Content uploaded by Hossein Davari
Author content
All content in this area was uploaded by Hossein Davari on Oct 11, 2018
Content may be subject to copyright.
Industrial Artificial Intelligence for industry 4.0-based manufacturing
systems
Jay Lee, Hossein Davari, Jaskaran Singh
⇑
, Vibhor Pandhare
Center for Industrial Artificial Intelligence (IAI), Department of Mechanical Engineering, University of Cincinnati, Cincinnati, OH 45221-0072, USA
article info
Article history:
Received 20 July 2018
Received in revised form 2 September 2018
Accepted 9 September 2018
Available online 10 September 2018
Keywords:
Industrial AI
Industry 4.0
Big data
Smart manufacturing
Cyber physical systems
abstract
The recent White House report on Artificial Intelligence (AI) (Lee, 2016) highlights the significance of AI
and the necessity of a clear roadmap and strategic investment in this area. As AI emerges from science
fiction to become the frontier of world-changing technologies, there is an urgent need for systematic
development and implementation of AI to see its real impact in the next generation of industrial systems,
namely Industry 4.0. Within the 5C architecture previously proposed in Lee et al. (2015), this paper pro-
vides an insight into the current state of AI technologies and the eco-system required to harness the
power of AI in industrial applications.
Ó2018 Society of Manufacturing Engineers (SME). Published by Elsevier Ltd. All rights reserved.
1. Introduction to industrial Artificial Intelligence
Artificial Intelligence (AI) is a cognitive science with rich
research activities in the areas of image processing, natural lan-
guage processing, robotics, machine learning etc. Historically,
Machine Learning and AI have been perceived as black-art tech-
niques and there is often a lack of compelling evidence to convince
industry that these techniques will work repeatedly and consis-
tently with a return on investment. At the same time, the perfor-
mance of machine learning algorithms is highly dependent on a
developer’s experience and preferences. Hence, the success of AI
in industrial applications has been limited. On the contrary, Indus-
trial AI is a systematic discipline, which focuses on developing, val-
idating and deploying various machine learning algorithms for
industrial applications with sustainable performance. It acts as a
systematic methodology and discipline to provide solutions for
industrial applications and function as a bridge connecting aca-
demic research outcomes in AI to industry practitioners.
AI-driven automation has yet to have a quantitatively major
impact on productivity growth [1]. Besides present day industries
are facing new challenges in terms of market demand and compe-
tition. They are in need of a radical change known as Industry 4.0.
Integration of AI with recent emerging technologies such as Indus-
trial Internet of Things (IIoT) [3], big data analytics [4–6], cloud
computing [7–9] and cyber physical systems [2,10–11] will enable
operation of industries in a flexible, efficient, and green way. Since
Industrial AI is in infancy stage, it is essential to clearly define its
structure, methodologies and challenges as a framework for its
implementation in industry. To this end, we designed an Industrial
AI ecosystem, which covers the essential elements in this space
and provides a guideline for better understanding and implement-
ing it. Furthermore, the enabling technologies that an Industrial AI
system can be built upon are described. Fig. 1-a provides a sche-
matic comparison of the desired system performance of Industrial
AI with other learning systems over time.
2. Key elements in Industrial AI: ABCDE
The key elements in Industrial AI can be characterized by
‘ABCDE’. These key elements include Analytics technology (A),
Big data technology (B), Cloud or Cyber technology (C), Domain
knowhow (D) and Evidence (E). Analytics is the core of AI, which
can only bring value if other elements are present. Big data tech-
nology and Cloud are both essential elements, which provide the
source of the information (data) and a platform for Industrial AI.
While these elements are essential, domain knowledge and Evi-
dence are also important factors that are mostly overlooked in this
context. Domain knowhow is the key element from the following
aspects: 1) understanding the problem and focus the power of
Industrial AI into solving it; 2) understanding the system so that
right data with the right quality can be collected; 3) understanding
the physical meanings of the parameters and how they are associ-
ated with the physical characteristics of a system or process; and
https://doi.org/10.1016/j.mfglet.2018.09.002
2213-8463/Ó2018 Society of Manufacturing Engineers (SME). Published by Elsevier Ltd. All rights reserved.
⇑
Corresponding author.
E-mail address: singh2jn@ucmail.uc.edu (J. Singh).
Manufacturing Letters 18 (2018) 20–23
Contents lists available at ScienceDirect
Manufacturing Letters
journal homepage: www.elsevier.com/locate/mfglet
4) understanding how these parameters vary from machine to
machine. Evidence is also an essential element in validating Indus-
trial AI models and incorporate them with cumulative learning
ability. By gathering data patterns and the evidence (or label) asso-
ciated with those patterns can only we improve the AI model to
become more accurate, comprehensive and robust as it ages.
Fig. 1-b shows how AI can drive us from visible space to invisible,
and from solving the problems to avoiding them before they
surface.
3. Industrial AI eco-system
Fig. 2 shows the proposed Industrial AI ecosystem, which
defines a sequential thinking strategy for needs, challenges, tech-
nologies and methodologies for developing transformative AI sys-
tems for industry. Practitioners can follow this diagram as a
systematic guideline for developing a strategy for Industrial AI
development and deployment. Within the targeted industry, this
ecosystem defines the common unmet needs such as Self-aware,
Self-compare, Self-predict, Self-optimize and Resilience. This chart
also includes four main enabling technologies including Data Tech-
nology (DT), Analytic Technology (AT), Platform Technology (PT)
and Operations Technology (OT). These four technologies can bet-
ter be understood when put in the context of the Cyber-Physical
Systems (CPS), proposed in [2]. As depicted in Fig. 3, these four
technologies (DT, AT, PT and OT) are the enablers for achieving suc-
cess in Connection, Conversion, Cyber, Cognition and Configura-
tion, or 5C. This section of the paper provides a brief description
of each of the mentioned technologies.
3.1. Data technologies (DT)
Data Technologies are those technologies, which enable suc-
cessful acquisition of useful data with significant performance
metrics across dimensions. Therefore, it becomes a co-enabler of
the ‘Smart Connection’ step in the 5C architecture by identifying
the appropriate equipment and mechanism for acquiring useful
data. The other aspect of data technologies is data communication.
Time
ecnamrofreP
Experiences
Discontinued
Upgrade
Expert Systems (Rule-based)
AI and Machine Learning
Industrial AI
(Systematic Learning Approach)
Expert’s Experiences
Visible Invisible
Solve
Avo id
Problem Solving
Through Continuous
Improvement and
Standard Work
Utilize New Methods/
Techniques to Solve
The Unknown Problems
Value Creation
using
Smarter Information
For Unknown Knowledge
Utilize New
Knowledge/
Technologies
For Value-added
Improvement
Fig. 1. a) Comparison of Industrial AI with other learning systems; b) The impact of Industrial AI: from solving visible problems to avoiding invisible.
Fig. 2. Industrial AI Eco-system.
J. Lee et al. / Manufacturing Letters 18 (2018) 20–23 21
Communication in Smart Manufacturing extends beyond the rela-
tively straight-forward transfer of acquired data from its source to
the point of analysis. It involves: 1) Interaction between manufac-
turing resources in the physical-space. 2) Transfer and storage of
data from machines and the factory floor to the Cloud. 3) Commu-
nication from physical space to cyber space. 4) Communication
from the cyber-space to the physical-space. In addition, DT needs
to address 3B issues of data systems, namely, broken, bad, and
background of data [6].
3.2. Analytics technologies (AT)
Analytics Technology converts the sensory data from critical
components into useful information. Data driven modeling uncov-
ers hidden patterns, unknown correlations and other useful infor-
mation from manufacturing systems. This information can be used
for asset health prediction, such as generating a health value or a
remaining useful life value, which can be used for machine prog-
nostics and health management. Analytic Technologies integrate
this information with other technologies for improved productivity
and innovation.
3.3. Platform technologies (PT)
Platform technologies include the hardware architecture for
manufacturing data storage, analysis and feedback. A compatible
platform architecture for analyzing data is a major deciding factor
for realizing smart manufacturing characteristics such as agility,
complex-event processing, and so on. Three major types of platform
configurations are generally found – stand-alone, embedded and
cloud. Cloud computing is a significant advancement in Information
and Communication Technologies with regard to computational,
storage and servitization capabilities. The cloud platform can pro-
vide rapid service deployment, high level of customization, knowl-
edge integration, and effective visualization with high scalability.
3.4. Operations technology (OT)
Operation technology here refers to a series of decisions made
and actions taken based on the information extracted from data.
While delivering machine and process health information to the
operators is valuable, an Industry 4.0 factory goes beyond and
enables machines to communicate and make decisions based on
the provided insight. This machine-to-machine collaboration can
be between two machines in a shop floor, or machines in two dif-
ferent factories far apart. They can share their experience on how
adjusting specific parameters can optimize performance, and
adjust their production based on the availability of other machines.
In an industry 4.0 factory, Operations technology is the last step
leading to the following four capabilities: 1) Self-aware 2) Self-
predict, 3) Self-Configure and 4) Self-Compare.
4. Case Study: Intelligent spindle system
This section describes the application and implementation of
the Industrial AI architecture framework described in Section 3
to machine tool spindle of a Computer numerical control (CNC)
machine. In manufacturing industry, the health condition of the
machine tool spindle is of major importance and this case study
aims to show how Industrial AI-powered by the four enabling tech-
nologies can provide a full solution for real-time monitoring and
performance prediction of a machine tool spindle. This system is
designed to minimize maintenance costs and optimize product
quality, simultaneously. Based upon Fig. 3, the first step in the
guideline is to consider the common unmet needs in this applica-
tion area. For addressing the unmet needs (a self-aware and self-
optimizing machine) the challenges of 1) data quality, 2) multi-
regime complexity, 3) machine-to-machine variation, 4) incorpo-
rating expert system and 5) complexity of multi-source data need
to be considered. Fig. 4 provides an overview of how DT, AT, PT and
OT are utilized to address these challenges and develop an intelli-
gent spindle system.
5. Challenges of Industrial Artificial Intelligence
The expectations from Industrial AI are versatile and enormous
and even a partial fulfilment of these expectations would represent
unique and real challenges of applying AI to industries. Among the
existing challenges and complexities, the following ones are of
higher importance and priority:
5.1. Machine-to-machine interactions
While AI algorithms can accurately map a set of inputs to a set
of outputs, they are also susceptible to small variations in the
inputs caused by variations from machine to machine. It needs to
Fig. 3. Enabling technologies for realization of CPS in manufacturing.
22 J. Lee et al. / Manufacturing Letters 18 (2018) 20–23
ensure that individual AI solutions do not interfere/conflict with
the working of other systems, further down the line.
5.2. Data quality
AI algorithms require massive and clean data sets with mini-
mum biases. By learning from inaccurate or inadequate data sets,
the downstream results can be flawed.
5.3. Cybersecurity
The increasing use of connected technologies makes the smart
manufacturing system vulnerable to cyber risks. Currently, the
scale of this vulnerability is under-appreciated and the industry
is not prepared for the security threats that exist [12].
6. Conclusion
As AI emerges from science fiction to become the frontier of
world-changing technologies, there is an urgent need for system-
atic development and implementation of AI to see its real impact
in the next generation of industrial systems, namely Industry 4.0.
This study aims to define the term Industrial AI and put it into
the perspective of Industry 4.0 paradigm. In addition, by providing
an overview of the Industrial AI eco-system in today’s manufactur-
ing, this paper aims to provide a guideline for strategizing the
efforts toward realization of Industrial AI systems.
References
[1] Lee K. Artificial intelligence, automation, and the economy. The White. House
Blog; 2016.
[2] Lee J, Bagheri B, Kao HA. A cyber-physical systems architecture for industry
4.0-based manufacturing systems. Manuf Lett 2015;3:18–23.
[3] Da Xu L, He W, Li S. Internet of things in industries: A survey. IEEE Trans Ind Inf
2014;10(4):2233–43.
[4] Lee J, Lapira E, Bagheri B, Kao HA. Recent advances and trends in predictive
manufacturing systems in big data environment. Manuf Lett 2013;1(1):38–41.
[5] Shi J, Wan J, Yan H, Suo H. November. A survey of cyber-physical systems. In:
Wireless Communications and Signal Processing (WCSP), 2011 International
Conference on. IEEE. 2011. p. 1–6.
[6] Lee J, Ardakani HD, Yang S, Bagheri B. Industrial big data analytics and cyber-
physical systems for future maintenance & service innovation. Procedia CIRP
2015;38:3–7.
[7] Zhang L, Luo Y, Tao F, Li BH, Ren L, Zhang X, et al. Cloud manufacturing: a new
manufacturing paradigm. Enterprise Inf Syst 2014;8(2):167–87.
[8] Wu D, Greer MJ, Rosen DW, Schaefer D. Cloud manufacturing: Strategic vision
and state-of-the-art. J Manuf Syst 2013;32(4):564–79.
[9] Yang S, Bagheri B, Kao HA, Lee J. A unified framework and platform for
designing of cloud-based machine health monitoring and manufacturing
systems. J Manuf Sci Eng 2015;137(4):040914.
[10] Baheti R, Gill H. Cyber-physical systems. Impact Control Technol 2011;12
(1):161–6.
[11] Leitao P, Karnouskos S, Ribeiro L, Lee J, Strasser T, Colombo AW. Smart agents
in industrial cyber–physical systems. Proc IEEE 2016;104(5):1086–101.
[12] Tuptuk N, Hailes S. Security of smart manufacturing systems. J Manuf Syst
2018;47:93–106.
Fig. 4. Platform technology for intelligent spindle.
J. Lee et al. / Manufacturing Letters 18 (2018) 20–23 23