Content uploaded by Nabil El Bazi
Author content
All content in this area was uploaded by Nabil El Bazi on Jul 13, 2022
Content may be subject to copyright.
978-1-6654-6925-8/22/$31.00 ©2022 IEEE
Digital Twin Architecture for Mining Industry: Case
Study of a Stacker Machine in an Experimental
Open-Pit Mine
Nabil Elbazi
Laboratory of Industrial Engineering
Faculty of Science and Technology
University Sultan Moulay Slimane,
Beni Mellal
Green Tech Institute (GTI)
Mohammed VI polytechnique university
Benguerir, Morocco
nabil.elbazi@um6p.ma
Mustapha Mabrouki
Laboratory of Industrial Engineering
Faculty of Science and Technology
University Sultan Moulay Slimane,
Beni Mellal
m.mabrouki@usms.ma
FatimaEzzahrae Hammouch
Green Tech Institute (GTI)
Mohammed VI polytechnique university
Benguerir, Morocco
fatimaezzahra.hammouch@um6p.ma
Ahmed chebak
Green Tech Institute (GTI)
Mohammed VI polytechnique university
Benguerir, Morocco
Ahmed.chebak@um6p.ma
Abstract— Digitalization in mining industry has become an
important component nowadays in order to improve the
productivity, the efficiency while increasing the availability of
machines and different equipment The use of digital twin as a
feature in mining industry has shown promising results to deal
with its multiple challenges such as maintenance, production,
energy consumption. In this paper, a comparative study is
presented of developed digital twins in different applications
such as energy management, manufacturing, industrial and
campus, the goal is to design a conceptual architecture of a
proposed digital twin within presenting a case study of a stacker
machine in the experimental open pit mine of Benguerir. This
design presented by 4 layers : physical, Data pre-processing,
Edge computing, and cloud data, the goal is to work on
interactions between these layers to enhance the performance of
different mining machines. The case study elucidates a practical
result on Stacker machine used in mining industry simulating
the mechanism and the automatism of this system. This
developed digital twin will be used to simulate critical scenarios
and see the behavior of the stacker components in order to
optimize the usage of this machine increasing its availability and
reliability.
Keywords—Digital Twin, Mining Industry, Artificial
Intelligence, Predictive maintenance, Concept, Design,
Automation
I. INTRODUCTION
A digital twin is a digital replica of an object, process, or
system that can be used for various purposes. The digital
representation indicates both the elements and the dynamics
of how an Internet of Things device functions over the course
of its lifetime. A digital twin also incorporates historical data
from the past use of the machine that it incorporates into its
digital model. Digital twins are utilized in a variety of
industries to improve the operation and maintenance of
physical assets, systems, and manufacturing processes. Digital
twins are a formative technology for the Industrial Internet of
Things, where physical objects can live and interact virtually
with other machines and people. According to PWC France
Agency's definition, a digital twin is "a dynamic software
model of a process, product or service. More simply, the
digital twin can be seen as the digital model of a real system.
In an increasingly competitive environment where
economic players must react ever more swiftly, predict market
developments while decreasing costs, the deployment of the
digital twin has several advantages for companies, particularly
those in the industry sector. This technology offers, for
example, numerous possibilities for improving the
performance of products and industrial systems, for
monitoring and anticipating all those stages of a product's life
cycle or assuring the scheduling of activities in a production
chain. In the Industry of the Future or Industry 4.0 roadmaps,
the term "digital twin" appears prominently among the key
building blocks of a successful digital transformation. This
term is easy to understand semantically, but it remains obscure
when you take a closer look! Of course, it is a dynamic model
of a machine, a process or even a complete factory. But if we
stop there, it is a model as it exists and as it has been used in
the industry for decades! A digital twin is a more systematic
and therefore more ambitious concept that assumes a strong
link with reality; in fact, it assumes a duality between the
physical and virtual worlds.
The model is closely linked to reality not only by the
realism of the modeling (multi-scale, multi-physics, 3D
representation...) but also and above all by the updating
(parameterization) in near real time of the model by field
data... This link is maintained throughout the life cycle of the
modeled product or system. It is therefore difficult to imagine
a digital twin without talking about a network of sensors, data
collection and analysis, the Internet of Things or at least a
connected machine, a decision support tool, digital chaining
with MES (Manufacturing Execution System), PLM (Product
Life Cycle), ERP (Enterprise Resource Planning), etc. and, in
general, artificial intelligence. Thanks to it, access to data is
facilitated, as well as the manipulation of these data; and this,
even remotely. It helps to make decisions by allowing to test
different scenarios. The new generation of digital twins is
even capable of automating actions: The twin gathers the data,
tries scenarios, and then automatically activates actions once
the optimum scenario is determined.
II. STATE OF ART
A. Digital Twin
A digital twin is a virtual representation of a physical
object that is meant to be accurate. A wind turbine, for
example, is equipped with a variety of sensors that are relevant
to critical areas of operation. These sensors generate
information regarding many elements of a physical object's
performance, such as energy output, which is a key element in
mining industry where it is very important to forecast and
monitor the energy consumption [1] temperature, weather
conditions, and so on. This information is subsequently sent
to a processing system and applied to the digital copy. Once
such data is available, the virtual model may be used to
conduct simulations, investigate performance concerns, and
produce potential changes, all with the purpose of providing
important insights that can later be brought back to the original
physical device[2]. The Digital Twin has several definitions,
but it is best described as the seamless integration of data
between a physical and virtual system in either way.[3], Figure
1 describes the difference between digital model, shadow and
twin, and the digitalization levels of integration for each one
of them, thus there are 3 levels of integration, which are
characterized by the data flow exchange between the physical
plant and the digital system regardless of being a digital model
or digital shadow or digital twin. in application like open pit
mines many data are entered manually in this paper some parts
of the design are represented as digital shadow and using
Programmable Logic Controllers and automation system most
parts are fully integrated digital twin.
TABLE I. T
ABLE
.
D
IGITAL TWIN APPLICATIONS AND FEATURES
Team Year Application Features Digital
Twin
Thomas
[4]
2021 industrial heat
transfer
station
Functional mock
up interface
Python
OPC UA
Concept
Yinping
[5]
2022 Storage yard
scheduling
Genetic
optimization
Neural network
prediction
Co-simulation
Automati
on
Zongmin
[6]
2021 Population
Health
management
virtual-real
integration of
industrial IoT
Concept
Christop
h [7]
2019 Power System
mirror
Neural network
Energy
management
Concept
and
design
Edward
[8]
2020 EV Charging
Micro grid
Smart energy
management
systems
Concept
Vivi [9] 2019 Campus Building Case
study
Sofia
[10] 2021 Energy
management
Building AI Concept
Abdelali
[11] 2021 Energy
management
Building Case
study
Ahmed
[12] 2020
Cyber-
physical
systems
Energy
management
Cyber physical
Design
and
impleme
ntation
Kamil
[13] 2020 Manufacturin
g
Assembly system
Industry 4.0
Concept
Damir
[14] 2019
Energy
management
systems
Distributed EMS
Prediction
Simulation
Concept
Simulatio
n
Nada
[15]
2021 Shop floor
monitoring
Monitoring
Cloud
collaboration
Edge cloud
Concept
and case
study
According to Gartner, 13% of firms adopting IoT projects
are currently using digital twins, while the remaining 62% are
either in the process of installing digital twins or plan to do so.
According to Markets and Markets' recent analysis, the digital
twin market is expected to rise from $3.8 billion in 2019 to
$35.8 billion by 2025, at a CAGR of 37.8 percent [16].
Fig. 1. The levels of integration for a Digital Model, Digital Shadow and
Digital Twin
B. Digital twin applications
Many digital twin applications in various industrial sectors
and residential case studies have been introduced in recent
work, the main goals of these digital twins are Optimization,
Scheduling, Smart Energy management systems, Predictive
maintenance and both if a well integration of monitoring
system of the power grid and predictive maintenance for the
power transformer[17], using different features and
methodologies, such as machine learning algorithms,
prediction techniques, simulation, co-simulation genetic
algorithms for optimization and different technologies such as
automation, programming and monitoring techniques.
As mentioned in the different case studies, as Table 1 lists
digital twin applications and features, DTs are used for smart
manufacturing, scheduling and process automation. However,
in mining industry the use of digital twins still not be
developed, these applications can improve the Smart Energy
Management Systems, particularly for open-pit mines, where
smart meters and predictive analyses are integrated[18].
DTs can also be used to calculate and estimate the life loss of
machines as a feature of predictive maintenance typically for
Squirrel Cage Induction Motors which are the most used type
of loads in mining industry [19].
C. Mining machines
In mining industry, mainly, we make reference to Bucket-
Wheel Reclairems, Belt Conveyors and Stacker machines
which are very critical elements in productions and stockyard
in an open-pit mines, where monitoring and maintenance are
mandatory because those mining machines are a complicated
industrial process for dealing with huge equipment that suffers
from several external interferences such as wear of
mechanical components, imprecision of process variables, and
fluctuation in physical and chemical properties of the material
to be processed, as an illustration, the Bucket Wheel
Reclaimer ensures the operation of picking up the yard’s
stored material in stack from and transporting it to the ship
loader for shipping via conveyor belts [20], which is
considered as an important component of the belt conveyor,
transports materials and transfers power, and its cost accounts
for 30–50% of the entire cost of the conveyor. When the
rollers break or the material becomes stuck, conveyor belts
frequently suffer from longitudinal ripping, surface scratches,
and other damage. If the damage is not discovered and
addressed in a timely and effective manner, it will worsen,
resulting in belt breaking and other mishaps[21].
One of the key focuses in the mining sector has been
reliable, real-time, and cost-effective condition monitoring of
mining conveyors. This is owing to the continuous
arrangement of conveyor structure that spans kilometers in
length, where a breakdown in one of the conveyor components
can cause severe disruption to the mining company's whole
operational system. This occurrence not only causes economic
loss, but it also endangers site personnel's safety. The belt
conveyor system is made up of four major components: the
driving unit, pulleys, belt, and idlers[22].
Then there is the stacker machine, is a huge equipment
used to handle bulk materials. Its purpose is to load raw
material like limestone, ores, and grains onto a stockpile. They
are used to stack in a variety of configurations, including cone
stacking and chevron stacking. Size segregation occurs while
stacking in a single cone, with coarser material migrating out
towards the base.
Additional cones are stacked adjacent to the initial cone in
raw cone ply stacking. The stacker in diagonal stacking moves
along the length of the stockpile, adding layer upon layer of
material. Stackers and reclaimers were initially operated
manually, with no remote control. Modern machines are
usually semi-automatic or fully automated, with settings
controlled remotely. A programmable logic controller with a
human-machine interface for display is commonly employed,
and it is linked to a central control system. Digital Twin
Applications [23]. [24].
D. Challenges of Digital Twin Applications in Mining
Industry
The mining industry deals with the extraction of valuable
minerals and other geological elements. The extracted
minerals are converted into a mineralized state that benefits
the prospector or miner financially. Metals production, metals
investing, and metals trading are all common operations in the
mining business.
The challenges that the mining sector faces are outlined in
this section. Despite the fact that these challenges are
unrelated to big data, their presence has boosted the demand
for new technologies and ideas. Using the digital twin
technology to its full potential can help the mining industry
enhance productivity and respond more quickly to
uncertainty. Notably, the use of digital twins in the mining
industry is not a match for the issues listed below.
Due to its particular merits, the digital twin should instead
encourage the solution of these challenges. Furthermore, in
the long run, a digital twin can aid in problem-solving, such as
the default analysis and waste time in productivity
III. D
IGITAL
T
WIN
A
RCHITECTURE
A. Digital Twin Components
Digital Twins are viewed in a variety of ways. Most
researchers estimate that simulation should be at the center of
Digital Twin research. Others contend that Digital Twin has
three components: physical, virtual, and connectivity. The
basic framework is shown in Figure 1, in which the virtual
space is transferred to the physical space via the connection
portion, which transfers data and information.
B. Conceptual Architecture of a Digital Twin
The conceptual architecture shown in fig 3 presents the
design of a two-level Digital Twin which is the digital shadow.
that includes four layers: physical layer, data preprocessing
layer, edge computing layer and cloud layer, as well as the
digital treads depicted are used to characterize the digital
twin’s degree of maturity either its traceability back to the
physical asset’s requirements, parts and control systems. Each
layer will be described in detail in its own subsection.
1) Physical layer
Data must first be acquired from physical assets on the open
pit mine until it enters into the Digital Twin framework. The
mine's data is dispersed in a variety of ways, including sensor
reading, videos and images, staff clocking system, electric
meters, and so on. Any information relevant to the goal of the
Digital Twin, such as equipment operating data, scheduling
data, and production environment data, must be included in
the collected data. Essentially, Mine data consists of
information gathered from humans, machine, material, and
environment.
2) Data preprocessing layer
Data preprocessing involves converting raw data into
well-formed data sets in order to use data mining methods.
Raw data is frequently incomplete and formatted
inconsistently. The success of every project involving data
analytics is directly proportional to the quality of data
preparation. After that the collect of data is done, the data
continue its journey thorough the DT framework next layer,
by entailing its different applications such as Data Cleaning
which entails filling in missing values or deleting rows with
missing data, smoothing noisy data, and correcting data
discrepancies? also the Data Integration which is the process
of combining data with various representations and resolving
data conflicts.
On the other hand, Databases can become slower, more
expensive to access, and more difficult to store when the
volume of data is large. In a data warehouse, Data Reduction
seeks to give a simplified version of the data.
3) Edge computing layer
Edge computing is processing that takes place near a
system's data or end user where information is coming from
or going to. By minimizing latency and lag, edge architecture
enables for faster processing.
Fig. 2. The major three Component of a Digital Twin
Fig. 3. The conceptual architecture of the proposed digital twin for mining industry
Edge-based applications and programs can operate more
quickly and efficiently, resulting in a better user experience
and overall performance. Edge computing is a distributed
information technology (IT) architecture wherein client data
is processed as close to the original source as possible at the
network's perimeter.
A virtual Twin Real-time monitoring operations should be
performed in the edge computing layer for reasons such as
enhancing the Digital Twin's real-time capabilities and
minimizing the cloud's computation complexity. The response
time, awareness, and safety of the various mine elements and
equipements will all improve significantly as a result of this.
Real-time control, real-time state optimization, equipment
prognosis, and other equipment-specific jobs, particularly
real-time tasks, are examples of the virtual models’ tasks. A
closed-loop Digital Twin module could be developed for real-
time control to offer real-time actions if an anomaly arises.
Physical systems, for example, can be changed and controlled
in real time based on simulations of virtual models. However,
greater efforts should be made to ensure that Digital Twin
input is safe.
4) Cloud layer
Here, the last layer of the DT, it is the cloud layer, which is
characterized by hosting the cloud database, the main database
that receives data from the previous layer for either storing and
feeding the virtual mine and its Optimization & Predictive
Data applications, including predictive production and
maintenance scheduling, Process Optimization, supply chain,
and predictive shift-work scheduling. Furthermore, those
applications will be carried out by interacting with virtual
models that exist on the edge computing layer locally.
For particular, the cloud layer's predictive maintenance
application will interface with the edge computing layer's
online defects diagnosis and online process quality control
per each component, machine station to develop a general
predictive maintenance schedule for the mine.
On the other hand, models performed in the edge computing
layer must be replicated in the cloud layer so that if an edge
computing application fails, its models are not lost. In
addition, in both the edge computing and cloud layers, the
cloud layer is responsible for training and optimizing
algorithms and models. The virtual models algorithms will be
updated and optimized in the cloud on a regular basis and then
transmitted back to the edge, ensuring that the edge layer has
the most up-to-date versions of algorithms and models.
IV. C
ASE
S
TUDY
At the end of the product production operations, the
storage machine (Stacker) allows to store the final product
according to the quality of phosphate in the suitable stock as
shown in table 2, the stacker process characteristics presented
are taken into consideration while developing the digital twin
in order to study the behavior of different components and its
impact on the production and the maintenance main key
performance indicators.
The goal is to control the automatism in the simulation in
parallel with the real case study and compare these different
behaviors and test critical scenarios.
TABLE II. S
TACKER
P
ROCESS
C
HARACTERISTICS
Measurand Value
Output 1200 tons/hours
Boom length 38.265 meter
Swing angle 190°
Slewing speed 10 meter/minute
Boom inclination 17°
Discharge height 17,150 meters
Track gauge 6 meters
Travelling speed 30 meter/minute.
TABLE III. STACKER CHARACTERISTICS AND COMPONENTS
Mechanism Power Train
system
Component
Characteristics Sensor
Translation 6 Motors with
gearboxes
Power: 7.5
kW
2 Magnetic
sensors
Voltage: 500
V
13 Capacitif
sensors
Jib lifting
and
lowering
(2 double
acting
cylinders)
Hydraulic unit
Power: 55/75
kW 4 Magnetic
sensors
Voltage: 500
V
boom
conveyor
motor and
reducer
Power: 5.5
kW
Voltage: 500
V
power
winder
motor and
reducer
Power: 1.5
kW
Voltage: 500
V
Arrow
orientation
motor and
reducer
Power: 5.5
kW 6 Magnetics
sensors
Voltage: 500
V
It is managed by a single Schneider M340
Ethernet/ModBus CPU that controls its mechanisms, boom
lift/lower, boom slewing, translation and power reel. Table 3
describes the main components of the system mechanisms and
components. All the developments must be made in
compatibility with the Schneider automats installed on the
machine. Wifi is used to connect the storage equipment to the
control rooms. There are two modes of operation of the
storage machine, the automatic mode and the manual / local
mode. Figure 3 shows the mechanism of the selected digital
twin with different modes of automatisms, integrating security
and check lists which are included in the digital twin to
simulate the critical behaviors of components.
V. RESULT
The work presented in this article is a significant approach
toward the design of a digital twin of the loading park's
Stacker machine; it is a digital twin that faithfully represents
the operative and control part of the automatism as well as the
mechanisms (actions, orientation, displacement and lifting of
the boom), with a real link with the PLC of the system. The
DT in its first level which is based on a digital simulation of
the real process, thorough a software solution dedicated to the
simulation of automated systems (electrical diagrams,
machines, and processes). Thanks to a patented modeling
technology, it allows users to design and provide realistic
virtual systems to test the design and control of real systems.
It is a simulation environment for automated systems, with
virtual modules available and configurable for connection to
PLCs for the purpose of validating the control-command
system SIMAC is a development environment that combines
virtual modules and simulation connected to the PLC.
Fig. 4. The automatism flowchart of the designed system
VI. CONCLUSION AND FUTURE WORK
This paper presents a conceptual architecture that shows
up the details of the design of DT particularly in the mining
industry, furthermore the benefits of using that technology to
reduce many challenges faced in the mining industry. In the
proposed architecture of DT for the mine, four layers are
required: physical, Pre-processing data, Edge computing and
Cloud Data, which integrate many applications and services
that encapsulate the digital treads according to each level of
maturity of using: Basic, Full, Enhanced and the Next
generation. As a case study of that architecture, this work
represents a digital twin design for a stacker machine, in
particular, it stands for representing the operative and control
part of the automatism including the connection with the real
PLC of the system. As a future work, we would enlarge this
work by developing the digital Twin of the other equipment
that constitute the production line of the open pit mine in order
to form the digital twin of the mine, moreover we would
reform and revise the applications and services presented in
each layer by focusing on many research points such as the
deployment of blockchain technology, predictive
maintenance and the predictive shift-work scheduling in order
to build an opportunistic maintenance application into the
proposed design of the digital twin for an Open Pit Mine.
REFERENCES
[1] O. Laayati, M. Bouzi, and A. Chebak, “Smart Energy Management
System: Design of a Monitoring and Peak Load Forecasting System
for an Experimental Open-Pit Mine,” p. 18, 2022.
https://doi.org/10.3390/asi5010018.
[2] “What is a digital twin?” https://www.ibm.com/topics/what-is-a-
digital-twin (accessed Jan. 20, 2022).
[3] A. Fuller, Z. Fan, C. Day, and C. Barlow, “Digital Twin: Enabling
Technologies, Challenges and Open Research,” IEEE Access, vol. 8,
pp. 108952–108971, 2020, doi: 10.1109/ACCESS.2020.2998358.
[4] T. Kohne, M. Burkhardt, L. Theisinger, and M. Weigold, “Technical
and digital twin concept of an industrial heat transfer station for low
exergy waste heat,” Procedia CIRP, vol. 104, pp. 223–228, Jan.
2021, doi: 10.1016/j.procir.2021.11.038.
[5] Y. Gao, D. Chang, C.-H. Chen, and Z. Xu, “Design of digital twin
applications in automated storage yard scheduling,” Advanced
Engineering Informatics, vol. 51, p. 101477, Jan. 2022, doi:
10.1016/j.aei.2021.101477.
[6] Z. Jiang, Y. Guo, and Z. Wang, “Digital twin to improve the virtual-
real integration of industrial IoT,” Journal of Industrial Information
Integration, vol. 22, p. 100196, Jun. 2021, doi:
10.1016/j.jii.2020.100196.
[7] M. C. Brosinsky, M. X. Song, and D. Westermann, “Digital Twin -
Concept of a Continuously Adaptive Power System Mirror,” p. 6,
2019.
[8] E. O’Dwyer, “Integration of an energy management tool and digital
twin for coordination and control of multi-vector smart energy
systems,” Sustainable Cities and Society, p. 14, 2020.
[9] V. Qiuchen Lu, A. K. Parlikad, P. Woodall, G. D. Ranasinghe, and
J. Heaton, “Developing a Dynamic Digital Twin at a Building Level:
using Cambridge Campus as Case Study,” in International
Conference on Smart Infrastructure and Construction 2019 (ICSIC),
Cambridge, UK, Jan. 2019, pp. 67–75. doi: 10.1680/icsic.64669.067.
[10] S. Agostinelli, F. Cumo, G. Guidi, and C. Tomazzoli, “Cyber-
Physical Systems Improving Building Energy Management: Digital
Twin and Artificial Intelligence,” Energies, vol. 14, no. 8, p. 2338,
Apr. 2021, doi: 10.3390/en14082338.
[11] A. Agouzoul, M. Tabaa, B. Chegari, E. Simeu, A. Dandache, and K.
Alami, “Towards a Digital Twin model for Building Energy
Management: Case of Morocco,” Procedia Computer Science, vol.
184, pp. 404–410, 2021, doi: 10.1016/j.procs.2021.03.051.
[12] A. Saad, S. Faddel, and O. Mohammed, “IoT-Based Digital Twin for
Energy Cyber-Physical Systems: Design and Implementation,”
Energies, vol. 13, no. 18, p. 4762, Sep. 2020, doi:
10.3390/en13184762.
[13] K. Židek, J. Piteľ, M. Adámek, P. Lazorík, and A. Hošovský,
“Digital Twin of Experimental Smart Manufacturing Assembly
System for Industry 4.0 Concept,” Sustainability, vol. 12, no. 9, p.
3658, May 2020, doi: 10.3390/su12093658.
[14] D. Urazayev, D. Bragin, D. Zykov, R. Hafizov, I. Pospelova, and A.
Shelupanov, “Distributed Energy Management System with the Use
of Digital Twin,” in 2019 International Multi-Conference on
Engineering, Computer and Information Sciences (SIBIRCON),
Novosibirsk, Russia, Oct. 2019, pp. 0685–0689. doi:
10.1109/SIBIRCON48586.2019.8958118.
[15] N. Ouahabi, A. Chebak, M. Zegrari, O. Kamach, and M. Berquedich,
“A Distributed Digital Twin Architecture for Shop Floor Monitoring
Based on Edge-Cloud Collaboration,” in 2021 Third International
Conference on Transportation and Smart Technologies (TST), May
2021, pp. 72–78. doi: 10.1109/TST52996.2021.00019.
[16] “Digital Twins Technology, Its Benefits & Challenges to
Information Security,” GlobalLogic, Jun. 11, 2020.
https://www.globallogic.com/insights/blogs/if-you-build-products-
you-should-be-using-digital-twins/ (accessed Jan. 20, 2022).
[17] O. Laayati, M. Bouzi, and A. Chebak, “Design of an oil immersed
power transformer monitoring and self diagnostic system integrated
in Smart Energy Management System,” in 2021 3rd Global Power,
Energy and Communication Conference (GPECOM), Antalya,
Turkey, Oct. 2021, pp. 240–245. doi:
10.1109/GPECOM52585.2021.9587640.
[18] O. Laayati, M. Bouzi, and A. Chebak, “Smart energy management:
Energy consumption metering, monitoring and prediction for mining
industry,” in 2020 IEEE 2nd International Conference on
Electronics, Control, Optimization and Computer Science
(ICECOCS), Kenitra, Morocco, Dec. 2020, pp. 1–5. doi:
10.1109/ICECOCS50124.2020.9314532.
[19] O. Laayati, M. Bouzi, and A. Chebak, “Smart Energy Management
System: SCIM Diagnosis and Failure Classification and Prediction
Using Energy Consumption Data,” in Digital Technologies and
Applications, vol. 211, S. Motahhir and B. Bossoufi, Eds. Cham:
Springer International Publishing, 2021, pp. 1377–1386. doi:
10.1007/978-3-030-73882-2_125.
[20] J. P. de Moura, P. H. M. Rego, and J. V. da Fonseca Neto, “Online
discrete-time LQR controller design with integral action for bulk
Bucket Wheel Reclaimer operational processes via Action-
Dependent Heuristic Dynamic Programming,” ISA Transactions,
vol. 90, pp. 294–310, Jul. 2019, doi: 10.1016/j.isatra.2019.01.010.
[21] M. Zhang, H. Shi, Y. Zhang, Y. Yu, and M. Zhou, “Deep learning-
based damage detection of mining conveyor belt,” Measurement,
vol. 175, p. 109130, Apr. 2021, doi:
10.1016/j.measurement.2021.109130.
[22] H. Wijaya, P. Rajeev, E. Gad, and R. Vivekanantham, “Automatic
fault detection system for mining conveyor using distributed acoustic
sensor,” Measurement, vol. 187, p. 110330, Jan. 2022, doi:
10.1016/j.measurement.2021.110330.
[23] S. Joshi and J. W. H. Price, “A comparative study on application of
design codes for prediction of fatigue life of a mining dragline
cluster,” Engineering Failure Analysis, vol. 16, no. 5, pp. 1562–
1569, Jul. 2009, doi: 10.1016/j.engfailanal.2008.10.006.
[24] B. P. Numbi, J. Zhang, and X. Xia, “Optimal energy management
for a jaw crushing process in deep mines,” Energy, vol. 68, pp. 337–
348, Apr. 2014, doi: 10.1016/j.energy.2014.02.100.