Peer-review under responsibility of the scientific committee of the 24th CIRP Conference on Life Cycle Engineering
doi:10.1016/j.procir.2016.11.213
 Ryan Bradley et al. / Procedia CIRP 61 (2017) 58 – 62 59

presents an approach that is comprised of leveraging analytics can translate customer requirements into an increase
domain/expert knowledge of a system, product, and/or in sales, by being able to mine the rationale from metadata. In
process in combination with an advanced machine learning addition to the positives, the utilization of BD results in
algorithm. The premise of the approach lies in consolidating negatives as well. For example, tailored consumer level detail
the functionality of the system into minimal hardware and can result in the loss of purchasing options among other
physical infrastructure. By designing the system hardware in things [13].
parallel with the IoT architecture, the amount of data collected Cost, energy, and resources have been discussed
can be trimmed to the amount that will actually be used. extensively, yet water is considered sparingly. The work by
Koo et al. [14] advocates using the IoT technology for
2. Previous Work sustainable water development. The proposed solution
consists of using sensors that capture water data through a
For years, the vision of the IoT and its impact on product virtual platform and control system. This work established
design and manufacturing has been being molded for future three benefits: leak detection/prediction, optimization of
implementation. It can be said that the IoT is a means for production, and optimization of consumption.
aligning the physical and information life-cycles [4]. This
vision suggests that this intimate connection and the 3. Proposed Approach
information itself presents a major source of value [4, 5].
Dubey et al. [6] suggest that Big Data (BD) is one of the The proposed approach for implementing an IoT system
emerging research areas that are considered “game changers” for sustainable value creation consists of leveraging
in the manufacturing sector. The claim is that the use of big domain/expert knowledge of a product, process, and/or
data can see a 15-20% increase in return on investment and system by the means of parallel design of the system
surplus cash for customers [6]. hardware and the IoT architecture. In addition to the co-
Looking at IoT and BD through the lens of sustainability, design element, the other essential component to the proposed
the sought-after gain from such an implementation is approach is combining the domain/expert knowledge with a
information that mainly aims at reducing energy and resource machine learning algorithm. This machine learning algorithm
consumption. However, there must be a balance of the amount allows for more information to be extracted from the IoT
of energy and resources used to build the required sensor network than what would traditionally be measured.
infrastructure and support system in order to prove a net For example, in a traditional IoT system you may have
improvement [7]. In addition, it is suggested that Node 1 measuring time, Node 2 measuring value “A”, Node 3
improvements to sustainability can also come in the form of measuring value “B”, Node 4 measuring value “C”. However,
combining multi-source information, and then making a with this approach, because the system is being designed in
calculated decision from that information using cloud parallel, one is aware through an understanding of the
computing and web services [8]. Although many companies physical system that Node 2 can be slightly altered to be a
are going after cost reductions, those reductions will dynamic measurement and a function of time. With that
inevitably give way to the law of diminishing returns. alteration combined with the use of a machine learning
Because of this, other companies have seen better results algorithm, Node 2 solely becomes able to represent time and
utilizing big data in sales, marketing, and research and values A, B, and C. This paradigm suggests that the number
development in order to increase profits indirectly [9]. of sensors does not have to be equal to the number of
There have been several case studies involving the use of measured values.
IoT and BD in order to drive sustainable value creation. In The overall approach can be seen in Figure 1, where the
Pan et al. [10], a framework is built surrounding the HVAC product, process, and system are being designed in parallel
and building industry and the use of IoT systems to improve
energy usage. The approach envisions creating significant
economic benefits, as well as social and environmental
benefits. Tao et al. [11] presents an integration between an
IoT system and a traditional PLM system. This work provides
an idea for collecting environmental and life-cycle data
throughout the entire life-cycle. The work also proposes the
idea of a big Bill of Material (BOM) that uses the integration
interface with the IoT systems in order to exchange and
transform information. The next case considers the idea of
using cloud based technologies in order to support product
services [12]. In other words, a decision support system is
built on top of the BD foundation. In other cases, these
services are built to be proactive by building in predictive
models and analytics into the decision support system [6].
Another case is seen in the food production sector where
the application of BD to the supply chain can have
implications for many industries. The work claims that

Fig. 1 Overview of the Proposed Approach

60 Ryan Bradley et al. / Procedia CIRP 61 (2017) 58 – 62

and that knowledge gained can then be seen joined with the
machine learning algorithm. This approach suggests that the
overall cost and associated footprint of an IoT system can be
reduced by deploying the proposed method.
The traditional approach, shown in Fig. 2, is outfitting a
physical system with a complex network of sensor nodes in
order to collect a large amount of data coinciding with various
attributes of the system. In this figure it can clearly be seen
that there are four nodes that are collecting data and storing
that data in the cloud. There are two issues with this setup: 1)
It requires hardware for all 4 nodes, 2) The data is stored in
the cloud and must sifted through to come up with the needed
subset. This results in an inflated system with considerable
amount of resources and energy being required for the
hardware, as well as a large amount of required processing in
order to consume the data. With that in consideration, this
setup shows that there is much left to be desired in terms
reducing the overall cost and footprint of such a system.

Fig. 3. Proposed IoT System

4. Case Study

4.1 Motivation

This case study looks at the proposed approach as applied

Fig. 2. Traditional Extensive IoT System to the consumer electronics industry, more specifically, the
consumer printing and managed print services industry. In the
On the contrary, the proposed counter-approach can be managed print services industry in particular, there is a push
seen in Figure 3. In this approach, the four nodes have been for the development of proactive and predictive service
consolidated into a single node through the use of domain management programs that can help mitigate field service
expert knowledge of the physical system. In addition, this issues seen with many printing devices. As part of this larger
product, process, & system knowledge is used in combination effort, the system that was designed in this case was an
with the machine learning algorithm in order to reduce the automatic media type classification system that keeps users
overall footprint of the system from a cost, energy, and from having to change the settings themselves.
resources perspective. In addition, the machine learning Looking at the facts, it has been determined that a majority
algorithm can be imposed directly at the point of the node of the users of printing devices never check or adjust the
itself. Although this may not be applicable for every media type settings. In addition, out of those users that do
application, it can present a unique advantage over large check or adjust the media settings at least some of the time,
volumes of cloud computing. Therefore, this solution offers only fraction of them select the correct settings. Incorrect
economic, environmental, and societal benefits and identifies settings on these devices can cause detrimental problems for
as the more sustainable option to be put into practice. both the customers and manufacturers in all three pillars of
With the consideration of the proposed approach and the sustainability. First, wrong settings during the operation of the
possible benefits, there is a need for the application of the device can cause damage to the machine, resulting in a service
approach in a case study. The case study shown in the next call that can lead to astronomical costs. In addition, wrong
section validates the limit in infrastructure, offers a cheaper settings can result in unneeded energy use, numerous wasted
implementation with sustainability improvement. sheets of paper, and an overuse of toner. These wastes
represent both cost and an environmental impact. Lastly,
wrong settings significantly impact the print quality of the
 Ryan Bradley et al. / Procedia CIRP 61 (2017) 58 – 62 61

device and can cause negative experience for the customer this system are the lofty costs and overall footprint involved
and unneeded service calls for the manufacturer. Therefore, with fielding four sensors. Any cost reduction or identified
the studied application looks at a system internal to a printing improvement would be quickly swallowed up by the cost
device that aims at determining the correct media moving associated with the implementation. However, by using the
throughout the machine. This case-study also lends itself well knowledge of the system, a more efficient architecture could
to the manufacturing industry. The printing process, although be formed.
internal to a consumer product, can be imagined as a small-
scale manufacturing process and therefore contains strong 4.3 Leveraging the Methodology
similarities to that of a manufacturing line.
The four sensor nodes could ultimately be reduced to one
4.2 Preliminary Implementation sensor node, while not losing any performance. The
breakthrough that allowed for this, was expanding the
Prior to devising the proposed methodology, the mindset LED/photoresistor being used to capture optical translucence
surrounding the solution was very much in line with the to a dynamic measurement to encapsulate the domain expert
traditional approach of outfitting the device with numerous knowledge of the printing system. Instead of collecting
sensor nodes in hopes to collect as much data as possible. In individual measurements through individual sensor nodes, a
this case, the preliminary implementation looked at using four smart system was deployed that consolidated all of various
different sensor nodes to capture various measurements of the media attributes that were being measured with the previous
paper: bending stiffness, optical translucence, density, and nodes into a singular time-series trace. Figure 5 shows the
electrical impedance. All of these measurements are directly final solution that was devised.
related to physical attributes of the media. These attributes
contribute to controlling operating parameters that are a
function of how various media types interact with the
electrophotography (EP) printing process. Figure 4 shows the
original sensor nodes and their corresponding properties.

Fig. 5 Final Implementation System

As stated previously, this singular node implementation

extracts all properties of the media across the time-based trace
of data: optical translucence, media uniformity, sheet density,
and surface roughness. Replacing impedance with uniformity
Fig. 4 Preliminary Implementation System and stiffness with roughness, ultimately allowed for the
consolidation and similar performance. In addition, the
With this system, four total nodes were being considered, dynamic nature of the measurement allows for a secondary
all of which were tailored to the purpose of collecting a piece of data to be extracted in the form of the media and
specific piece of data. These data points were then used as machine interaction. This interaction adds to the robustness of
features for a support vector machine that was used as the such an architecture.
machine learning algorithm. The limitations that exist with
62 Ryan Bradley et al. / Procedia CIRP 61 (2017) 58 – 62

In addition to the functionality, the economics are also big data for sustainable value creation. Many industries can
compelling. The system went from a bloated system that benefit from the counter approach, especially manufacturing
would struggle to justify itself in the form of value-added and due to their unique use of unstructured and structured data to
operational efficiency, to a more sustainable system that drive improvements in energy efficiency, reduced resources,
makes up a fraction of the cost, energy, and resources. cost reduction, scalability, and environmental sustainability. A
To be able to leverage this cheap singular sensor in such a case study was presented that looks at the consumer printing
compelling way, one must look at the support vector machine process and a sensor solution that aims at improving the field
that drove the functionality. Through the dynamic time series service issues with various products out in the field. The case
data, features were able to be selected in parallel with the study validates the premise of co-designing a product,
knowledge of designing the sensor systems themselves to be process, and/or system in parallel with the IoT framework in
able to stretch the sensor hardware and machine learning order to minimize costs and improve functionality. The
algorithm to its full potential. Figure 6 shows the feature combination of the domain/expert knowledge and the machine
selection that was determined in order to create the largest learning algorithm creates a robust framework for use in
separation between the various media types. various applications. Future work can entail extending this
approach to other industry sectors to show how big data can
be leveraged for sustainable value creation.

References

[1] Bughin, Jacques, Michael Chui, and James Manyika. "Clouds, big data,
and smart assets: Ten tech-enabled business trends to watch." McKinsey
Quarterly 56.1 (2010): 75-86.
[2] Wu, Dazhong, et al. "Cloud-based design and manufacturing: A new
paradigm in digital manufacturing and design innovation." Computer-
Aided Design 59 (2015): 1-14.
[3] Ross, Jeanne W., Cynthia M. Beath, and Anne Quaadgras. "You may
not need big data after all." Harvard Business Review 91.12 (2013): 90-
+.
[4] Uckelmann, Dieter, Mark Harrison, and Florian Michahelles. "An
architectural approach towards the future internet of things."
Architecting the internet of things. Springer Berlin Heidelberg, 2011: 1-
24.
[5] Sundmaeker, Harald, et al. "Vision and challenges for realising the
Internet of Things." Cluster of European Research Projects on the
Internet of Things, European Commision (2010).
[6] Dubey, Rameshwar, et al. "The impact of big data on world-class
sustainable manufacturing." The International Journal of Advanced
Manufacturing Technology 84.1-4 (2016): 631-645.
Fig. 6 Support Vector Machine Feature Selection [7] Hart, Jane K., and Kirk Martinez. "Toward an environmental Internet of
Things." Earth and Space Science 2.5 (2015): 194-200.
Four zones can clearly be seen in Figure 6. The separation [8] Fang, Shifeng, et al. "An integrated system for regional environmental
monitoring and management based on internet of things." IEEE
between the various media types can be seen from the average
Transactions on Industrial Informatics 10.2 (2014): 1596-1605.
trace values. Each zone was used to devise statistical metrics [9] Ramaswamy, Satya. "What the companies winning at big data do
that were then fed into the algorithm. The algorithm was differently." Bloomberg, June: http://www. bloomberg. com/news/2013-
subsequently used to make a calculated guess at the paper 06-25/what-the-companies-winning-at-big-data-do-differently. html
type in order to be able to set the device to the appropriate (2013).
[10] Pan, Jianli, et al. "An Internet of Things Framework for Smart Energy in
operating parameters.
Buildings: Designs, Prototype, and Experiments." IEEE Internet of
Things Journal 2.6 (2015): 527-537.
4.4 Results [11] Tao, Fei, et al. "Internet of Things and BOM-Based Life Cycle
Assessment of Energy-Saving and Emission-Reduction of Products."
The five considered media types were trained and then IEEE Transactions on Industrial Informatics 10.2 (2014): 1252-1261.
[12] Demirkan, Haluk, and Dursun Delen. "Leveraging the capabilities of
tested with the proposed solution. Overall, 92.23% of media
service-oriented decision support systems: Putting analytics and big data
types were determined correctly, and 99.3% were determined in cloud." Decision Support Systems 55.1 (2013): 412-421.
to be in a range of satisfactory performance. In addition, it [13] Ahearn, Mary Clare, Walt Armbruster, and Robert Young. "Big Data's
was estimated that real cost savings and reductions in energy, Potential to Improve Food Supply Chain Environmental Sustainability
paper, and service action can be realized throughout the and Food Safety." International Food and Agribusiness Management
Review 19.A (2016).
product life-cycle.
[14] Koo, Dan, Kalyan Piratla, and C. John Matthews. "Towards Sustainable
Water Supply: Schematic Development of Big Data Collection Using
5. Conclusions Internet of Things (IoT)." Procedia Engineering 118 (2015): 489-497.

The proposed approach for designing an IoT architecture

shows an opportunity for minimizing cost while leveraging