Content uploaded by Attia Hussien Gomaa
Author content
All content in this area was uploaded by Attia Hussien Gomaa on Dec 03, 2024
Content may be subject to copyright.
International Journal of Modern Studies in Mechanical Engineering (IJMSME)
Volume 10, Issue 1, 2024, PP 20-35
ISSN 2454-9711 (Online)
DOI: https://doi.org/10.20431/2454-9711.1001003
www.arcjournals.org
Enhancing Proactive Maintenance of Critical Equipment by Inte-
grating Digital Twins and Lean Six Sigma Approaches
Attia Hussien Gomaa
Mechanical Eng. Department, Faculty of Eng. Shubra, Benha University, Cairo, Egypt.
1. INTRODUCTION
Proactive maintenance is a proactive policy that aims to identify, analyze, and correct the root cause of
a failure before it causes further problems and leads to machinery failure. Implementing this policy can
enhance reliability, availability, maintainability, and safety (RAMS), [11]. As depicted in Figure 1, a
digital twin (DT) is a digital version of a physical object or system. It can successfully model a virtual
object from its physical counterpart. The main function of a DT is to provide a two-way data flow
between the virtual and physical entity so that it can continuously upgrade and improve the physical
counterpart, [5,6]. NASA first used the term digital twin in 2010, which was described as “an integrated,
multi-physics, multi-scale, probabilistic simulation of a vehicle or system that uses the best available
physics models, sensor updates, fleet history, etc., to simulate the life of its flying twin.” [32,38]. Mi-
chael Graves was the first to propose the term DT, [12,37]. Recently, DT has been utilized in various
manufacturing fields, and it is promoting positive developments in these fields, [16,19]. Kritzinger, [23]
recognized three levels of DT integration, namely digital model, digital shadow, and digital twin, as
shown in Figure 2. Attaran, [3] mentioned the main DT applications in manufacturing, as presented in
Figure 3. Many diagnostic tools are available to identify and analyze the root causes of failures. Failure
Mode Effects and Criticality Analysis (FMECA) is the most common diagnostic method, which consists
of two analyses; the Failure Mode and Effects Analysis (FMEA) and the Criticality Analysis (CA),
[11,18,37,40,43]. DT enables maintenance management to accurately identify equipment status, proac-
tively predict faults, and enhance reliability, [1,2,4]. DT contains a set of adaptive models that can
emulate the behavior of a physical system in a virtual system, obtaining real-time data to update itself
along its life cycle, [3,39]. Figure 4 shows an equivalent representation of the general architecture of
DT, [56].
*Corresponding Author:
Attia Hussien Gomaa ,Mechanical Eng. Department, Faculty of Eng. Shubra,
Benha University, Cairo, Egypt.
Abstract: Proactive maintenance is a policy aimed at identifying the root cause of failure and correcting it
before it causes other problems and leads to machinery failure and breakdown. Implementing this policy can
enhance reliability, availability, maintainability, and safety (RAMS) at low cost. Digital Twin (DT) and Lean
Six Sigma (LSS) are useful tools to enhance proactive maintenance. DT is a digital copy of a physical object
whose applications will play a leading role in the future of smart manufacturing. DTs facilitate real-time
monitoring and investigation, improve decision-making, and enhance performance. LSS is the industry's most
recognized approach to process continuous improvement, focusing on eliminating waste, reducing variation,
and improving process efficiency, effectiveness, and customer satisfaction. This study reviewed and analyzed
the LSS methodology and the DT approach (DTs-LSS) to improve proactive maintenance management. It
explored the fact that previous studies have paid limited attention to DTs-LSS. Furthermore, this study provides
a comprehensive roadmap for future research initiatives aiming to utilize technology design teams' capabilities
fully. To the authors' knowledge, this is the first time that the structure and tools of DTs and LSSs have been
combined in a hybrid framework for enhancing proactive maintenance. Finally, this study's results will be
valuable to professionals who want and aspire to implement technological design to achieve maintenance
excellence.
Keywords: Proactive Maintenance, Fault Prediction, Digital Twin, Lean Six Sigma, Continuous Improvement
Fig1Digitaltwin illustration.
Fig2. Digital twin Levels of integration.
Fig3. Digital twin applications in manufacturing.
Fig4. Equivalent representation of the general architecture of DT.
Organizations constantly seek ways to enhance operations efficiency, reduce costs, and improve com-
petitiveness. In this effort, Lean Six Sigma (LSS) tools provide structured approaches to streamline
operations and improve efficiency and effectiveness. The main objectives of LSS are to improve process
quality, improve production rate, reduce delivery time, reduce production cost, and improve customer
satisfaction. DMAIC is a specific framework for process continuous improvement within LSS that in-
cludes, (D) defining the problems and objectives, (M) measuring the current situation, (A) analyzing
the problem's root causes, (I) implementing a workable solution (I), and (C) controlling the process to
ensure and maintain the continuous improvement. Figure 5 shows the most popular LSS tools. By using
these tools and techniques, the organization can improve business processes, [70,71].
Fig5.Main LSS tools in maintenance operations, [70,71].
This study focuses on the performance and applications of DTs and LSS in proactive maintenance pol-
icies and the importance of maintenance management for improving equipment RAMS (reliability,
availability, maintainability, and safety).
After this introduction, this paper is organized as follows: In Section 2, the literature review is carried
out. In Section 3, the research gap is identified. Section 4 includes the frameworks for proactive mainte-
nance. Finally, Section 5 focuses on conclusions and future directions.
2. LITERATURE REVIEW
Firstly, the DT technique and its applications in proactive maintenance are reviewed. Then the literature
on LSS technology and its applications in proactive maintenance are investigated.
2.1. Review of Digital Twins in Proactive Maintenance
Digital twins (DT) can provide a real-time response to the manufacturing system and increase flexibility
and reliability, [13]. According to Hu, [16] Figure 6 illustrates some of the key milestones in the devel-
opment of DT. In 2016, Siemens used DT devices in Industry 4.0, resulting in a tremendous growth in
related publications.
Fig6. The milestones of DT development, [16].
Proactive maintenance can reduce failure risks, improve system uptime, extend the equipment life, and
lower process downtime losses. DT can model individual equipment or processes to identify variations
that indicate the need for preventive maintenance. The goal is to estimate, predict, detect, or diagnose
the condition of the component for more effective maintenance. This can prevent costly failures before
a serious problem occurs. They can also determine if better materials or processes can be used or help
improve cycle times, load levels, and tool calibrations, [20,46]. The application of DTs enables the
monitoring of the condition and prediction of abnormal conditions in machine tools. This greatly en-
hances the safe and efficient operation of mechanical process systems. Parameter optimization plays a
crucial role in the optimization of the operation process. Traditional parameter optimization methods
rely on manual experience and often involve high levels of uncertainty. DT operation process facilitates
the suppression of errors and the optimization of operating parameters, thus laying the foundation for
achieving high-quality and high-level operation, [16].
DT represents the innovation that has spurred evolution and adaptation in the aerospace industry. For
instance, employing DT for an aircraft or rocket ship is believed to enhance global tracking accuracy
by 147%. In a recent survey, 75% of Air Force executives favored DT solutions for their industry. DT
enables engineers to ensure the safety of the aircraft by looking into the potential aircraft’s problem
before any danger. For example, Boeing, the world’s largest aerospace company, uses DT solutions to
improve the safety of the parts and systems used to manufacture commercial and military airplanes.
DTs of specific aircraft models enable technicians to use augmented reality (AR) overlaying the DT
data on the real plane, facilitating faster and more accurate inspections and improving maintenance
efficiency. As a result, Boeing has achieved a 40 percent improvement in the quality of the parts and
systems, [29,50]. According to GE Research, [9] GE’s DT technology is revolutionizing how the avi-
ation industry handles maintenance. Predicting engine wear, such as the blade wear on the GE90, saves
airlines millions of dollars in costs and prevents aircraft from landing unexpectedly, especially in areas
with sand, a major contributor to the problem.
According to Pinello [33], the European Space Agency (ESA) also adopted the DT approach for its
ExoMars mission. They built Amalia, a physical and DT of the Rosalind Franklin rover. This duo serves
a vital purpose: anticipating and solving potential problems before they occur on the Martian surface.
Overall, using both physical and DTs significantly increases mission success by minimizing risks and
improving rover performance.
DTs have been increasingly used in condition monitoring and fault diagnosis (CMFD) in recent years.
Table (1) shows the survey of DTs in maintenance over the past years. The details of these studies are
explained in the next section.
Table 1. Survey of DTs in Proactive Maintenance, (2017 to August 2024).
2017
2
[40,42]
2018
3
[23,44,50]
2019
7
[1,2,29,34,41,43,53]
2020
4
[7,14,19,25]
2021
10
[13,20,27,31,35,37,47,48,51,52]
2022
9
[10,15,22,30,32,45,56,57,59]
2023
12
[4,6,9,26,28,33,36,39,46,48,55,58]
August 2024
10
[3,5,8,11,16,17,21,24,49,54]
Tao, [42] adopted the concept of a DTs workshop, providing theoretical support for industry applica-
tions by discussing its characteristics, composition, operating mechanism, and key technologies. Tao,
[44] suggested a five-dimension DT model for complex systems to improve the accuracy of prognosis.
Qiao, [34] developed a data-driven model for DT, together with a hybrid model prediction method based
on deep learning that creates a prediction technique for enhanced machining tool condition prediction.
Xu, [53] studied a two-stage DT-assisted method based on deep migration learning. This method iden-
tifies potential problems that may not have been considered during the design phase and uses deep
neural network-based diagnostic models for fault diagnosis. Aivaliotis, [2] presented a methodology to
calculate the Remaining Useful Life (RUL) of machinery equipment by utilizing physics-based simu-
lation models and the DT concept, to enable predictive maintenance for manufacturing resources using
Prognostics and health management (PHM) techniques.
Luo, [25] suggested a hybrid DT model that consists of model-based DTs and data-driven DTs to take
into consideration the environmental variations in the life cycle of the tool. To realize reliable predictive
maintenance of CNC machine tools, a hybrid approach driven by DT is studied. Xia, [51] developed a
DT model for machinery fault diagnosis where the DT is built by establishing the simulation model
which can be updated through the real-time data collected from the physical asset. The proposed DT is
validated through a case study of triplex pump fault diagnosis. Xiong, [52] investigated the predictive
maintenance model of an aero-engine driven by DTs. Through the consistent evaluation of virtual data
assets and real data assets, the effectiveness of the model is verified. Experimental results show that
when the dataset used to train the model is 80%, the model prediction has high accuracy. Wang, [48]
developed a DT model including a geometric model, physical model, behavior model, and rule model
to perform fault prediction of the autoclave to generate simulated data to address the problem of insuf-
ficient data for fault prediction. The effectiveness of the proposed model is verified through result anal-
ysis. Olatunji, [31] discussed an overview of the application of DT technology in the fault diagnosis
and condition monitoring of wind turbine mechanical components. Qin, [35] proposed a DT model of
life-cycle rolling bearing driven by the data-model combination. By comparing the obtained DT result
with the signal measured in the time domain and frequency domain, the effectiveness of the developed
model is verified.
Refer to Xiong, [52] DTs solutions are widely used in the aerospace industry for aircraft maintenance
and tracking, weight monitoring, accurate determination of weather conditions, flight time measurement,
catastrophic failure analysis, safety and security management, and failure detection. Moghadam and
Nejad, [30] presented a DT-based condition monitoring and fault diagnosis (CMFD) approach for off-
shore drivetrain systems, where the DT in the study includes a torsional dynamic model, online meas-
urements, and fatigue damage estimation. The remaining useful life of the drivetrain can be estimated
by means of the DT. Kim, [22] utilized various environmental information to design a predictive model
for offshore WT power generation based on DT. The proposed system enables an accurate representa-
tion of the offshore WT power generation and makes contributions to the safety of the power system.
Hosamo, [15] suggested a DT predictive maintenance framework for air handling units (AHU) to over-
come the limitations of facility maintenance management (FMM) systems now in use in buildings. The
proposed framework was tested in a real-world case study.
Zhong, [58] reviewed the increasing research interest in DTs-based predictive maintenance in the man-
ufacturing industry. The predictive maintenance approaches based on DTs are introduced. Wang, [48]
proposed a real-time planetary gear fault diagnosis method by combining the atom search optimization-
support vector machine and DTs which can significantly improve the operation of wind turbines.
Reimann, [36] developed a DT model of a wind turbine. The model was evaluated in simulations using
real measurement data of the wind speed from a research wind turbine. Luo, [25] suggested a DT system
for wind turbine blades, which can construct a DT in virtual space that is completely equivalent to the
wind turbine blades, reflecting in real time the operational data and status of the wind turbine blades,
and realizing online monitoring and predictive maintenance of the wind turbine blades. Van-Dinter, [46]
conducted domain analysis to model key features and synthesize relevant literature. A case study on
fault diagnosis using DFDD in a vehicle body-side production line is presented. The results demonstrate
the superiority and applicability of the proposed method. Yang, [55] developed a complex fault diagno-
sis method using DT by combining virtual and real data. Field data from an offshore platform in the
South China Sea were used to demonstrate the effect of the suggested method. The results indicate that
the proposed method is very effective for complex faults of production control systems.
Inturi, [17] reported a review study focusing on the definitions, methods, applications, and performance
of different aspects of DTs in the context of transportation and industrial machinery. This review sum-
marizes how individual aspects of DTs are extremely useful for lifelong design, manufacturing, or de-
cision-making. Liu, [24] developed an innovative DT-based anomaly detection framework for real-time
tool condition monitoring (TCM). The ‘‘data flow connections’’ involve real-time measured vibration
data and machine tool numerical controller (NC) signals providing real-time information on machine
tool dynamics and various machining processes. Experimental studies have demonstrated the effective-
ness of the proposed method, especially for complicated machining processes. Gao, [8] discussed the
concept of post-disaster recovery for power DTs systems to study rational approaches to enhance the
post-disaster monitoring capability of such systems after significant disasters. The results indicate that
the proposed branch-and-limit algorithm greatly enhances the monitoring capabilities of the resource-
constrained power system, thus enhancing its stability and emergency response mechanisms. Xue, [54]
developed a DT-driven fault diagnosis method for CNC machine tools. By using the spindle of a CNC
machine as an example, the deterioration of spindle stiffness during operation is effectively diagnosed,
which confirms the effectiveness and applicability of the proposed method. Karkaria, [21] discussed a
DT framework for predictive maintenance of long-term physical systems. Using tire health monitoring
as an application, they demonstrate how the DT framework can be used to enhance the safety and effi-
ciency of automobiles. The proposed framework effectively embodies a physical system, leveraging
big data and machine learning for predictive maintenance, model updates, and decision-making. Finally,
Wang, [49] developed a novel intelligent state evaluation and maintenance arrangement (iSEMA) sys-
tem based on DT, which can accurately evaluate the state of wind turbines, detect faults in the early
stage, and provide useful information or warnings to operators and help them to efficiently arrange
maintenance tasks.
2.2. Review of Lean Six Sigma in Proactive Maintenance
LSS tools have been increasingly used in proactive maintenance in recent years. Table (2) shows the
survey of LSS tools in maintenance over the past years. For example, Al Farihi,et al., [60] proposed a
lean maintenance methodology in an automotive company to reduce machine breakdown and mainte-
nance downtime and improve process efficiency. Several steps were used to solve the problem: root
cause analysis, determining the TPM pillars applied, RCM, and realization of TPM pillars. Trubetskaya
et al., [78] developed an LSS-DMAIC framework for optimizing maintenance shutdown performance
in the industry. They presented a case study applying the proposed model to Ireland’s largest dairy
processing site to optimize the annual maintenance shutdown. The objective was to deliver a 30% re-
duction in the duration of the overhaul, enabling an extension of the processing season. Gomaa, [70,71]
discussed the importance of LSS tools in proactive maintenance management. LSS critical failure fac-
tors (CFFs) in project management were discussed. A generic LSS-MM framework was proposed and
validated with a case study conducted in a petrochemical company in Egypt. A case study of a feedwater
pump station in a steam system has been used to illustrate the proposed framework. Results indicated
that the proposed methodology is successful in identifying the critical equipment and improving mainte-
nance efficiency and effectiveness. For example, overall equipment effectiveness (OEE) improved from
50% to 68%, the sigma level improved from 2.53 to 2.88, and maintenance process efficiency improved
from 62.3% to 69.7 %. Imanov et al., [73] conducted a Six Sigma DMAIC framework for the identifi-
cation of its applicability in the development of a maintenance task card for an engine replacement on
the Boeing 747-8 using PM, and the essential results can be summarized as follows: Engine replacement
maintenance task cards decreased by 18 items, Total saving man hours on engine replacement consist
of 68 h., and Total saving man hours on equipment removal and installation consist of 48 h.
Table 2.Survey of LSS in Proactive Maintenance, (2014 to August 2024).
2014
1
[80]
2015
1
[61]
2016
0
-
2017
2
[69,81]
2018
2
[62,76]
2019
0
-
2020
5
[65,66,67,72,75]
2021
1
[73]
2022
2
[64,74]
2023
6
[60,68,70,77,78,79]
August 2024
2
[63,71]
3. RESEARCH GAP ANALYSIS
The literature review shows that the application of DT and LSS techniques in proactive maintenance
remains very important for managing the maintenance of critical equipment to improve equipment
RAMS (reliability, availability, maintainability, and safety) and achieve maintenance excellence. How-
ever, there is still a need for a common platform based on creating a physical model via a common
methodology. This is a requirement for implementing the DT and LSS concept of proactive maintenance.
Moreover, implementing DT technology, for maintenance activities in a production plant, requires cre-
ating a DT for each machine. Furthermore, to the authors' knowledge, there is no research demonstrating
that the structure and tools of DTs and LSS have been combined into a hybrid framework. Finally, a
more detailed review of the literature should also be conducted to identify further gaps, which will be
addressed within the framework of constructing and fine-tuning the proposed model.
4. PROPOSED FRAMEWORKS FOR IMPROVING PROACTIVE MAINTENANCE
Firstly, the DT framework is proposed to improve proactive maintenance. Then the LSS framework is
suggested to enhance proactive maintenance.
4.1. DTs Frameworks for Improving Proactive Maintenance
As mentioned earlier, manufacturing maintenance costs and downtime losses are very high in different
sectors, which justifies the investment in creating DTs to optimize maintenance activities. Figure 7
shows a DT model in maintenance, [10]. According to Dihan [5], data analysis is the technology driver
of a successful DT system. Since data is the fundamental difference between a successful and unsuc-
cessful system, proper guidance of data structure should be given due attention. Figure 8 shows the DT
data analysis process for building a successful DT.
Fig7. DT model in maintenance.
Fig8. DTs Data analysis process, [5].
Hosamo, [15] suggested a DT predictive maintenance framework for air handling units (AHU). The
proposed framework utilizes DT technology for fault detection and diagnostics and predicts the condi-
tion of the building components so that the facility management staff can make better decisions at the
right time. Figure 9 shows the principle of a DT in proactive maintenance. The proposed framework
includes three main steps, Data acquisition, predictive maintenance process, and BIM model for infor-
mation visualization and monitoring. Spatial information can be obtained from the BIM model. The
BIM model was integrated with predictive maintenance results to support decision-making by develop-
ing a plug-in extension for Autodesk Revit using C sharp so that the FM team can easily understand the
data. The three main levels of this framework will be explained in detail in the following sections. For
facility management, COBie (Construction Operations Building Information Exchange) and Industrial
Foundation Classes (IFC) are information exchange specifications for the lifetime capture and transfer
of information. Figure 10 shows COBie components.
Fig9. DT predictive maintenance framework, [15].
Fig10. Standard COBie components, [15].
Mihai et al., [27] developed a framework that aims to achieve optimized predictive maintenance by
leveraging predominantly time-indexed streaming sensor data, along with configuration data coming
from the digital twin of the Cyber-Physical Factory. The developed framework is illustrated in Figure
11, which consists of: the data acquisition block, the pre-processing block, the database, the time-series
anomaly detection block, the RUL predictor block, and the monitoring dashboard.
Fig11. A Digital Twin Framework for Predictive Maintenance, [27].
Karkaria, [21] introduced a DT framework for proactive maintenance of long-term physical systems.
Figure 12 shows the tire health DT framework demonstrating the flow of information, and important
components of DT like offline training, model update, and decision making. As shown in this figure,
the digital twin begins with the offline training of the Tire Health Temporal Fusion Transformer (TFT)
model in Step 1, leveraging historical datasets which has operating parameters (𝑇�!) - conditions under
which the tire operates, usage parameters (𝑈�!) - how the tire is used, and state parameters (𝑀�!) - the
current condition of the tire. Additionally, within our digital twin framework, we get our dataset with
inputs derived from a physics-based Tire Design Finite Element Method (FEM) integrating physical
insights with measured data. Incorporating a physics-based Tire Design Finite Element Method (FEM)
is crucial to accurately understand the tire's physics-based state, ensuring a comprehensive analysis of
its condition through the integration of physical principles with observed data. Then the Tire Health
TFT model, a critical component of the Tire Health Digital Twin, facilitates real-time predictions of the
damage state. A continuous quantity, named as Remaining Casing Potential (RCP), is considered as the
damage state parameter). RCP serves as a key indicator of tire endurance damage, allowing for proac-
tive maintenance decisions. The predictions by the Tire Health TFT model are subsequently compared
with real-world instances of tire damage. This comparison allows us to quantify the discrepancy, effec-
tively measuring the difference between the model's predictions and the actual tire damage data in Step
2. We utilize observed discrepancies to refine our Tire Health TFT model. It is important to highlight
that, following an update, our model evolves into a hybrid version. Despite this transformation, we
continue to refer to it as the Tire Health TFT model for consistency and clarity in our discussion in this
paper. Then the updated Tire Health TFT model, with the Tire State Decision Algorithm in Step 3,
informs timely tire replacement decisions. Thus, our tire health digital twin has the surrogate model,
which is updated in real-time, and aids in making predictive maintenance decisions.
Fig12. Tire health digital twin framework, [21].
4.2. LSS Frameworks for Enhancing Proactive Maintenance
Trubetskaya et al., [78] developed an LSS framework for improving maintenance operations. Figure 13
illustrates a graphic of the DMAIC, TAM, and LSS-DMAIC approaches and how they could be visual-
ized to complement each other. These are important to consider in the further DMAIC-TAM methodol-
ogy enhancements as three distinct tools working towards a common goal. On the other hand, Gomaa,
[70,71] proposed a general framework for LSS to improve maintenance processes and validated it
through a case study conducted in a petrochemical company, as shown in Table (3), [60,62,64,70,71,78].
Visualize DMAIC, TAM, and TPM approaches that complement each other, [78].
Proposed LSS Roadmap for improving maintenance operations.
Approach
Maintenance objectives
Main LSS Tools
Current
Situation
Analysis
- Maintenance process description
- Maintenance KPIs dashboard
Process mapping (process layout, process
flow chart, and SIPOC diagram)
Voice of the customer (VOC)
Maintenance performance evaluation
Leading and lagging KPIs
Benchmarking
Performance gap analysis
KPIs dashboard
Define the problem statement
Establish the objectives and targets
Responsibility matrix (RACI)
Prepare a Project Charter
Construct LSS-DMAIC framework
Kaizen
Approach
- Improving maintenance Staff's culture
& productivity
- Enhancing maintenance resource
productivity
Visual control (5S)
Standardize work (SW)
Root cause failure analysis (RCFA)
Mistake proofing (Poka-yoka)
Lean
Approach
- Improving maintenance process value-
added
- Reducing maintenance process wastes
Total productive maintenance (TPM)
Overall equipment effectiveness (OEE)
Value-added time analysis
Value stream mapping (VSM)
Lean waste analysis (8 wastes)
Just in time (JIT)
Breakdown structure analysis
Approach
Maintenance objectives
Main LSS Tools
Networking and Gantt chart
Six Sigma
Approach
- Reducing equipment failures
- Reducing equipment variance
Critical to quality (CTQ) analysis
Sigma-level analysis
SQC for failure analysis
Pareto analysis of main failures
Root cause failure analysis (RCFA)
Cause and effect diagram (Fishbone)
Failure mode effect analysis (FMEA)
Equipment reliability analysis
Reliability centered maintenance (RCM)
5. CONCLUSION AND FURTHER WORK
Proactive maintenance is a policy that aims to identify the root cause of a failure and correct it before it
causes further problems and leads to machinery failure. Implementing this policy can enhance reliability,
availability, maintainability, and safety (RAMS). This paper focuses on reviewing the applications of
digital twins (DT) and Lean Six Sigma (LSS) in proactive maintenance. DT can be used as a data-driven
digital concept or technology to effectively address critical equipment maintenance issues. DT enables
maintenance management to accurately determine equipment status, proactively predict faults, and en-
hance reliability. LSS is the industry's most recognized approach to continuous improvement, focusing
on eliminating waste, reducing variation, and improving process efficiency, effectiveness, and customer
satisfaction. The application of DT and LSS technologies remains a critical proactive technology for
critical equipment to improve equipment RAMS and achieve maintenance excellence. Several DT and
LSS frameworks for proactive maintenance have been discussed. Furthermore, this study provides a
comprehensive roadmap for future research initiatives aiming to utilize technology design teams' capa-
bilities fully. To the authors' knowledge, this is the first time that the structure and tools of DTs and
LSSs have been combined in a hybrid framework.
In future activities, the author plans to integrate and implement DT methodology and Lean Six Sigma
approach into a more general maintenance management framework for critical equipment whose main
role will be to assess and improve the health status of machines, improve reliability, and plan mainte-
nance activities.
Abbreviations
ATM
Turnaround maintenance
CMFD
Condition monitoring and fault diagnosis
DT
Digital twins
LSS
Lean six sigma
RAMS
Reliability, availability, maintainability, and safety
6. CONFLICTS OF INTEREST
REFERENCES
[1] Aivaliotis, P., Georgoulias, K. and Alexopoulos, K., (2019 a), “Using digital twin for maintenance
applications in manufacturing: State of the Art and Gap analysis. In 2019 IEEE International Conference on
Engineering, Technology and Innovation (ICE/ITMC) (pp. 1-5). IEEE.
https://www.researchgate.net/publication/333893836
[2] Aivaliotis, P., Georgoulias, K., Chryssolouris, G., (2019 b), “The use of Digital Twin for predictive
maintenance in manufacturing”, International Journal of Computer Integrated Manufacturing, 32: 11, pp.
1067-1080. https://doi.org/10.1080/0951192X.2019.1686173
[3] Attaran, S., Attaran, M. and Celik, B. G., (2024), “Digital Twins and Industrial Internet of Things:
Uncovering operational intelligence in industry 4.0”, Decision Analytics Journal, 10, p. 100398.
https://doi.org/10.1016/j.dajour.2024.100398
[4] Chen, C., Fu, H., Zheng, Y., Tao, F., Liu, Y., (2023), “The advance of digital twin for predictive maintenance: the
role and function of machine learning”, J Manuf Syst, vol. 71, pp. 581-594.
https://doi.org/10.1016/j.jmsy.2023.10.010
[5] Dihan, M. S., Akash, A. I., Tasneem, Z., Das, P., Das, S. K., Islam, M. R., Islam, M. M., Badal, F. R., Ali, M. F.,
Ahmed, M. H. and Abhi, S. H., 2024. Digital twin: Data exploration, architecture, implementation and future.
Heliyon.
[6] Emmert-Streib, F., 2023. Defining a digital twin: A data science-based unification. Machine Learning and
Knowledge Extraction, 5(3), pp. 1036-1054. https://doi.org/10.3390/make5030054
[7] Errandonea, I., Beltrán, S., & Arrizabalaga, S. (2020). Digital Twin for maintenance: A literature review.
Computers in Industry, 123, 103316. https://doi.org/10.1016/j.compind.2020.103316
[8] Gao, S., Wang, W., Chen, J., Wu, X. and Shao, J., 2024. Optimal decision-making method for equipment
maintenance to enhance the resilience of power digital twin system under extreme disaster. Global Energy
Interconnection, 7(3), pp. 336-346. https://doi.org/10.1016/j.gloei.2024.06.005
[9] GE Research, Digital twin creation, 2023, Retrieved 12-27-2023. https://www.ge.com/research/offering/digital-
twin-creation.
[10] Gomaa, Attia H., (2022), “Enhancing Maintenance Management of Critical Equipment Using Digital Twin”,
Comprehensive Research and Reviews in Engineering and Technology, (CRRET), vol. 1, no. 1, pp. 45-55.
https://doi.org/10.58175/gjret.2022.1.1.0015
[11] Gomaa, Attia H., (2024), “Improving Shutdown Maintenance Management Performance Using Lean Six Sigma
Approach: A Case Study”, International Journal of Applied and Physical Sciences, IJAPS, Vol. 10, No. 1, pp.
1-14. https://dx.doi.org/10.20469/ijaps.10.50001
[12] Grieves, M., (2014), "Digital twin: Manufacturing excellence through virtual factory replication", White
Paper, vol. 1, no. 2014, pp. 1-7.
[13] He, B. and Bai, K. J., (2021) "Digital twin-based sustainable intelligent manufacturing: A review," Adv.
Manuf., vol. 9, no. 1, pp. 1-21. https://doi.org/10.1007/s40436-020-00302-5
[14] Heim, S., Clemens, J., Steck, J. E., Basic, C., Timmons, D. and Zwiener, K., (2020), December. Predictive
maintenance on aircraft and applications with digital twin. In 2020 IEEE International Conference on Big
Data (Big Data), pp. 4122-4127. DOI: 10.1109/BigData50022.2020.9378433
[15] Hosamo, H. H., Svennevig, P. R., Svidt, K., Han, D. and Nielsen, H. K., 2022. A Digital Twin predictive
maintenance framework of air handling units based on automatic fault detection and diagnostics. Energy and
Buildings, 261, p. 111988. https://doi.org/10.1016/j.enbuild.2022.111988
[16] Hu, S., Li, C., Li, B., Yang, M., Wang, X., Gao, T., Xu, W., Dambatta, Y. S., Zhou, Z. and Xu, P., (2024).
Digital Twins Enabling Intelligent Manufacturing: From Methodology to Application. Intelligent and
Sustainable Manufacturing, 1(1), p. 10007, pp. 1-22. https://doi.org/10.35534/ism.2024.10007
[17] Inturi, V., Ghosh, B., Rajasekharan, S. G. and Pakrashi, V., (2024). A Review of Digital Twinning for
Rotating Machinery. Sensors, 24(15), p. 5002, pp. 1-33. https://doi.org/10.3390/s24155002
[18] Jay, L., W. Fangji, Z. Wenyu, G. Masoud, L. Linxia, and S. David., (2014), “Prognostics and Health
Management Design for Rotary Machinery systems -Reviews Methodology and Applications”, Mechanical
Systems and Signal Processing 42, pp. 314–334. https://doi.org/10.1016/j.ymssp.2013.06.004
[19] Jones, D., Snider, C., Nassehi, A., Yon J. and Hicks, B., (2020), "Characterising the digital twin: A systematic
literature review", CIRP J. Manuf. Sci. Technol., vol. 29, pp. 36-52.
https://doi.org/10.1016/j.cirpj.2020.02.002
[20] Kang, Z., Catal, C. and Tekinerdogan, B., (2021), “Remaining useful life (RUL) prediction of equipment in
production lines using artificial neural networks” Sensors, 21(3), p. 932. https://doi.org/10.3390/s21030932
[21] Karkaria, V., Chen, J., Luey, C., Siuta, C., Lim, D., Radulescu, R. and Chen, W., 2024. A Digital Twin
Framework Utilizing Machine Learning for Robust Predictive Maintenance: Enhancing Tire Health
Monitoring. arXiv preprint arXiv: 2408. 06220 https://doi.org/10.48550/arXiv.2408.06220
[22] Kim, C., (2022), "Design, implementation, and evaluation of an output prediction model of the 10 mw
floating offshore wind turbine for a digital twin," Energies, vol. 15, no. 17, art no. 6329, pp. 1-
16. https://doi.org/10.3390/en15176329
[23] Kritzinger, W., Karner, M., Traar, G., Henjes, J. and Sihn, W., 2018. Digital Twin in manufacturing: A
categorical literature review and classification. Ifac-PapersOnline, 51(11), pp. 1016-1022.
https://doi.org/10.1016/j.ifacol.2018.08.474
[24] Liu, Z.; Lang, Z. Q.; Gui, Y.; Zhu, Y. P.; Laalej, H., (2024), “Digital twin-based anomaly detection for real-
time tool condition monitoring in machining”, J. Manuf. Syst., 75, pp. 163–173.
https://doi.org/10.1016/j.jmsy.2024.06.004
[25] Luo W, Hu T, Ye Y, Zhang C, Wei Y., (2020), “A hybrid predictive maintenance approach for CNC machine
tool driven by digital twin”, Robot Comput-Integr Manuf, 65: 101974, pp. 1-16.
https://doi.org/10.1016/j.rcim.2020.10197
[26] Luo, H., Wang, L., Sun, W. and Lu, C., (2023), “Intelligent Monitoring and Maintenance of Wind Turbine
Blades Driven by Digital Twin Technology”, 3rd International Conference on New Energy and Power
Engineering (ICNEPE), pp. 626-630. DOI: 10.1109/ICNEPE60694.2023.10429668
[27] Mihai, S., Davis, W., Hung, D., Trestian, R., Karamanoglu, M., Barn, B., Prasad, R., Venkataraman, H. and
Nguyen, H. 2021. A digital twin framework for predictive maintenance in industry 4.0. HPCS 2020: 18th
Annual Meeting. Barcelona, Spain (Online Virtual Conference) 22 - 27 Mar 2021 IEEE.
[28] Minghui, H. U., Ya, H. E., Xinzhi, L. I. N., Ziyuan, L. U., Jiang, Z. and Bo, M. A., 2023. Digital twin model
of gas turbine and its application in warning of performance fault. Chinese Journal of Aeronautics, 36(3),
pp. 449-470. https://doi.org/10.1016/j.cja.2022.07.021
[29] Miskinis, C., 2019. Future role of digital twin in the aerospace industry. January. https://www. challenge.
org/insights/digital-twinin-aerospace.
[30] Moghadam FK, Nejad AR., (2022), “Online condition monitoring of floating wind turbines drivetrain by
means of digital twin”, Mech Syst Signal Process, 162: 108087, pp. 1-26.
https://doi.org/10.1016/j.ymssp.2021.108087
[31] Olatunji, O. O., Adedeji, P. A., Madushele, N., & Jen, T.-C. (2021), “Overview of Digital Twin Technology
in Wind Turbine Fault Diagnosis and Condition Monitoring”, IEEE 12th International Conference on
Mechanical and Intelligent Manufacturing Technologies (ICMIMT), pp. 1-7.
DOI: 10.1109/ICMIMT52186.2021.9476186
[32] Onaji, I., Tiwari, D., Soulatiantork, P., Song, B. and Tiwari, A., (2022), “Digital twin in manufacturing:
conceptual framework and case studies”, International journal of computer integrated manufacturing, 35(8),
pp. 831-858. https://doi.org/10.1080/0951192X.2022.2027014
[33] Pinello, L., Giglio, M., Cadini, C. and De Luca, G. F., 2023, September. Development of a space exploration
rover digital twin for damage detection. In PHM Society Asia-Pacific Conference (Vol. 4, No. 1).
DOI https://doi.org/10.36001/phmap.2023.v4i1.3628
[34] Qiao, Q., Wang, J., Ye, L. and Gao, R. X., (2019), “Digital twin for machining tool condition prediction”,
Procedia CIRP, 81, pp. 1388-1393. https://doi.org/10.1016/j.procir.2019.04.049
[35] Qin, Y., Wu, X. and Luo, J., (2021). Data-model combined driven digital twin of life-cycle rolling bearing.
IEEE Transactions on Industrial Informatics, 18(3), pp. 1530-1540. DOI: 10.1109/TII.2021.3089340
[36] Reimann, R., Menzel, S., Holzke, W., Raffel, H. and Orlik, B., (2023), “Development and Evaluation of a
Model for the Implementation of a Digital Twin for a Wind Turbine”, In PCIM Europe 2023; International
Exhibition and Conference for Power Electronics, Intelligent Motion, Renewable Energy and Energy
Management, pp. 1-9. DOI: 10.30420/566091280
[37] Semeraro, C., Lezoche, M., Panetto, H. and Dassisti, M., 2021. Digital twin paradigm: A systematic literature
review. Computers in Industry, 130, p. 103469. https://doi.org/10.1016/j.compind.2021.103469
[38] Shafto, M., Conroy, M., Doyle, R., Glaessgen, E., Kemp, C., LeMoigne, J. and Wang, L., (2010), “Draft
modeling, simulation, information technology & processing roadmap”, Technology area, 11, pp. 1-32.
[39] Soori, M., Arezoo, B. and Dastres, R., 2023. Digital twin for smart manufacturing, A review. Sustainable
Manufacturing and Service Economics, p. 100017. https://doi.org/10.1016/j.smse.2023.100017
[40] Spreafico, C., D. Russo, and Rizzi, C., (2017), “A State-Of-the-art Review of FMEA / FMECA Including
Patents”, Computer Science Review 25, pp. 19–28. https://doi.org/10.1016/j.cosrev.2017.05.002
[41] Tao F, Liu W, Zhang M, Hu T-L, Qi Q, Zhang H, (2019), “Five-dimension digital twin model and its ten
applications”, Comput. Integr. Manuf. Syst., 25, pp. 1-18.
[42] Tao F, Zhang M, Cheng J, Qi Q., (2017), “Digital twin workshop: a new paradigm for future workshop”,
Comput. Integr. Manuf. Syst. 23, pp. 1-9.
[43] Tao F, Zhang M, Liu Y, Nee AY, (2019), "Digital Twin in Industry: State-of-the-Art," in IEEE Transactions
on Industrial Informatics, vol. 15, no. 4, pp. 2405-2415. DOI: 10.1109/TII.2018.2873186
[44] Tao, F., Zhang, M., Liu, Y., & Nee, A. Y. C. (2018). Digital twin driven prognostics and health management
for complex equipment. CIRP Annals, 67(1), pp. 169-172. https://doi.org/10.1016/j.cirp.2018.04.055
[45] Van Dinter, R., Tekinerdogan, B. and Catal, C., (2022), “Predictive maintenance using digital twins: A
systematic literature review”, Information and Software Technology, 151, p. 107008.
https://doi.org/10.1016/j.infsof.2022.107008
[46] Van Dinter, R., Tekinerdogan, B. and Catal, C., (2023), “Reference architecture for digital twin-based
predictive maintenance systems”, Computers & Industrial Engineering, 177, p. 109099, pp. 1-24.
https://doi.org/10.1016/j.cie.2023.109099
[47] Wang, Y., Tao, F., Zhang, M., Wang, L., & Zuo, Y. (2021). Digital twin enhanced fault prediction for the autoclave
with insufficient data. Journal of Manufacturing Systems, 60, pp. 350–359.
https://doi.org/10.1016/j.jmsy.2021.05.015
[48] Wang, Y.; Sun, W.; Liu, L.; Wang, B.; Bao, S.; Jiang, R., (2023), “Fault Diagnosis of Wind Turbine Planetary Gear
Based on a Digital Twin”, Applied Sciences, vol. 13, no. 8, art no. 4776, pp. 1-19.
https://doi.org/10.3390/app13084776
[49] Wang, G., Wei, H.L. and Liu, Z.H., 2024. An intelligent maintenance arrangement for wind turbines based on
digital twin. Academia Engineering, 1(4). Pp. 1-16. https://doi.org/10.20935/AcadEng7391
[50] Woodrow III, B., (2018), “Boeing CEIO talks ‘digital twin’era of aviation”.
[51] Xia, M., Shao, H., Williams, D., Lu, S., Shu, L., & de Silva, C. W., (2021), “Intelligent fault diagnosis of machinery
using digital twin-assisted deep transfer learning”, Reliability Engineering & System Safety, 215, 107938, pp. 1-
9. https://doi.org/10.1016/j.ress.2021.107938
[52] Xiong, M., Wang, H., Fu, Q. and Xu, Y., (2021), “Digital twin–driven aero-engine intelligent predictive
maintenance”, The International Journal of Advanced Manufacturing Technology, 114(11), pp. 3751-3761.
https://doi.org/10.1007/s00170-021-06976-w
[53] Xu, Y., Sun, Y., Liu, X. and Zheng, Y., (2019), “A digital-twin-assisted fault diagnosis using deep transfer learning”,
Ieee Access, 7, pp. 19990-19999. DOI:10.1109/ACCESS.2018.2890566
[54] Xue, R., Zhang, P., Huang, Z. and Wang, J., 2024. Digital twin-driven fault diagnosis for CNC machine tool. The
International Journal of Advanced Manufacturing Technology, 131(11), pp. 5457-5470.
https://doi.org/10.1007/s00170-022-09978-4
[55] Yang, C., Cai, B., Wu, Q., Wang, C., Ge, W., Hu, Z., Zhu, W., Zhang, L. and Wang, L., 2023. Digital twin-driven
fault diagnosis method for composite faults by combining virtual and real data. Journal of Industrial Information
Integration, 33, p. 100469. https://doi.org/10.1016/j.jii.2023.100469
[56] You, Y., Chen, C., Hu, F., Liu, Y. and Ji, Z., 2022. Advances of digital twins for predictive maintenance. Procedia
computer science, 200, pp. 1471-1480. https://doi.org/10.1016/j.procs.2022.01.348
[57] Zhao, J., Feng, H., Chen, Q. and de Soto, B. G., (2022), “Developing a conceptual framework for the application
of digital twin technologies to revamp building operation and maintenance processes”, Journal of Building
Engineering, 49, p. 104028. https://doi.org/10.1016/j.jobe.2022.104028
[58] Zhong, D., Xia, Z., Zhu, Y. and Duan, J., (2023), “Overview of predictive maintenance based on digital twin
technology”, Heliyon, 9(4), pp. 1-23. https://doi.org/10.1016/j.heliyon.2023.e14534
[59] Zhou, C., Xiao, D., Hu, J., Yang, Y., Li, B., Hu, S., Demartino, C. and Butala, M., 2022. An example of digital
twins for bridge monitoring and maintenance: preliminary results. In Proceedings of the 1st Conference of the
European Association on Quality Control of Bridges and Structures: EUROSTRUCT 2021 1 (pp. 1134-1143).
Springer International Publishing. https://doi.org/10.1007/978-3-030-91877-4_129
[60] Al Farihi, A.H., Sumartini, S. and Herdiman, L., 2023. Designing lean maintenance using total productive
maintenance method–a case study at wiring harness production. In E3s web of conferences (Vol. 465, p. 02016).
EDP Sciences.
[61] Aldairi, J., Khan, M. and Munive-Hernandez, J., 2015. A conceptual model for a hybrid knowledge-based
lean six sigma maintenance system for sustainable buildings. In Proceedings of the World Congress on
Engineering (Vol. 2, pp. 1-3).
[62] Alsubaie, B. and Yang, Q., 2018. Maintenance process improvement model by integrating LSS and TPM for
service organisations. In Engineering Asset Management 2016: Proceedings of the 11th World Congress on
Engineering Asset Management (pp. 13-24). Springer International Publishing.
[63] Amrina, E. and Firda, S., 2024, February. Evaluation model of total productive maintenance implementation
for cement plant. In AIP Conference Proceedings (Vol. 2710, No. 1). AIP Publishing.
[64] Antosz, K., Jasiulewicz-Kaczmarek, M., Waszkowski, R. and Machado, J., 2022. Application of Lean Six
Sigma for sustainable maintenance: case study. IFAC-PapersOnLine, 55(19), pp.181-186.
[65] Antosz, K., Pasko, L. and Gola, A., 2020. The use of artificial intelligence methods to assess the effectiveness
of lean maintenance concept implementation in manufacturing enterprises. Applied Sciences, 10(21), p.7922.
[66] Arrascue-Hernandez, G., Cabrera-Brusil, J., Chavez-Soriano, P., Raymundo-Ibañez, C. and Perez, M., 2020,
March. LEAN maintenance model based on change management allowing the reduction of delays in the
production line of textile SMEs in Peru. In Iop conference series: Materials science and engineering (Vol.
796, No. 1, p. 012017). IOP Publishing.
[67] Chinhengo, I., Goriwondo, W.M. and Sarema, B., 2020. Application of lean tools in planned maintenance:
Case study of a coal handling plant at a thermal power station. Zimbabwe: National University of Science
and Technology Bulawayo.
[68] da Silva, R.F., Melani, A.H.D.A., Michalski, M.A.D.C. and de Souza, G.F.M., 2023. Reliability and Risk
Centered Maintenance: A novel method for supporting maintenance management. Applied Sciences, 13(19),
p.10605.
[69] Epler, I., Sokolovic, V., Milenkov, M. and Bukvic, M., 2017. Application of lean tools for improved
effectiveness in maintenance of technical systems for special purposes. Eksploatacja i Niezawodność, 19(4).
[70] Gomaa, A.H., 2023. Maintenance Process Improvement Framework Using Lean Six Sigma: A Case
Study. International Journal of Business & Administrative Studies, 9(1).
[71] Gomaa, A.H., 2024. Improving Shutdown Maintenance Management Performance Using Lean Six Sigma
Approach: A Case Study. International Journal of Applied and Physical Sciences, IJAPS, Vol. 10, No. 1, pp.
1-14. https://dx.doi.org/10.20469/ijaps.10.50001
[72] Hassan, M.N., Barakat, A.F. and Sobh, A.S., 2020, July. Effect of applying lean maintenance in oil and gas
fields. In The international conference on applied mechanics and mechanical engineering (Vol. 19, No. 19th
International Conference on Applied Mechanics and Mechanical Engineering., pp. 1-13). Military Technical
College.
[73] Imanov, T., Yildiz, M. and Koruyucu, E., 2021, June. Development of aircraft maintenance procedures using
lean tools. In International symposium on aviation technology, mro, and operations (pp. 61-65). Cham:
Springer International Publishing.
[74] Korchagin, A., Deniskin, Y., Pocebneva, I. and Vasilyeva, O., 2022. Lean Maintenance 4.0: implementation
for aviation industry. Transportation Research Procedia, 63, pp.1521-1533.
[75] Pinto, G., Silva, F.J.G., Baptista, A., Fernandes, N.O., Casais, R. and Carvalho, C., 2020. TPM
implementation and maintenance strategic plan–a case study. Procedia Manufacturing, 51, pp.1423-1430.
[76] Requeijo, J.F.G., da Costa Feliciano, A.J.P., Calado, J.M.F. and da Eira Dias, A.S.M., 2018. Six sigma
business scorecard approach to support maintenance projects in a collaborative context. Revista produção e
desenvolvimento, 4(1), pp.82-97.
[77] Shannon, N., Trubetskaya, A., Iqbal, J. and McDermott, O., 2023. A total productive maintenance &
reliability framework for an active pharmaceutical ingredient plant utilising design for Lean Six
Sigma. Heliyon, 9(10).
[78] Trubetskaya, A., Ryan, A., Powell, D.J. and Moore, C., 2023. Utilising a hybrid DMAIC/TAM model to
optimise annual maintenance shutdown performance in the dairy industry: a case study. International Journal
of Lean Six Sigma, 15(8), pp.70-92.
[79] Wolska, M., Gorewoda, T., Roszak, M. and Gajda, L., 2023. Implementation and improvement of the total
productive maintenance concept in an organization. Encyclopedia, 3(4), pp.1537-1564.
[80] Youssouf, A., Rachid, C. and Ion, V., 2014. Contribution to the optimization of strategy of maintenance by
lean six sigma. Physics procedia, 55, pp.512-518.
[81] Zasadzień, M., 2017, February. Application of the Six Sigma method for improving maintenance processes–
case study. In International conference on operations research and enterprise systems (Vol. 2, pp. 314-320).
SCITEPRESS.
Attia Hussien Gomaa. Enhancing Proactive Maintenance of Critical Equipment by Integrating Dig-
ital Twins and Lean Six Sigma Approaches. International Journal of Modern Studies in Mechanical Engineer-
ing (IJMSME)”, 10(1), pp.20-35, DOI: https://doi.org/10.20431/2454-9711.1001003.
© 2024 Attia Hussien Gomaa. This is an open-access article distributed under the terms of the
Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any
medium, provided the original author and source are credited.